model.safetensors.index.json
241.6 KB · 2714 lines · json Raw
1 {
2 "metadata": {
3 "total_size": 6779249408
4 },
5 "weight_map": {
6 "model.sam_model.pos_embed": "model-00001-of-000001.safetensors",
7 "model.sam_model.patch_embed.proj.weight": "model-00001-of-000001.safetensors",
8 "model.sam_model.patch_embed.proj.bias": "model-00001-of-000001.safetensors",
9 "model.sam_model.blocks.0.norm1.weight": "model-00001-of-000001.safetensors",
10 "model.sam_model.blocks.0.norm1.bias": "model-00001-of-000001.safetensors",
11 "model.sam_model.blocks.0.attn.rel_pos_h": "model-00001-of-000001.safetensors",
12 "model.sam_model.blocks.0.attn.rel_pos_w": "model-00001-of-000001.safetensors",
13 "model.sam_model.blocks.0.attn.qkv.weight": "model-00001-of-000001.safetensors",
14 "model.sam_model.blocks.0.attn.qkv.bias": "model-00001-of-000001.safetensors",
15 "model.sam_model.blocks.0.attn.proj.weight": "model-00001-of-000001.safetensors",
16 "model.sam_model.blocks.0.attn.proj.bias": "model-00001-of-000001.safetensors",
17 "model.sam_model.blocks.0.norm2.weight": "model-00001-of-000001.safetensors",
18 "model.sam_model.blocks.0.norm2.bias": "model-00001-of-000001.safetensors",
19 "model.sam_model.blocks.0.mlp.lin1.weight": "model-00001-of-000001.safetensors",
20 "model.sam_model.blocks.0.mlp.lin1.bias": "model-00001-of-000001.safetensors",
21 "model.sam_model.blocks.0.mlp.lin2.weight": "model-00001-of-000001.safetensors",
22 "model.sam_model.blocks.0.mlp.lin2.bias": "model-00001-of-000001.safetensors",
23 "model.sam_model.blocks.1.norm1.weight": "model-00001-of-000001.safetensors",
24 "model.sam_model.blocks.1.norm1.bias": "model-00001-of-000001.safetensors",
25 "model.sam_model.blocks.1.attn.rel_pos_h": "model-00001-of-000001.safetensors",
26 "model.sam_model.blocks.1.attn.rel_pos_w": "model-00001-of-000001.safetensors",
27 "model.sam_model.blocks.1.attn.qkv.weight": "model-00001-of-000001.safetensors",
28 "model.sam_model.blocks.1.attn.qkv.bias": "model-00001-of-000001.safetensors",
29 "model.sam_model.blocks.1.attn.proj.weight": "model-00001-of-000001.safetensors",
30 "model.sam_model.blocks.1.attn.proj.bias": "model-00001-of-000001.safetensors",
31 "model.sam_model.blocks.1.norm2.weight": "model-00001-of-000001.safetensors",
32 "model.sam_model.blocks.1.norm2.bias": "model-00001-of-000001.safetensors",
33 "model.sam_model.blocks.1.mlp.lin1.weight": "model-00001-of-000001.safetensors",
34 "model.sam_model.blocks.1.mlp.lin1.bias": "model-00001-of-000001.safetensors",
35 "model.sam_model.blocks.1.mlp.lin2.weight": "model-00001-of-000001.safetensors",
36 "model.sam_model.blocks.1.mlp.lin2.bias": "model-00001-of-000001.safetensors",
37 "model.sam_model.blocks.2.norm1.weight": "model-00001-of-000001.safetensors",
38 "model.sam_model.blocks.2.norm1.bias": "model-00001-of-000001.safetensors",
39 "model.sam_model.blocks.2.attn.rel_pos_h": "model-00001-of-000001.safetensors",
40 "model.sam_model.blocks.2.attn.rel_pos_w": "model-00001-of-000001.safetensors",
41 "model.sam_model.blocks.2.attn.qkv.weight": "model-00001-of-000001.safetensors",
42 "model.sam_model.blocks.2.attn.qkv.bias": "model-00001-of-000001.safetensors",
43 "model.sam_model.blocks.2.attn.proj.weight": "model-00001-of-000001.safetensors",
44 "model.sam_model.blocks.2.attn.proj.bias": "model-00001-of-000001.safetensors",
45 "model.sam_model.blocks.2.norm2.weight": "model-00001-of-000001.safetensors",
46 "model.sam_model.blocks.2.norm2.bias": "model-00001-of-000001.safetensors",
47 "model.sam_model.blocks.2.mlp.lin1.weight": "model-00001-of-000001.safetensors",
48 "model.sam_model.blocks.2.mlp.lin1.bias": "model-00001-of-000001.safetensors",
49 "model.sam_model.blocks.2.mlp.lin2.weight": "model-00001-of-000001.safetensors",
50 "model.sam_model.blocks.2.mlp.lin2.bias": "model-00001-of-000001.safetensors",
51 "model.sam_model.blocks.3.norm1.weight": "model-00001-of-000001.safetensors",
52 "model.sam_model.blocks.3.norm1.bias": "model-00001-of-000001.safetensors",
53 "model.sam_model.blocks.3.attn.rel_pos_h": "model-00001-of-000001.safetensors",
54 "model.sam_model.blocks.3.attn.rel_pos_w": "model-00001-of-000001.safetensors",
55 "model.sam_model.blocks.3.attn.qkv.weight": "model-00001-of-000001.safetensors",
56 "model.sam_model.blocks.3.attn.qkv.bias": "model-00001-of-000001.safetensors",
57 "model.sam_model.blocks.3.attn.proj.weight": "model-00001-of-000001.safetensors",
58 "model.sam_model.blocks.3.attn.proj.bias": "model-00001-of-000001.safetensors",
59 "model.sam_model.blocks.3.norm2.weight": "model-00001-of-000001.safetensors",
60 "model.sam_model.blocks.3.norm2.bias": "model-00001-of-000001.safetensors",
61 "model.sam_model.blocks.3.mlp.lin1.weight": "model-00001-of-000001.safetensors",
62 "model.sam_model.blocks.3.mlp.lin1.bias": "model-00001-of-000001.safetensors",
63 "model.sam_model.blocks.3.mlp.lin2.weight": "model-00001-of-000001.safetensors",
64 "model.sam_model.blocks.3.mlp.lin2.bias": "model-00001-of-000001.safetensors",
65 "model.sam_model.blocks.4.norm1.weight": "model-00001-of-000001.safetensors",
66 "model.sam_model.blocks.4.norm1.bias": "model-00001-of-000001.safetensors",
67 "model.sam_model.blocks.4.attn.rel_pos_h": "model-00001-of-000001.safetensors",
68 "model.sam_model.blocks.4.attn.rel_pos_w": "model-00001-of-000001.safetensors",
69 "model.sam_model.blocks.4.attn.qkv.weight": "model-00001-of-000001.safetensors",
70 "model.sam_model.blocks.4.attn.qkv.bias": "model-00001-of-000001.safetensors",
71 "model.sam_model.blocks.4.attn.proj.weight": "model-00001-of-000001.safetensors",
72 "model.sam_model.blocks.4.attn.proj.bias": "model-00001-of-000001.safetensors",
73 "model.sam_model.blocks.4.norm2.weight": "model-00001-of-000001.safetensors",
74 "model.sam_model.blocks.4.norm2.bias": "model-00001-of-000001.safetensors",
75 "model.sam_model.blocks.4.mlp.lin1.weight": "model-00001-of-000001.safetensors",
76 "model.sam_model.blocks.4.mlp.lin1.bias": "model-00001-of-000001.safetensors",
77 "model.sam_model.blocks.4.mlp.lin2.weight": "model-00001-of-000001.safetensors",
78 "model.sam_model.blocks.4.mlp.lin2.bias": "model-00001-of-000001.safetensors",
79 "model.sam_model.blocks.5.norm1.weight": "model-00001-of-000001.safetensors",
80 "model.sam_model.blocks.5.norm1.bias": "model-00001-of-000001.safetensors",
81 "model.sam_model.blocks.5.attn.rel_pos_h": "model-00001-of-000001.safetensors",
82 "model.sam_model.blocks.5.attn.rel_pos_w": "model-00001-of-000001.safetensors",
83 "model.sam_model.blocks.5.attn.qkv.weight": "model-00001-of-000001.safetensors",
84 "model.sam_model.blocks.5.attn.qkv.bias": "model-00001-of-000001.safetensors",
85 "model.sam_model.blocks.5.attn.proj.weight": "model-00001-of-000001.safetensors",
86 "model.sam_model.blocks.5.attn.proj.bias": "model-00001-of-000001.safetensors",
87 "model.sam_model.blocks.5.norm2.weight": "model-00001-of-000001.safetensors",
88 "model.sam_model.blocks.5.norm2.bias": "model-00001-of-000001.safetensors",
89 "model.sam_model.blocks.5.mlp.lin1.weight": "model-00001-of-000001.safetensors",
90 "model.sam_model.blocks.5.mlp.lin1.bias": "model-00001-of-000001.safetensors",
91 "model.sam_model.blocks.5.mlp.lin2.weight": "model-00001-of-000001.safetensors",
92 "model.sam_model.blocks.5.mlp.lin2.bias": "model-00001-of-000001.safetensors",
93 "model.sam_model.blocks.6.norm1.weight": "model-00001-of-000001.safetensors",
94 "model.sam_model.blocks.6.norm1.bias": "model-00001-of-000001.safetensors",
95 "model.sam_model.blocks.6.attn.rel_pos_h": "model-00001-of-000001.safetensors",
96 "model.sam_model.blocks.6.attn.rel_pos_w": "model-00001-of-000001.safetensors",
97 "model.sam_model.blocks.6.attn.qkv.weight": "model-00001-of-000001.safetensors",
98 "model.sam_model.blocks.6.attn.qkv.bias": "model-00001-of-000001.safetensors",
99 "model.sam_model.blocks.6.attn.proj.weight": "model-00001-of-000001.safetensors",
100 "model.sam_model.blocks.6.attn.proj.bias": "model-00001-of-000001.safetensors",
101 "model.sam_model.blocks.6.norm2.weight": "model-00001-of-000001.safetensors",
102 "model.sam_model.blocks.6.norm2.bias": "model-00001-of-000001.safetensors",
103 "model.sam_model.blocks.6.mlp.lin1.weight": "model-00001-of-000001.safetensors",
104 "model.sam_model.blocks.6.mlp.lin1.bias": "model-00001-of-000001.safetensors",
105 "model.sam_model.blocks.6.mlp.lin2.weight": "model-00001-of-000001.safetensors",
106 "model.sam_model.blocks.6.mlp.lin2.bias": "model-00001-of-000001.safetensors",
107 "model.sam_model.blocks.7.norm1.weight": "model-00001-of-000001.safetensors",
108 "model.sam_model.blocks.7.norm1.bias": "model-00001-of-000001.safetensors",
109 "model.sam_model.blocks.7.attn.rel_pos_h": "model-00001-of-000001.safetensors",
110 "model.sam_model.blocks.7.attn.rel_pos_w": "model-00001-of-000001.safetensors",
111 "model.sam_model.blocks.7.attn.qkv.weight": "model-00001-of-000001.safetensors",
112 "model.sam_model.blocks.7.attn.qkv.bias": "model-00001-of-000001.safetensors",
113 "model.sam_model.blocks.7.attn.proj.weight": "model-00001-of-000001.safetensors",
114 "model.sam_model.blocks.7.attn.proj.bias": "model-00001-of-000001.safetensors",
115 "model.sam_model.blocks.7.norm2.weight": "model-00001-of-000001.safetensors",
116 "model.sam_model.blocks.7.norm2.bias": "model-00001-of-000001.safetensors",
117 "model.sam_model.blocks.7.mlp.lin1.weight": "model-00001-of-000001.safetensors",
118 "model.sam_model.blocks.7.mlp.lin1.bias": "model-00001-of-000001.safetensors",
119 "model.sam_model.blocks.7.mlp.lin2.weight": "model-00001-of-000001.safetensors",
120 "model.sam_model.blocks.7.mlp.lin2.bias": "model-00001-of-000001.safetensors",
121 "model.sam_model.blocks.8.norm1.weight": "model-00001-of-000001.safetensors",
122 "model.sam_model.blocks.8.norm1.bias": "model-00001-of-000001.safetensors",
123 "model.sam_model.blocks.8.attn.rel_pos_h": "model-00001-of-000001.safetensors",
124 "model.sam_model.blocks.8.attn.rel_pos_w": "model-00001-of-000001.safetensors",
125 "model.sam_model.blocks.8.attn.qkv.weight": "model-00001-of-000001.safetensors",
126 "model.sam_model.blocks.8.attn.qkv.bias": "model-00001-of-000001.safetensors",
127 "model.sam_model.blocks.8.attn.proj.weight": "model-00001-of-000001.safetensors",
128 "model.sam_model.blocks.8.attn.proj.bias": "model-00001-of-000001.safetensors",
129 "model.sam_model.blocks.8.norm2.weight": "model-00001-of-000001.safetensors",
130 "model.sam_model.blocks.8.norm2.bias": "model-00001-of-000001.safetensors",
131 "model.sam_model.blocks.8.mlp.lin1.weight": "model-00001-of-000001.safetensors",
132 "model.sam_model.blocks.8.mlp.lin1.bias": "model-00001-of-000001.safetensors",
133 "model.sam_model.blocks.8.mlp.lin2.weight": "model-00001-of-000001.safetensors",
134 "model.sam_model.blocks.8.mlp.lin2.bias": "model-00001-of-000001.safetensors",
135 "model.sam_model.blocks.9.norm1.weight": "model-00001-of-000001.safetensors",
136 "model.sam_model.blocks.9.norm1.bias": "model-00001-of-000001.safetensors",
137 "model.sam_model.blocks.9.attn.rel_pos_h": "model-00001-of-000001.safetensors",
138 "model.sam_model.blocks.9.attn.rel_pos_w": "model-00001-of-000001.safetensors",
139 "model.sam_model.blocks.9.attn.qkv.weight": "model-00001-of-000001.safetensors",
140 "model.sam_model.blocks.9.attn.qkv.bias": "model-00001-of-000001.safetensors",
141 "model.sam_model.blocks.9.attn.proj.weight": "model-00001-of-000001.safetensors",
142 "model.sam_model.blocks.9.attn.proj.bias": "model-00001-of-000001.safetensors",
143 "model.sam_model.blocks.9.norm2.weight": "model-00001-of-000001.safetensors",
144 "model.sam_model.blocks.9.norm2.bias": "model-00001-of-000001.safetensors",
145 "model.sam_model.blocks.9.mlp.lin1.weight": "model-00001-of-000001.safetensors",
146 "model.sam_model.blocks.9.mlp.lin1.bias": "model-00001-of-000001.safetensors",
147 "model.sam_model.blocks.9.mlp.lin2.weight": "model-00001-of-000001.safetensors",
148 "model.sam_model.blocks.9.mlp.lin2.bias": "model-00001-of-000001.safetensors",
149 "model.sam_model.blocks.10.norm1.weight": "model-00001-of-000001.safetensors",
150 "model.sam_model.blocks.10.norm1.bias": "model-00001-of-000001.safetensors",
151 "model.sam_model.blocks.10.attn.rel_pos_h": "model-00001-of-000001.safetensors",
152 "model.sam_model.blocks.10.attn.rel_pos_w": "model-00001-of-000001.safetensors",
153 "model.sam_model.blocks.10.attn.qkv.weight": "model-00001-of-000001.safetensors",
154 "model.sam_model.blocks.10.attn.qkv.bias": "model-00001-of-000001.safetensors",
155 "model.sam_model.blocks.10.attn.proj.weight": "model-00001-of-000001.safetensors",
156 "model.sam_model.blocks.10.attn.proj.bias": "model-00001-of-000001.safetensors",
157 "model.sam_model.blocks.10.norm2.weight": "model-00001-of-000001.safetensors",
158 "model.sam_model.blocks.10.norm2.bias": "model-00001-of-000001.safetensors",
159 "model.sam_model.blocks.10.mlp.lin1.weight": "model-00001-of-000001.safetensors",
160 "model.sam_model.blocks.10.mlp.lin1.bias": "model-00001-of-000001.safetensors",
161 "model.sam_model.blocks.10.mlp.lin2.weight": "model-00001-of-000001.safetensors",
162 "model.sam_model.blocks.10.mlp.lin2.bias": "model-00001-of-000001.safetensors",
163 "model.sam_model.blocks.11.norm1.weight": "model-00001-of-000001.safetensors",
164 "model.sam_model.blocks.11.norm1.bias": "model-00001-of-000001.safetensors",
165 "model.sam_model.blocks.11.attn.rel_pos_h": "model-00001-of-000001.safetensors",
166 "model.sam_model.blocks.11.attn.rel_pos_w": "model-00001-of-000001.safetensors",
167 "model.sam_model.blocks.11.attn.qkv.weight": "model-00001-of-000001.safetensors",
168 "model.sam_model.blocks.11.attn.qkv.bias": "model-00001-of-000001.safetensors",
169 "model.sam_model.blocks.11.attn.proj.weight": "model-00001-of-000001.safetensors",
170 "model.sam_model.blocks.11.attn.proj.bias": "model-00001-of-000001.safetensors",
171 "model.sam_model.blocks.11.norm2.weight": "model-00001-of-000001.safetensors",
172 "model.sam_model.blocks.11.norm2.bias": "model-00001-of-000001.safetensors",
173 "model.sam_model.blocks.11.mlp.lin1.weight": "model-00001-of-000001.safetensors",
174 "model.sam_model.blocks.11.mlp.lin1.bias": "model-00001-of-000001.safetensors",
175 "model.sam_model.blocks.11.mlp.lin2.weight": "model-00001-of-000001.safetensors",
176 "model.sam_model.blocks.11.mlp.lin2.bias": "model-00001-of-000001.safetensors",
177 "model.sam_model.neck.0.weight": "model-00001-of-000001.safetensors",
178 "model.sam_model.neck.1.weight": "model-00001-of-000001.safetensors",
179 "model.sam_model.neck.1.bias": "model-00001-of-000001.safetensors",
180 "model.sam_model.neck.2.weight": "model-00001-of-000001.safetensors",
181 "model.sam_model.neck.3.weight": "model-00001-of-000001.safetensors",
182 "model.sam_model.neck.3.bias": "model-00001-of-000001.safetensors",
183 "model.sam_model.net_2.weight": "model-00001-of-000001.safetensors",
184 "model.sam_model.net_3.weight": "model-00001-of-000001.safetensors",
185 "model.qwen2_model.model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-000001.safetensors",
186 "model.qwen2_model.model.model.layers.0.self_attn.q_proj.bias": "model-00001-of-000001.safetensors",
187 "model.qwen2_model.model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-000001.safetensors",
188 "model.qwen2_model.model.model.layers.0.self_attn.k_proj.bias": "model-00001-of-000001.safetensors",
189 "model.qwen2_model.model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-000001.safetensors",
190 "model.qwen2_model.model.model.layers.0.self_attn.v_proj.bias": "model-00001-of-000001.safetensors",
191 "model.qwen2_model.model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-000001.safetensors",
192 "model.qwen2_model.model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-000001.safetensors",
193 "model.qwen2_model.model.model.layers.0.mlp.up_proj.weight": "model-00001-of-000001.safetensors",
194 "model.qwen2_model.model.model.layers.0.mlp.down_proj.weight": "model-00001-of-000001.safetensors",
195 "model.qwen2_model.model.model.layers.0.input_layernorm.weight": "model-00001-of-000001.safetensors",
196 "model.qwen2_model.model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-000001.safetensors",
197 "model.qwen2_model.model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-000001.safetensors",
198 "model.qwen2_model.model.model.layers.1.self_attn.q_proj.bias": "model-00001-of-000001.safetensors",
199 "model.qwen2_model.model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-000001.safetensors",
200 "model.qwen2_model.model.model.layers.1.self_attn.k_proj.bias": "model-00001-of-000001.safetensors",
201 "model.qwen2_model.model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-000001.safetensors",
202 "model.qwen2_model.model.model.layers.1.self_attn.v_proj.bias": "model-00001-of-000001.safetensors",
203 "model.qwen2_model.model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-000001.safetensors",
204 "model.qwen2_model.model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-000001.safetensors",
205 "model.qwen2_model.model.model.layers.1.mlp.up_proj.weight": "model-00001-of-000001.safetensors",
206 "model.qwen2_model.model.model.layers.1.mlp.down_proj.weight": "model-00001-of-000001.safetensors",
207 "model.qwen2_model.model.model.layers.1.input_layernorm.weight": "model-00001-of-000001.safetensors",
208 "model.qwen2_model.model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-000001.safetensors",
209 "model.qwen2_model.model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-000001.safetensors",
210 "model.qwen2_model.model.model.layers.2.self_attn.q_proj.bias": "model-00001-of-000001.safetensors",
211 "model.qwen2_model.model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-000001.safetensors",
212 "model.qwen2_model.model.model.layers.2.self_attn.k_proj.bias": "model-00001-of-000001.safetensors",
213 "model.qwen2_model.model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-000001.safetensors",
214 "model.qwen2_model.model.model.layers.2.self_attn.v_proj.bias": "model-00001-of-000001.safetensors",
215 "model.qwen2_model.model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-000001.safetensors",
216 "model.qwen2_model.model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-000001.safetensors",
217 "model.qwen2_model.model.model.layers.2.mlp.up_proj.weight": "model-00001-of-000001.safetensors",
218 "model.qwen2_model.model.model.layers.2.mlp.down_proj.weight": "model-00001-of-000001.safetensors",
219 "model.qwen2_model.model.model.layers.2.input_layernorm.weight": "model-00001-of-000001.safetensors",
220 "model.qwen2_model.model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-000001.safetensors",
221 "model.qwen2_model.model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-000001.safetensors",
222 "model.qwen2_model.model.model.layers.3.self_attn.q_proj.bias": "model-00001-of-000001.safetensors",
223 "model.qwen2_model.model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-000001.safetensors",
224 "model.qwen2_model.model.model.layers.3.self_attn.k_proj.bias": "model-00001-of-000001.safetensors",
225 "model.qwen2_model.model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-000001.safetensors",
226 "model.qwen2_model.model.model.layers.3.self_attn.v_proj.bias": "model-00001-of-000001.safetensors",
227 "model.qwen2_model.model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-000001.safetensors",
228 "model.qwen2_model.model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-000001.safetensors",
229 "model.qwen2_model.model.model.layers.3.mlp.up_proj.weight": "model-00001-of-000001.safetensors",
230 "model.qwen2_model.model.model.layers.3.mlp.down_proj.weight": "model-00001-of-000001.safetensors",
231 "model.qwen2_model.model.model.layers.3.input_layernorm.weight": "model-00001-of-000001.safetensors",
232 "model.qwen2_model.model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-000001.safetensors",
233 "model.qwen2_model.model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-000001.safetensors",
234 "model.qwen2_model.model.model.layers.4.self_attn.q_proj.bias": "model-00001-of-000001.safetensors",
235 "model.qwen2_model.model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-000001.safetensors",
236 "model.qwen2_model.model.model.layers.4.self_attn.k_proj.bias": "model-00001-of-000001.safetensors",
237 "model.qwen2_model.model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-000001.safetensors",
238 "model.qwen2_model.model.model.layers.4.self_attn.v_proj.bias": "model-00001-of-000001.safetensors",
239 "model.qwen2_model.model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-000001.safetensors",
240 "model.qwen2_model.model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-000001.safetensors",
241 "model.qwen2_model.model.model.layers.4.mlp.up_proj.weight": "model-00001-of-000001.safetensors",
242 "model.qwen2_model.model.model.layers.4.mlp.down_proj.weight": "model-00001-of-000001.safetensors",
243 "model.qwen2_model.model.model.layers.4.input_layernorm.weight": "model-00001-of-000001.safetensors",
244 "model.qwen2_model.model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-000001.safetensors",
245 "model.qwen2_model.model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-000001.safetensors",
246 "model.qwen2_model.model.model.layers.5.self_attn.q_proj.bias": "model-00001-of-000001.safetensors",
247 "model.qwen2_model.model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-000001.safetensors",
248 "model.qwen2_model.model.model.layers.5.self_attn.k_proj.bias": "model-00001-of-000001.safetensors",
249 "model.qwen2_model.model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-000001.safetensors",
250 "model.qwen2_model.model.model.layers.5.self_attn.v_proj.bias": "model-00001-of-000001.safetensors",
251 "model.qwen2_model.model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-000001.safetensors",
252 "model.qwen2_model.model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-000001.safetensors",
253 "model.qwen2_model.model.model.layers.5.mlp.up_proj.weight": "model-00001-of-000001.safetensors",
254 "model.qwen2_model.model.model.layers.5.mlp.down_proj.weight": "model-00001-of-000001.safetensors",
255 "model.qwen2_model.model.model.layers.5.input_layernorm.weight": "model-00001-of-000001.safetensors",
256 "model.qwen2_model.model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-000001.safetensors",
257 "model.qwen2_model.model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-000001.safetensors",
258 "model.qwen2_model.model.model.layers.6.self_attn.q_proj.bias": "model-00001-of-000001.safetensors",
259 "model.qwen2_model.model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-000001.safetensors",
260 "model.qwen2_model.model.model.layers.6.self_attn.k_proj.bias": "model-00001-of-000001.safetensors",
261 "model.qwen2_model.model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-000001.safetensors",
262 "model.qwen2_model.model.model.layers.6.self_attn.v_proj.bias": "model-00001-of-000001.safetensors",
263 "model.qwen2_model.model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-000001.safetensors",
264 "model.qwen2_model.model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-000001.safetensors",
265 "model.qwen2_model.model.model.layers.6.mlp.up_proj.weight": "model-00001-of-000001.safetensors",
266 "model.qwen2_model.model.model.layers.6.mlp.down_proj.weight": "model-00001-of-000001.safetensors",
267 "model.qwen2_model.model.model.layers.6.input_layernorm.weight": "model-00001-of-000001.safetensors",
268 "model.qwen2_model.model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-000001.safetensors",
269 "model.qwen2_model.model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-000001.safetensors",
270 "model.qwen2_model.model.model.layers.7.self_attn.q_proj.bias": "model-00001-of-000001.safetensors",
271 "model.qwen2_model.model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-000001.safetensors",
272 "model.qwen2_model.model.model.layers.7.self_attn.k_proj.bias": "model-00001-of-000001.safetensors",
273 "model.qwen2_model.model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-000001.safetensors",
274 "model.qwen2_model.model.model.layers.7.self_attn.v_proj.bias": "model-00001-of-000001.safetensors",
275 "model.qwen2_model.model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-000001.safetensors",
276 "model.qwen2_model.model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-000001.safetensors",
277 "model.qwen2_model.model.model.layers.7.mlp.up_proj.weight": "model-00001-of-000001.safetensors",
278 "model.qwen2_model.model.model.layers.7.mlp.down_proj.weight": "model-00001-of-000001.safetensors",
279 "model.qwen2_model.model.model.layers.7.input_layernorm.weight": "model-00001-of-000001.safetensors",
280 "model.qwen2_model.model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-000001.safetensors",
281 "model.qwen2_model.model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-000001.safetensors",
282 "model.qwen2_model.model.model.layers.8.self_attn.q_proj.bias": "model-00001-of-000001.safetensors",
283 "model.qwen2_model.model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-000001.safetensors",
284 "model.qwen2_model.model.model.layers.8.self_attn.k_proj.bias": "model-00001-of-000001.safetensors",
285 "model.qwen2_model.model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-000001.safetensors",
286 "model.qwen2_model.model.model.layers.8.self_attn.v_proj.bias": "model-00001-of-000001.safetensors",
287 "model.qwen2_model.model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-000001.safetensors",
288 "model.qwen2_model.model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-000001.safetensors",
289 "model.qwen2_model.model.model.layers.8.mlp.up_proj.weight": "model-00001-of-000001.safetensors",
290 "model.qwen2_model.model.model.layers.8.mlp.down_proj.weight": "model-00001-of-000001.safetensors",
291 "model.qwen2_model.model.model.layers.8.input_layernorm.weight": "model-00001-of-000001.safetensors",
292 "model.qwen2_model.model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-000001.safetensors",
293 "model.qwen2_model.model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-000001.safetensors",
294 "model.qwen2_model.model.model.layers.9.self_attn.q_proj.bias": "model-00001-of-000001.safetensors",
295 "model.qwen2_model.model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-000001.safetensors",
296 "model.qwen2_model.model.model.layers.9.self_attn.k_proj.bias": "model-00001-of-000001.safetensors",
297 "model.qwen2_model.model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-000001.safetensors",
298 "model.qwen2_model.model.model.layers.9.self_attn.v_proj.bias": "model-00001-of-000001.safetensors",
299 "model.qwen2_model.model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-000001.safetensors",
300 "model.qwen2_model.model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-000001.safetensors",
301 "model.qwen2_model.model.model.layers.9.mlp.up_proj.weight": "model-00001-of-000001.safetensors",
302 "model.qwen2_model.model.model.layers.9.mlp.down_proj.weight": "model-00001-of-000001.safetensors",
303 "model.qwen2_model.model.model.layers.9.input_layernorm.weight": "model-00001-of-000001.safetensors",
304 "model.qwen2_model.model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-000001.safetensors",
305 "model.qwen2_model.model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-000001.safetensors",
306 "model.qwen2_model.model.model.layers.10.self_attn.q_proj.bias": "model-00001-of-000001.safetensors",
307 "model.qwen2_model.model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-000001.safetensors",
308 "model.qwen2_model.model.model.layers.10.self_attn.k_proj.bias": "model-00001-of-000001.safetensors",
309 "model.qwen2_model.model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-000001.safetensors",
310 "model.qwen2_model.model.model.layers.10.self_attn.v_proj.bias": "model-00001-of-000001.safetensors",
311 "model.qwen2_model.model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-000001.safetensors",
312 "model.qwen2_model.model.model.layers.10.mlp.gate_proj.weight": "model-00001-of-000001.safetensors",
313 "model.qwen2_model.model.model.layers.10.mlp.up_proj.weight": "model-00001-of-000001.safetensors",
314 "model.qwen2_model.model.model.layers.10.mlp.down_proj.weight": "model-00001-of-000001.safetensors",
315 "model.qwen2_model.model.model.layers.10.input_layernorm.weight": "model-00001-of-000001.safetensors",
316 "model.qwen2_model.model.model.layers.10.post_attention_layernorm.weight": "model-00001-of-000001.safetensors",
317 "model.qwen2_model.model.model.layers.11.self_attn.q_proj.weight": "model-00001-of-000001.safetensors",
318 "model.qwen2_model.model.model.layers.11.self_attn.q_proj.bias": "model-00001-of-000001.safetensors",
319 "model.qwen2_model.model.model.layers.11.self_attn.k_proj.weight": "model-00001-of-000001.safetensors",
320 "model.qwen2_model.model.model.layers.11.self_attn.k_proj.bias": "model-00001-of-000001.safetensors",
321 "model.qwen2_model.model.model.layers.11.self_attn.v_proj.weight": "model-00001-of-000001.safetensors",
322 "model.qwen2_model.model.model.layers.11.self_attn.v_proj.bias": "model-00001-of-000001.safetensors",
323 "model.qwen2_model.model.model.layers.11.self_attn.o_proj.weight": "model-00001-of-000001.safetensors",
324 "model.qwen2_model.model.model.layers.11.mlp.gate_proj.weight": "model-00001-of-000001.safetensors",
325 "model.qwen2_model.model.model.layers.11.mlp.up_proj.weight": "model-00001-of-000001.safetensors",
326 "model.qwen2_model.model.model.layers.11.mlp.down_proj.weight": "model-00001-of-000001.safetensors",
327 "model.qwen2_model.model.model.layers.11.input_layernorm.weight": "model-00001-of-000001.safetensors",
328 "model.qwen2_model.model.model.layers.11.post_attention_layernorm.weight": "model-00001-of-000001.safetensors",
329 "model.qwen2_model.model.model.layers.12.self_attn.q_proj.weight": "model-00001-of-000001.safetensors",
330 "model.qwen2_model.model.model.layers.12.self_attn.q_proj.bias": "model-00001-of-000001.safetensors",
331 "model.qwen2_model.model.model.layers.12.self_attn.k_proj.weight": "model-00001-of-000001.safetensors",
332 "model.qwen2_model.model.model.layers.12.self_attn.k_proj.bias": "model-00001-of-000001.safetensors",
333 "model.qwen2_model.model.model.layers.12.self_attn.v_proj.weight": "model-00001-of-000001.safetensors",
334 "model.qwen2_model.model.model.layers.12.self_attn.v_proj.bias": "model-00001-of-000001.safetensors",
335 "model.qwen2_model.model.model.layers.12.self_attn.o_proj.weight": "model-00001-of-000001.safetensors",
336 "model.qwen2_model.model.model.layers.12.mlp.gate_proj.weight": "model-00001-of-000001.safetensors",
337 "model.qwen2_model.model.model.layers.12.mlp.up_proj.weight": "model-00001-of-000001.safetensors",
338 "model.qwen2_model.model.model.layers.12.mlp.down_proj.weight": "model-00001-of-000001.safetensors",
339 "model.qwen2_model.model.model.layers.12.input_layernorm.weight": "model-00001-of-000001.safetensors",
340 "model.qwen2_model.model.model.layers.12.post_attention_layernorm.weight": "model-00001-of-000001.safetensors",
341 "model.qwen2_model.model.model.layers.13.self_attn.q_proj.weight": "model-00001-of-000001.safetensors",
342 "model.qwen2_model.model.model.layers.13.self_attn.q_proj.bias": "model-00001-of-000001.safetensors",
343 "model.qwen2_model.model.model.layers.13.self_attn.k_proj.weight": "model-00001-of-000001.safetensors",
344 "model.qwen2_model.model.model.layers.13.self_attn.k_proj.bias": "model-00001-of-000001.safetensors",
345 "model.qwen2_model.model.model.layers.13.self_attn.v_proj.weight": "model-00001-of-000001.safetensors",
346 "model.qwen2_model.model.model.layers.13.self_attn.v_proj.bias": "model-00001-of-000001.safetensors",
347 "model.qwen2_model.model.model.layers.13.self_attn.o_proj.weight": "model-00001-of-000001.safetensors",
348 "model.qwen2_model.model.model.layers.13.mlp.gate_proj.weight": "model-00001-of-000001.safetensors",
349 "model.qwen2_model.model.model.layers.13.mlp.up_proj.weight": "model-00001-of-000001.safetensors",
350 "model.qwen2_model.model.model.layers.13.mlp.down_proj.weight": "model-00001-of-000001.safetensors",
351 "model.qwen2_model.model.model.layers.13.input_layernorm.weight": "model-00001-of-000001.safetensors",
352 "model.qwen2_model.model.model.layers.13.post_attention_layernorm.weight": "model-00001-of-000001.safetensors",
353 "model.qwen2_model.model.model.layers.14.self_attn.q_proj.weight": "model-00001-of-000001.safetensors",
354 "model.qwen2_model.model.model.layers.14.self_attn.q_proj.bias": "model-00001-of-000001.safetensors",
355 "model.qwen2_model.model.model.layers.14.self_attn.k_proj.weight": "model-00001-of-000001.safetensors",
356 "model.qwen2_model.model.model.layers.14.self_attn.k_proj.bias": "model-00001-of-000001.safetensors",
357 "model.qwen2_model.model.model.layers.14.self_attn.v_proj.weight": "model-00001-of-000001.safetensors",
358 "model.qwen2_model.model.model.layers.14.self_attn.v_proj.bias": "model-00001-of-000001.safetensors",
359 "model.qwen2_model.model.model.layers.14.self_attn.o_proj.weight": "model-00001-of-000001.safetensors",
360 "model.qwen2_model.model.model.layers.14.mlp.gate_proj.weight": "model-00001-of-000001.safetensors",
361 "model.qwen2_model.model.model.layers.14.mlp.up_proj.weight": "model-00001-of-000001.safetensors",
362 "model.qwen2_model.model.model.layers.14.mlp.down_proj.weight": "model-00001-of-000001.safetensors",
363 "model.qwen2_model.model.model.layers.14.input_layernorm.weight": "model-00001-of-000001.safetensors",
364 "model.qwen2_model.model.model.layers.14.post_attention_layernorm.weight": "model-00001-of-000001.safetensors",
365 "model.qwen2_model.model.model.layers.15.self_attn.q_proj.weight": "model-00001-of-000001.safetensors",
366 "model.qwen2_model.model.model.layers.15.self_attn.q_proj.bias": "model-00001-of-000001.safetensors",
367 "model.qwen2_model.model.model.layers.15.self_attn.k_proj.weight": "model-00001-of-000001.safetensors",
368 "model.qwen2_model.model.model.layers.15.self_attn.k_proj.bias": "model-00001-of-000001.safetensors",
369 "model.qwen2_model.model.model.layers.15.self_attn.v_proj.weight": "model-00001-of-000001.safetensors",
370 "model.qwen2_model.model.model.layers.15.self_attn.v_proj.bias": "model-00001-of-000001.safetensors",
371 "model.qwen2_model.model.model.layers.15.self_attn.o_proj.weight": "model-00001-of-000001.safetensors",
372 "model.qwen2_model.model.model.layers.15.mlp.gate_proj.weight": "model-00001-of-000001.safetensors",
373 "model.qwen2_model.model.model.layers.15.mlp.up_proj.weight": "model-00001-of-000001.safetensors",
374 "model.qwen2_model.model.model.layers.15.mlp.down_proj.weight": "model-00001-of-000001.safetensors",
375 "model.qwen2_model.model.model.layers.15.input_layernorm.weight": "model-00001-of-000001.safetensors",
376 "model.qwen2_model.model.model.layers.15.post_attention_layernorm.weight": "model-00001-of-000001.safetensors",
377 "model.qwen2_model.model.model.layers.16.self_attn.q_proj.weight": "model-00001-of-000001.safetensors",
378 "model.qwen2_model.model.model.layers.16.self_attn.q_proj.bias": "model-00001-of-000001.safetensors",
379 "model.qwen2_model.model.model.layers.16.self_attn.k_proj.weight": "model-00001-of-000001.safetensors",
380 "model.qwen2_model.model.model.layers.16.self_attn.k_proj.bias": "model-00001-of-000001.safetensors",
381 "model.qwen2_model.model.model.layers.16.self_attn.v_proj.weight": "model-00001-of-000001.safetensors",
382 "model.qwen2_model.model.model.layers.16.self_attn.v_proj.bias": "model-00001-of-000001.safetensors",
383 "model.qwen2_model.model.model.layers.16.self_attn.o_proj.weight": "model-00001-of-000001.safetensors",
384 "model.qwen2_model.model.model.layers.16.mlp.gate_proj.weight": "model-00001-of-000001.safetensors",
385 "model.qwen2_model.model.model.layers.16.mlp.up_proj.weight": "model-00001-of-000001.safetensors",
386 "model.qwen2_model.model.model.layers.16.mlp.down_proj.weight": "model-00001-of-000001.safetensors",
387 "model.qwen2_model.model.model.layers.16.input_layernorm.weight": "model-00001-of-000001.safetensors",
388 "model.qwen2_model.model.model.layers.16.post_attention_layernorm.weight": "model-00001-of-000001.safetensors",
389 "model.qwen2_model.model.model.layers.17.self_attn.q_proj.weight": "model-00001-of-000001.safetensors",
390 "model.qwen2_model.model.model.layers.17.self_attn.q_proj.bias": "model-00001-of-000001.safetensors",
391 "model.qwen2_model.model.model.layers.17.self_attn.k_proj.weight": "model-00001-of-000001.safetensors",
392 "model.qwen2_model.model.model.layers.17.self_attn.k_proj.bias": "model-00001-of-000001.safetensors",
393 "model.qwen2_model.model.model.layers.17.self_attn.v_proj.weight": "model-00001-of-000001.safetensors",
394 "model.qwen2_model.model.model.layers.17.self_attn.v_proj.bias": "model-00001-of-000001.safetensors",
395 "model.qwen2_model.model.model.layers.17.self_attn.o_proj.weight": "model-00001-of-000001.safetensors",
396 "model.qwen2_model.model.model.layers.17.mlp.gate_proj.weight": "model-00001-of-000001.safetensors",
397 "model.qwen2_model.model.model.layers.17.mlp.up_proj.weight": "model-00001-of-000001.safetensors",
398 "model.qwen2_model.model.model.layers.17.mlp.down_proj.weight": "model-00001-of-000001.safetensors",
399 "model.qwen2_model.model.model.layers.17.input_layernorm.weight": "model-00001-of-000001.safetensors",
400 "model.qwen2_model.model.model.layers.17.post_attention_layernorm.weight": "model-00001-of-000001.safetensors",
401 "model.qwen2_model.model.model.layers.18.self_attn.q_proj.weight": "model-00001-of-000001.safetensors",
402 "model.qwen2_model.model.model.layers.18.self_attn.q_proj.bias": "model-00001-of-000001.safetensors",
403 "model.qwen2_model.model.model.layers.18.self_attn.k_proj.weight": "model-00001-of-000001.safetensors",
404 "model.qwen2_model.model.model.layers.18.self_attn.k_proj.bias": "model-00001-of-000001.safetensors",
405 "model.qwen2_model.model.model.layers.18.self_attn.v_proj.weight": "model-00001-of-000001.safetensors",
406 "model.qwen2_model.model.model.layers.18.self_attn.v_proj.bias": "model-00001-of-000001.safetensors",
407 "model.qwen2_model.model.model.layers.18.self_attn.o_proj.weight": "model-00001-of-000001.safetensors",
408 "model.qwen2_model.model.model.layers.18.mlp.gate_proj.weight": "model-00001-of-000001.safetensors",
409 "model.qwen2_model.model.model.layers.18.mlp.up_proj.weight": "model-00001-of-000001.safetensors",
410 "model.qwen2_model.model.model.layers.18.mlp.down_proj.weight": "model-00001-of-000001.safetensors",
411 "model.qwen2_model.model.model.layers.18.input_layernorm.weight": "model-00001-of-000001.safetensors",
412 "model.qwen2_model.model.model.layers.18.post_attention_layernorm.weight": "model-00001-of-000001.safetensors",
413 "model.qwen2_model.model.model.layers.19.self_attn.q_proj.weight": "model-00001-of-000001.safetensors",
414 "model.qwen2_model.model.model.layers.19.self_attn.q_proj.bias": "model-00001-of-000001.safetensors",
415 "model.qwen2_model.model.model.layers.19.self_attn.k_proj.weight": "model-00001-of-000001.safetensors",
416 "model.qwen2_model.model.model.layers.19.self_attn.k_proj.bias": "model-00001-of-000001.safetensors",
417 "model.qwen2_model.model.model.layers.19.self_attn.v_proj.weight": "model-00001-of-000001.safetensors",
418 "model.qwen2_model.model.model.layers.19.self_attn.v_proj.bias": "model-00001-of-000001.safetensors",
419 "model.qwen2_model.model.model.layers.19.self_attn.o_proj.weight": "model-00001-of-000001.safetensors",
420 "model.qwen2_model.model.model.layers.19.mlp.gate_proj.weight": "model-00001-of-000001.safetensors",
421 "model.qwen2_model.model.model.layers.19.mlp.up_proj.weight": "model-00001-of-000001.safetensors",
422 "model.qwen2_model.model.model.layers.19.mlp.down_proj.weight": "model-00001-of-000001.safetensors",
423 "model.qwen2_model.model.model.layers.19.input_layernorm.weight": "model-00001-of-000001.safetensors",
424 "model.qwen2_model.model.model.layers.19.post_attention_layernorm.weight": "model-00001-of-000001.safetensors",
425 "model.qwen2_model.model.model.layers.20.self_attn.q_proj.weight": "model-00001-of-000001.safetensors",
426 "model.qwen2_model.model.model.layers.20.self_attn.q_proj.bias": "model-00001-of-000001.safetensors",
427 "model.qwen2_model.model.model.layers.20.self_attn.k_proj.weight": "model-00001-of-000001.safetensors",
428 "model.qwen2_model.model.model.layers.20.self_attn.k_proj.bias": "model-00001-of-000001.safetensors",
429 "model.qwen2_model.model.model.layers.20.self_attn.v_proj.weight": "model-00001-of-000001.safetensors",
430 "model.qwen2_model.model.model.layers.20.self_attn.v_proj.bias": "model-00001-of-000001.safetensors",
431 "model.qwen2_model.model.model.layers.20.self_attn.o_proj.weight": "model-00001-of-000001.safetensors",
432 "model.qwen2_model.model.model.layers.20.mlp.gate_proj.weight": "model-00001-of-000001.safetensors",
433 "model.qwen2_model.model.model.layers.20.mlp.up_proj.weight": "model-00001-of-000001.safetensors",
434 "model.qwen2_model.model.model.layers.20.mlp.down_proj.weight": "model-00001-of-000001.safetensors",
435 "model.qwen2_model.model.model.layers.20.input_layernorm.weight": "model-00001-of-000001.safetensors",
436 "model.qwen2_model.model.model.layers.20.post_attention_layernorm.weight": "model-00001-of-000001.safetensors",
437 "model.qwen2_model.model.model.layers.21.self_attn.q_proj.weight": "model-00001-of-000001.safetensors",
438 "model.qwen2_model.model.model.layers.21.self_attn.q_proj.bias": "model-00001-of-000001.safetensors",
439 "model.qwen2_model.model.model.layers.21.self_attn.k_proj.weight": "model-00001-of-000001.safetensors",
440 "model.qwen2_model.model.model.layers.21.self_attn.k_proj.bias": "model-00001-of-000001.safetensors",
441 "model.qwen2_model.model.model.layers.21.self_attn.v_proj.weight": "model-00001-of-000001.safetensors",
442 "model.qwen2_model.model.model.layers.21.self_attn.v_proj.bias": "model-00001-of-000001.safetensors",
443 "model.qwen2_model.model.model.layers.21.self_attn.o_proj.weight": "model-00001-of-000001.safetensors",
444 "model.qwen2_model.model.model.layers.21.mlp.gate_proj.weight": "model-00001-of-000001.safetensors",
445 "model.qwen2_model.model.model.layers.21.mlp.up_proj.weight": "model-00001-of-000001.safetensors",
446 "model.qwen2_model.model.model.layers.21.mlp.down_proj.weight": "model-00001-of-000001.safetensors",
447 "model.qwen2_model.model.model.layers.21.input_layernorm.weight": "model-00001-of-000001.safetensors",
448 "model.qwen2_model.model.model.layers.21.post_attention_layernorm.weight": "model-00001-of-000001.safetensors",
449 "model.qwen2_model.model.model.layers.22.self_attn.q_proj.weight": "model-00001-of-000001.safetensors",
450 "model.qwen2_model.model.model.layers.22.self_attn.q_proj.bias": "model-00001-of-000001.safetensors",
451 "model.qwen2_model.model.model.layers.22.self_attn.k_proj.weight": "model-00001-of-000001.safetensors",
452 "model.qwen2_model.model.model.layers.22.self_attn.k_proj.bias": "model-00001-of-000001.safetensors",
453 "model.qwen2_model.model.model.layers.22.self_attn.v_proj.weight": "model-00001-of-000001.safetensors",
454 "model.qwen2_model.model.model.layers.22.self_attn.v_proj.bias": "model-00001-of-000001.safetensors",
455 "model.qwen2_model.model.model.layers.22.self_attn.o_proj.weight": "model-00001-of-000001.safetensors",
456 "model.qwen2_model.model.model.layers.22.mlp.gate_proj.weight": "model-00001-of-000001.safetensors",
457 "model.qwen2_model.model.model.layers.22.mlp.up_proj.weight": "model-00001-of-000001.safetensors",
458 "model.qwen2_model.model.model.layers.22.mlp.down_proj.weight": "model-00001-of-000001.safetensors",
459 "model.qwen2_model.model.model.layers.22.input_layernorm.weight": "model-00001-of-000001.safetensors",
460 "model.qwen2_model.model.model.layers.22.post_attention_layernorm.weight": "model-00001-of-000001.safetensors",
461 "model.qwen2_model.model.model.layers.23.self_attn.q_proj.weight": "model-00001-of-000001.safetensors",
462 "model.qwen2_model.model.model.layers.23.self_attn.q_proj.bias": "model-00001-of-000001.safetensors",
463 "model.qwen2_model.model.model.layers.23.self_attn.k_proj.weight": "model-00001-of-000001.safetensors",
464 "model.qwen2_model.model.model.layers.23.self_attn.k_proj.bias": "model-00001-of-000001.safetensors",
465 "model.qwen2_model.model.model.layers.23.self_attn.v_proj.weight": "model-00001-of-000001.safetensors",
466 "model.qwen2_model.model.model.layers.23.self_attn.v_proj.bias": "model-00001-of-000001.safetensors",
467 "model.qwen2_model.model.model.layers.23.self_attn.o_proj.weight": "model-00001-of-000001.safetensors",
468 "model.qwen2_model.model.model.layers.23.mlp.gate_proj.weight": "model-00001-of-000001.safetensors",
469 "model.qwen2_model.model.model.layers.23.mlp.up_proj.weight": "model-00001-of-000001.safetensors",
470 "model.qwen2_model.model.model.layers.23.mlp.down_proj.weight": "model-00001-of-000001.safetensors",
471 "model.qwen2_model.model.model.layers.23.input_layernorm.weight": "model-00001-of-000001.safetensors",
472 "model.qwen2_model.model.model.layers.23.post_attention_layernorm.weight": "model-00001-of-000001.safetensors",
473 "model.qwen2_model.model.model.norm.weight": "model-00001-of-000001.safetensors",
474 "model.qwen2_model.query_768.weight": "model-00001-of-000001.safetensors",
475 "model.qwen2_model.query_1024.weight": "model-00001-of-000001.safetensors",
476 "model.projector.layers.weight": "model-00001-of-000001.safetensors",
477 "model.projector.layers.bias": "model-00001-of-000001.safetensors",
478 "model.view_seperator": "model-00001-of-000001.safetensors",
479 "model.embed_tokens.weight": "model-00001-of-000001.safetensors",
480 "model.norm.weight": "model-00001-of-000001.safetensors",
481 "lm_head.weight": "model-00001-of-000001.safetensors",
482 "model.layers.0.self_attn.q_proj.weight": "model-00001-of-000001.safetensors",
483 "model.layers.0.self_attn.k_proj.weight": "model-00001-of-000001.safetensors",
484 "model.layers.0.self_attn.v_proj.weight": "model-00001-of-000001.safetensors",
485 "model.layers.0.self_attn.o_proj.weight": "model-00001-of-000001.safetensors",
486 "model.layers.0.mlp.gate_proj.weight": "model-00001-of-000001.safetensors",
487 "model.layers.0.mlp.up_proj.weight": "model-00001-of-000001.safetensors",
488 "model.layers.0.mlp.down_proj.weight": "model-00001-of-000001.safetensors",
489 "model.layers.0.input_layernorm.weight": "model-00001-of-000001.safetensors",
490 "model.layers.0.post_attention_layernorm.weight": "model-00001-of-000001.safetensors",
491 "model.layers.1.self_attn.q_proj.weight": "model-00001-of-000001.safetensors",
492 "model.layers.1.self_attn.k_proj.weight": "model-00001-of-000001.safetensors",
493 "model.layers.1.self_attn.v_proj.weight": "model-00001-of-000001.safetensors",
494 "model.layers.1.self_attn.o_proj.weight": "model-00001-of-000001.safetensors",
495 "model.layers.1.mlp.gate.weight": "model-00001-of-000001.safetensors",
496 "model.layers.1.mlp.shared_experts.gate_proj.weight": "model-00001-of-000001.safetensors",
497 "model.layers.1.mlp.shared_experts.up_proj.weight": "model-00001-of-000001.safetensors",
498 "model.layers.1.mlp.shared_experts.down_proj.weight": "model-00001-of-000001.safetensors",
499 "model.layers.1.mlp.experts.0.gate_proj.weight": "model-00001-of-000001.safetensors",
500 "model.layers.1.mlp.experts.0.up_proj.weight": "model-00001-of-000001.safetensors",
501 "model.layers.1.mlp.experts.0.down_proj.weight": "model-00001-of-000001.safetensors",
502 "model.layers.1.mlp.experts.1.gate_proj.weight": "model-00001-of-000001.safetensors",
503 "model.layers.1.mlp.experts.1.up_proj.weight": "model-00001-of-000001.safetensors",
504 "model.layers.1.mlp.experts.1.down_proj.weight": "model-00001-of-000001.safetensors",
505 "model.layers.1.mlp.experts.2.gate_proj.weight": "model-00001-of-000001.safetensors",
506 "model.layers.1.mlp.experts.2.up_proj.weight": "model-00001-of-000001.safetensors",
507 "model.layers.1.mlp.experts.2.down_proj.weight": "model-00001-of-000001.safetensors",
508 "model.layers.1.mlp.experts.3.gate_proj.weight": "model-00001-of-000001.safetensors",
509 "model.layers.1.mlp.experts.3.up_proj.weight": "model-00001-of-000001.safetensors",
510 "model.layers.1.mlp.experts.3.down_proj.weight": "model-00001-of-000001.safetensors",
511 "model.layers.1.mlp.experts.4.gate_proj.weight": "model-00001-of-000001.safetensors",
512 "model.layers.1.mlp.experts.4.up_proj.weight": "model-00001-of-000001.safetensors",
513 "model.layers.1.mlp.experts.4.down_proj.weight": "model-00001-of-000001.safetensors",
514 "model.layers.1.mlp.experts.5.gate_proj.weight": "model-00001-of-000001.safetensors",
515 "model.layers.1.mlp.experts.5.up_proj.weight": "model-00001-of-000001.safetensors",
516 "model.layers.1.mlp.experts.5.down_proj.weight": "model-00001-of-000001.safetensors",
517 "model.layers.1.mlp.experts.6.gate_proj.weight": "model-00001-of-000001.safetensors",
518 "model.layers.1.mlp.experts.6.up_proj.weight": "model-00001-of-000001.safetensors",
519 "model.layers.1.mlp.experts.6.down_proj.weight": "model-00001-of-000001.safetensors",
520 "model.layers.1.mlp.experts.7.gate_proj.weight": "model-00001-of-000001.safetensors",
521 "model.layers.1.mlp.experts.7.up_proj.weight": "model-00001-of-000001.safetensors",
522 "model.layers.1.mlp.experts.7.down_proj.weight": "model-00001-of-000001.safetensors",
523 "model.layers.1.mlp.experts.8.gate_proj.weight": "model-00001-of-000001.safetensors",
524 "model.layers.1.mlp.experts.8.up_proj.weight": "model-00001-of-000001.safetensors",
525 "model.layers.1.mlp.experts.8.down_proj.weight": "model-00001-of-000001.safetensors",
526 "model.layers.1.mlp.experts.9.gate_proj.weight": "model-00001-of-000001.safetensors",
527 "model.layers.1.mlp.experts.9.up_proj.weight": "model-00001-of-000001.safetensors",
528 "model.layers.1.mlp.experts.9.down_proj.weight": "model-00001-of-000001.safetensors",
529 "model.layers.1.mlp.experts.10.gate_proj.weight": "model-00001-of-000001.safetensors",
530 "model.layers.1.mlp.experts.10.up_proj.weight": "model-00001-of-000001.safetensors",
531 "model.layers.1.mlp.experts.10.down_proj.weight": "model-00001-of-000001.safetensors",
532 "model.layers.1.mlp.experts.11.gate_proj.weight": "model-00001-of-000001.safetensors",
533 "model.layers.1.mlp.experts.11.up_proj.weight": "model-00001-of-000001.safetensors",
534 "model.layers.1.mlp.experts.11.down_proj.weight": "model-00001-of-000001.safetensors",
535 "model.layers.1.mlp.experts.12.gate_proj.weight": "model-00001-of-000001.safetensors",
536 "model.layers.1.mlp.experts.12.up_proj.weight": "model-00001-of-000001.safetensors",
537 "model.layers.1.mlp.experts.12.down_proj.weight": "model-00001-of-000001.safetensors",
538 "model.layers.1.mlp.experts.13.gate_proj.weight": "model-00001-of-000001.safetensors",
539 "model.layers.1.mlp.experts.13.up_proj.weight": "model-00001-of-000001.safetensors",
540 "model.layers.1.mlp.experts.13.down_proj.weight": "model-00001-of-000001.safetensors",
541 "model.layers.1.mlp.experts.14.gate_proj.weight": "model-00001-of-000001.safetensors",
542 "model.layers.1.mlp.experts.14.up_proj.weight": "model-00001-of-000001.safetensors",
543 "model.layers.1.mlp.experts.14.down_proj.weight": "model-00001-of-000001.safetensors",
544 "model.layers.1.mlp.experts.15.gate_proj.weight": "model-00001-of-000001.safetensors",
545 "model.layers.1.mlp.experts.15.up_proj.weight": "model-00001-of-000001.safetensors",
546 "model.layers.1.mlp.experts.15.down_proj.weight": "model-00001-of-000001.safetensors",
547 "model.layers.1.mlp.experts.16.gate_proj.weight": "model-00001-of-000001.safetensors",
548 "model.layers.1.mlp.experts.16.up_proj.weight": "model-00001-of-000001.safetensors",
549 "model.layers.1.mlp.experts.16.down_proj.weight": "model-00001-of-000001.safetensors",
550 "model.layers.1.mlp.experts.17.gate_proj.weight": "model-00001-of-000001.safetensors",
551 "model.layers.1.mlp.experts.17.up_proj.weight": "model-00001-of-000001.safetensors",
552 "model.layers.1.mlp.experts.17.down_proj.weight": "model-00001-of-000001.safetensors",
553 "model.layers.1.mlp.experts.18.gate_proj.weight": "model-00001-of-000001.safetensors",
554 "model.layers.1.mlp.experts.18.up_proj.weight": "model-00001-of-000001.safetensors",
555 "model.layers.1.mlp.experts.18.down_proj.weight": "model-00001-of-000001.safetensors",
556 "model.layers.1.mlp.experts.19.gate_proj.weight": "model-00001-of-000001.safetensors",
557 "model.layers.1.mlp.experts.19.up_proj.weight": "model-00001-of-000001.safetensors",
558 "model.layers.1.mlp.experts.19.down_proj.weight": "model-00001-of-000001.safetensors",
559 "model.layers.1.mlp.experts.20.gate_proj.weight": "model-00001-of-000001.safetensors",
560 "model.layers.1.mlp.experts.20.up_proj.weight": "model-00001-of-000001.safetensors",
561 "model.layers.1.mlp.experts.20.down_proj.weight": "model-00001-of-000001.safetensors",
562 "model.layers.1.mlp.experts.21.gate_proj.weight": "model-00001-of-000001.safetensors",
563 "model.layers.1.mlp.experts.21.up_proj.weight": "model-00001-of-000001.safetensors",
564 "model.layers.1.mlp.experts.21.down_proj.weight": "model-00001-of-000001.safetensors",
565 "model.layers.1.mlp.experts.22.gate_proj.weight": "model-00001-of-000001.safetensors",
566 "model.layers.1.mlp.experts.22.up_proj.weight": "model-00001-of-000001.safetensors",
567 "model.layers.1.mlp.experts.22.down_proj.weight": "model-00001-of-000001.safetensors",
568 "model.layers.1.mlp.experts.23.gate_proj.weight": "model-00001-of-000001.safetensors",
569 "model.layers.1.mlp.experts.23.up_proj.weight": "model-00001-of-000001.safetensors",
570 "model.layers.1.mlp.experts.23.down_proj.weight": "model-00001-of-000001.safetensors",
571 "model.layers.1.mlp.experts.24.gate_proj.weight": "model-00001-of-000001.safetensors",
572 "model.layers.1.mlp.experts.24.up_proj.weight": "model-00001-of-000001.safetensors",
573 "model.layers.1.mlp.experts.24.down_proj.weight": "model-00001-of-000001.safetensors",
574 "model.layers.1.mlp.experts.25.gate_proj.weight": "model-00001-of-000001.safetensors",
575 "model.layers.1.mlp.experts.25.up_proj.weight": "model-00001-of-000001.safetensors",
576 "model.layers.1.mlp.experts.25.down_proj.weight": "model-00001-of-000001.safetensors",
577 "model.layers.1.mlp.experts.26.gate_proj.weight": "model-00001-of-000001.safetensors",
578 "model.layers.1.mlp.experts.26.up_proj.weight": "model-00001-of-000001.safetensors",
579 "model.layers.1.mlp.experts.26.down_proj.weight": "model-00001-of-000001.safetensors",
580 "model.layers.1.mlp.experts.27.gate_proj.weight": "model-00001-of-000001.safetensors",
581 "model.layers.1.mlp.experts.27.up_proj.weight": "model-00001-of-000001.safetensors",
582 "model.layers.1.mlp.experts.27.down_proj.weight": "model-00001-of-000001.safetensors",
583 "model.layers.1.mlp.experts.28.gate_proj.weight": "model-00001-of-000001.safetensors",
584 "model.layers.1.mlp.experts.28.up_proj.weight": "model-00001-of-000001.safetensors",
585 "model.layers.1.mlp.experts.28.down_proj.weight": "model-00001-of-000001.safetensors",
586 "model.layers.1.mlp.experts.29.gate_proj.weight": "model-00001-of-000001.safetensors",
587 "model.layers.1.mlp.experts.29.up_proj.weight": "model-00001-of-000001.safetensors",
588 "model.layers.1.mlp.experts.29.down_proj.weight": "model-00001-of-000001.safetensors",
589 "model.layers.1.mlp.experts.30.gate_proj.weight": "model-00001-of-000001.safetensors",
590 "model.layers.1.mlp.experts.30.up_proj.weight": "model-00001-of-000001.safetensors",
591 "model.layers.1.mlp.experts.30.down_proj.weight": "model-00001-of-000001.safetensors",
592 "model.layers.1.mlp.experts.31.gate_proj.weight": "model-00001-of-000001.safetensors",
593 "model.layers.1.mlp.experts.31.up_proj.weight": "model-00001-of-000001.safetensors",
594 "model.layers.1.mlp.experts.31.down_proj.weight": "model-00001-of-000001.safetensors",
595 "model.layers.1.mlp.experts.32.gate_proj.weight": "model-00001-of-000001.safetensors",
596 "model.layers.1.mlp.experts.32.up_proj.weight": "model-00001-of-000001.safetensors",
597 "model.layers.1.mlp.experts.32.down_proj.weight": "model-00001-of-000001.safetensors",
598 "model.layers.1.mlp.experts.33.gate_proj.weight": "model-00001-of-000001.safetensors",
599 "model.layers.1.mlp.experts.33.up_proj.weight": "model-00001-of-000001.safetensors",
600 "model.layers.1.mlp.experts.33.down_proj.weight": "model-00001-of-000001.safetensors",
601 "model.layers.1.mlp.experts.34.gate_proj.weight": "model-00001-of-000001.safetensors",
602 "model.layers.1.mlp.experts.34.up_proj.weight": "model-00001-of-000001.safetensors",
603 "model.layers.1.mlp.experts.34.down_proj.weight": "model-00001-of-000001.safetensors",
604 "model.layers.1.mlp.experts.35.gate_proj.weight": "model-00001-of-000001.safetensors",
605 "model.layers.1.mlp.experts.35.up_proj.weight": "model-00001-of-000001.safetensors",
606 "model.layers.1.mlp.experts.35.down_proj.weight": "model-00001-of-000001.safetensors",
607 "model.layers.1.mlp.experts.36.gate_proj.weight": "model-00001-of-000001.safetensors",
608 "model.layers.1.mlp.experts.36.up_proj.weight": "model-00001-of-000001.safetensors",
609 "model.layers.1.mlp.experts.36.down_proj.weight": "model-00001-of-000001.safetensors",
610 "model.layers.1.mlp.experts.37.gate_proj.weight": "model-00001-of-000001.safetensors",
611 "model.layers.1.mlp.experts.37.up_proj.weight": "model-00001-of-000001.safetensors",
612 "model.layers.1.mlp.experts.37.down_proj.weight": "model-00001-of-000001.safetensors",
613 "model.layers.1.mlp.experts.38.gate_proj.weight": "model-00001-of-000001.safetensors",
614 "model.layers.1.mlp.experts.38.up_proj.weight": "model-00001-of-000001.safetensors",
615 "model.layers.1.mlp.experts.38.down_proj.weight": "model-00001-of-000001.safetensors",
616 "model.layers.1.mlp.experts.39.gate_proj.weight": "model-00001-of-000001.safetensors",
617 "model.layers.1.mlp.experts.39.up_proj.weight": "model-00001-of-000001.safetensors",
618 "model.layers.1.mlp.experts.39.down_proj.weight": "model-00001-of-000001.safetensors",
619 "model.layers.1.mlp.experts.40.gate_proj.weight": "model-00001-of-000001.safetensors",
620 "model.layers.1.mlp.experts.40.up_proj.weight": "model-00001-of-000001.safetensors",
621 "model.layers.1.mlp.experts.40.down_proj.weight": "model-00001-of-000001.safetensors",
622 "model.layers.1.mlp.experts.41.gate_proj.weight": "model-00001-of-000001.safetensors",
623 "model.layers.1.mlp.experts.41.up_proj.weight": "model-00001-of-000001.safetensors",
624 "model.layers.1.mlp.experts.41.down_proj.weight": "model-00001-of-000001.safetensors",
625 "model.layers.1.mlp.experts.42.gate_proj.weight": "model-00001-of-000001.safetensors",
626 "model.layers.1.mlp.experts.42.up_proj.weight": "model-00001-of-000001.safetensors",
627 "model.layers.1.mlp.experts.42.down_proj.weight": "model-00001-of-000001.safetensors",
628 "model.layers.1.mlp.experts.43.gate_proj.weight": "model-00001-of-000001.safetensors",
629 "model.layers.1.mlp.experts.43.up_proj.weight": "model-00001-of-000001.safetensors",
630 "model.layers.1.mlp.experts.43.down_proj.weight": "model-00001-of-000001.safetensors",
631 "model.layers.1.mlp.experts.44.gate_proj.weight": "model-00001-of-000001.safetensors",
632 "model.layers.1.mlp.experts.44.up_proj.weight": "model-00001-of-000001.safetensors",
633 "model.layers.1.mlp.experts.44.down_proj.weight": "model-00001-of-000001.safetensors",
634 "model.layers.1.mlp.experts.45.gate_proj.weight": "model-00001-of-000001.safetensors",
635 "model.layers.1.mlp.experts.45.up_proj.weight": "model-00001-of-000001.safetensors",
636 "model.layers.1.mlp.experts.45.down_proj.weight": "model-00001-of-000001.safetensors",
637 "model.layers.1.mlp.experts.46.gate_proj.weight": "model-00001-of-000001.safetensors",
638 "model.layers.1.mlp.experts.46.up_proj.weight": "model-00001-of-000001.safetensors",
639 "model.layers.1.mlp.experts.46.down_proj.weight": "model-00001-of-000001.safetensors",
640 "model.layers.1.mlp.experts.47.gate_proj.weight": "model-00001-of-000001.safetensors",
641 "model.layers.1.mlp.experts.47.up_proj.weight": "model-00001-of-000001.safetensors",
642 "model.layers.1.mlp.experts.47.down_proj.weight": "model-00001-of-000001.safetensors",
643 "model.layers.1.mlp.experts.48.gate_proj.weight": "model-00001-of-000001.safetensors",
644 "model.layers.1.mlp.experts.48.up_proj.weight": "model-00001-of-000001.safetensors",
645 "model.layers.1.mlp.experts.48.down_proj.weight": "model-00001-of-000001.safetensors",
646 "model.layers.1.mlp.experts.49.gate_proj.weight": "model-00001-of-000001.safetensors",
647 "model.layers.1.mlp.experts.49.up_proj.weight": "model-00001-of-000001.safetensors",
648 "model.layers.1.mlp.experts.49.down_proj.weight": "model-00001-of-000001.safetensors",
649 "model.layers.1.mlp.experts.50.gate_proj.weight": "model-00001-of-000001.safetensors",
650 "model.layers.1.mlp.experts.50.up_proj.weight": "model-00001-of-000001.safetensors",
651 "model.layers.1.mlp.experts.50.down_proj.weight": "model-00001-of-000001.safetensors",
652 "model.layers.1.mlp.experts.51.gate_proj.weight": "model-00001-of-000001.safetensors",
653 "model.layers.1.mlp.experts.51.up_proj.weight": "model-00001-of-000001.safetensors",
654 "model.layers.1.mlp.experts.51.down_proj.weight": "model-00001-of-000001.safetensors",
655 "model.layers.1.mlp.experts.52.gate_proj.weight": "model-00001-of-000001.safetensors",
656 "model.layers.1.mlp.experts.52.up_proj.weight": "model-00001-of-000001.safetensors",
657 "model.layers.1.mlp.experts.52.down_proj.weight": "model-00001-of-000001.safetensors",
658 "model.layers.1.mlp.experts.53.gate_proj.weight": "model-00001-of-000001.safetensors",
659 "model.layers.1.mlp.experts.53.up_proj.weight": "model-00001-of-000001.safetensors",
660 "model.layers.1.mlp.experts.53.down_proj.weight": "model-00001-of-000001.safetensors",
661 "model.layers.1.mlp.experts.54.gate_proj.weight": "model-00001-of-000001.safetensors",
662 "model.layers.1.mlp.experts.54.up_proj.weight": "model-00001-of-000001.safetensors",
663 "model.layers.1.mlp.experts.54.down_proj.weight": "model-00001-of-000001.safetensors",
664 "model.layers.1.mlp.experts.55.gate_proj.weight": "model-00001-of-000001.safetensors",
665 "model.layers.1.mlp.experts.55.up_proj.weight": "model-00001-of-000001.safetensors",
666 "model.layers.1.mlp.experts.55.down_proj.weight": "model-00001-of-000001.safetensors",
667 "model.layers.1.mlp.experts.56.gate_proj.weight": "model-00001-of-000001.safetensors",
668 "model.layers.1.mlp.experts.56.up_proj.weight": "model-00001-of-000001.safetensors",
669 "model.layers.1.mlp.experts.56.down_proj.weight": "model-00001-of-000001.safetensors",
670 "model.layers.1.mlp.experts.57.gate_proj.weight": "model-00001-of-000001.safetensors",
671 "model.layers.1.mlp.experts.57.up_proj.weight": "model-00001-of-000001.safetensors",
672 "model.layers.1.mlp.experts.57.down_proj.weight": "model-00001-of-000001.safetensors",
673 "model.layers.1.mlp.experts.58.gate_proj.weight": "model-00001-of-000001.safetensors",
674 "model.layers.1.mlp.experts.58.up_proj.weight": "model-00001-of-000001.safetensors",
675 "model.layers.1.mlp.experts.58.down_proj.weight": "model-00001-of-000001.safetensors",
676 "model.layers.1.mlp.experts.59.gate_proj.weight": "model-00001-of-000001.safetensors",
677 "model.layers.1.mlp.experts.59.up_proj.weight": "model-00001-of-000001.safetensors",
678 "model.layers.1.mlp.experts.59.down_proj.weight": "model-00001-of-000001.safetensors",
679 "model.layers.1.mlp.experts.60.gate_proj.weight": "model-00001-of-000001.safetensors",
680 "model.layers.1.mlp.experts.60.up_proj.weight": "model-00001-of-000001.safetensors",
681 "model.layers.1.mlp.experts.60.down_proj.weight": "model-00001-of-000001.safetensors",
682 "model.layers.1.mlp.experts.61.gate_proj.weight": "model-00001-of-000001.safetensors",
683 "model.layers.1.mlp.experts.61.up_proj.weight": "model-00001-of-000001.safetensors",
684 "model.layers.1.mlp.experts.61.down_proj.weight": "model-00001-of-000001.safetensors",
685 "model.layers.1.mlp.experts.62.gate_proj.weight": "model-00001-of-000001.safetensors",
686 "model.layers.1.mlp.experts.62.up_proj.weight": "model-00001-of-000001.safetensors",
687 "model.layers.1.mlp.experts.62.down_proj.weight": "model-00001-of-000001.safetensors",
688 "model.layers.1.mlp.experts.63.gate_proj.weight": "model-00001-of-000001.safetensors",
689 "model.layers.1.mlp.experts.63.up_proj.weight": "model-00001-of-000001.safetensors",
690 "model.layers.1.mlp.experts.63.down_proj.weight": "model-00001-of-000001.safetensors",
691 "model.layers.1.input_layernorm.weight": "model-00001-of-000001.safetensors",
692 "model.layers.1.post_attention_layernorm.weight": "model-00001-of-000001.safetensors",
693 "model.layers.2.self_attn.q_proj.weight": "model-00001-of-000001.safetensors",
694 "model.layers.2.self_attn.k_proj.weight": "model-00001-of-000001.safetensors",
695 "model.layers.2.self_attn.v_proj.weight": "model-00001-of-000001.safetensors",
696 "model.layers.2.self_attn.o_proj.weight": "model-00001-of-000001.safetensors",
697 "model.layers.2.mlp.gate.weight": "model-00001-of-000001.safetensors",
698 "model.layers.2.mlp.shared_experts.gate_proj.weight": "model-00001-of-000001.safetensors",
699 "model.layers.2.mlp.shared_experts.up_proj.weight": "model-00001-of-000001.safetensors",
700 "model.layers.2.mlp.shared_experts.down_proj.weight": "model-00001-of-000001.safetensors",
701 "model.layers.2.mlp.experts.0.gate_proj.weight": "model-00001-of-000001.safetensors",
702 "model.layers.2.mlp.experts.0.up_proj.weight": "model-00001-of-000001.safetensors",
703 "model.layers.2.mlp.experts.0.down_proj.weight": "model-00001-of-000001.safetensors",
704 "model.layers.2.mlp.experts.1.gate_proj.weight": "model-00001-of-000001.safetensors",
705 "model.layers.2.mlp.experts.1.up_proj.weight": "model-00001-of-000001.safetensors",
706 "model.layers.2.mlp.experts.1.down_proj.weight": "model-00001-of-000001.safetensors",
707 "model.layers.2.mlp.experts.2.gate_proj.weight": "model-00001-of-000001.safetensors",
708 "model.layers.2.mlp.experts.2.up_proj.weight": "model-00001-of-000001.safetensors",
709 "model.layers.2.mlp.experts.2.down_proj.weight": "model-00001-of-000001.safetensors",
710 "model.layers.2.mlp.experts.3.gate_proj.weight": "model-00001-of-000001.safetensors",
711 "model.layers.2.mlp.experts.3.up_proj.weight": "model-00001-of-000001.safetensors",
712 "model.layers.2.mlp.experts.3.down_proj.weight": "model-00001-of-000001.safetensors",
713 "model.layers.2.mlp.experts.4.gate_proj.weight": "model-00001-of-000001.safetensors",
714 "model.layers.2.mlp.experts.4.up_proj.weight": "model-00001-of-000001.safetensors",
715 "model.layers.2.mlp.experts.4.down_proj.weight": "model-00001-of-000001.safetensors",
716 "model.layers.2.mlp.experts.5.gate_proj.weight": "model-00001-of-000001.safetensors",
717 "model.layers.2.mlp.experts.5.up_proj.weight": "model-00001-of-000001.safetensors",
718 "model.layers.2.mlp.experts.5.down_proj.weight": "model-00001-of-000001.safetensors",
719 "model.layers.2.mlp.experts.6.gate_proj.weight": "model-00001-of-000001.safetensors",
720 "model.layers.2.mlp.experts.6.up_proj.weight": "model-00001-of-000001.safetensors",
721 "model.layers.2.mlp.experts.6.down_proj.weight": "model-00001-of-000001.safetensors",
722 "model.layers.2.mlp.experts.7.gate_proj.weight": "model-00001-of-000001.safetensors",
723 "model.layers.2.mlp.experts.7.up_proj.weight": "model-00001-of-000001.safetensors",
724 "model.layers.2.mlp.experts.7.down_proj.weight": "model-00001-of-000001.safetensors",
725 "model.layers.2.mlp.experts.8.gate_proj.weight": "model-00001-of-000001.safetensors",
726 "model.layers.2.mlp.experts.8.up_proj.weight": "model-00001-of-000001.safetensors",
727 "model.layers.2.mlp.experts.8.down_proj.weight": "model-00001-of-000001.safetensors",
728 "model.layers.2.mlp.experts.9.gate_proj.weight": "model-00001-of-000001.safetensors",
729 "model.layers.2.mlp.experts.9.up_proj.weight": "model-00001-of-000001.safetensors",
730 "model.layers.2.mlp.experts.9.down_proj.weight": "model-00001-of-000001.safetensors",
731 "model.layers.2.mlp.experts.10.gate_proj.weight": "model-00001-of-000001.safetensors",
732 "model.layers.2.mlp.experts.10.up_proj.weight": "model-00001-of-000001.safetensors",
733 "model.layers.2.mlp.experts.10.down_proj.weight": "model-00001-of-000001.safetensors",
734 "model.layers.2.mlp.experts.11.gate_proj.weight": "model-00001-of-000001.safetensors",
735 "model.layers.2.mlp.experts.11.up_proj.weight": "model-00001-of-000001.safetensors",
736 "model.layers.2.mlp.experts.11.down_proj.weight": "model-00001-of-000001.safetensors",
737 "model.layers.2.mlp.experts.12.gate_proj.weight": "model-00001-of-000001.safetensors",
738 "model.layers.2.mlp.experts.12.up_proj.weight": "model-00001-of-000001.safetensors",
739 "model.layers.2.mlp.experts.12.down_proj.weight": "model-00001-of-000001.safetensors",
740 "model.layers.2.mlp.experts.13.gate_proj.weight": "model-00001-of-000001.safetensors",
741 "model.layers.2.mlp.experts.13.up_proj.weight": "model-00001-of-000001.safetensors",
742 "model.layers.2.mlp.experts.13.down_proj.weight": "model-00001-of-000001.safetensors",
743 "model.layers.2.mlp.experts.14.gate_proj.weight": "model-00001-of-000001.safetensors",
744 "model.layers.2.mlp.experts.14.up_proj.weight": "model-00001-of-000001.safetensors",
745 "model.layers.2.mlp.experts.14.down_proj.weight": "model-00001-of-000001.safetensors",
746 "model.layers.2.mlp.experts.15.gate_proj.weight": "model-00001-of-000001.safetensors",
747 "model.layers.2.mlp.experts.15.up_proj.weight": "model-00001-of-000001.safetensors",
748 "model.layers.2.mlp.experts.15.down_proj.weight": "model-00001-of-000001.safetensors",
749 "model.layers.2.mlp.experts.16.gate_proj.weight": "model-00001-of-000001.safetensors",
750 "model.layers.2.mlp.experts.16.up_proj.weight": "model-00001-of-000001.safetensors",
751 "model.layers.2.mlp.experts.16.down_proj.weight": "model-00001-of-000001.safetensors",
752 "model.layers.2.mlp.experts.17.gate_proj.weight": "model-00001-of-000001.safetensors",
753 "model.layers.2.mlp.experts.17.up_proj.weight": "model-00001-of-000001.safetensors",
754 "model.layers.2.mlp.experts.17.down_proj.weight": "model-00001-of-000001.safetensors",
755 "model.layers.2.mlp.experts.18.gate_proj.weight": "model-00001-of-000001.safetensors",
756 "model.layers.2.mlp.experts.18.up_proj.weight": "model-00001-of-000001.safetensors",
757 "model.layers.2.mlp.experts.18.down_proj.weight": "model-00001-of-000001.safetensors",
758 "model.layers.2.mlp.experts.19.gate_proj.weight": "model-00001-of-000001.safetensors",
759 "model.layers.2.mlp.experts.19.up_proj.weight": "model-00001-of-000001.safetensors",
760 "model.layers.2.mlp.experts.19.down_proj.weight": "model-00001-of-000001.safetensors",
761 "model.layers.2.mlp.experts.20.gate_proj.weight": "model-00001-of-000001.safetensors",
762 "model.layers.2.mlp.experts.20.up_proj.weight": "model-00001-of-000001.safetensors",
763 "model.layers.2.mlp.experts.20.down_proj.weight": "model-00001-of-000001.safetensors",
764 "model.layers.2.mlp.experts.21.gate_proj.weight": "model-00001-of-000001.safetensors",
765 "model.layers.2.mlp.experts.21.up_proj.weight": "model-00001-of-000001.safetensors",
766 "model.layers.2.mlp.experts.21.down_proj.weight": "model-00001-of-000001.safetensors",
767 "model.layers.2.mlp.experts.22.gate_proj.weight": "model-00001-of-000001.safetensors",
768 "model.layers.2.mlp.experts.22.up_proj.weight": "model-00001-of-000001.safetensors",
769 "model.layers.2.mlp.experts.22.down_proj.weight": "model-00001-of-000001.safetensors",
770 "model.layers.2.mlp.experts.23.gate_proj.weight": "model-00001-of-000001.safetensors",
771 "model.layers.2.mlp.experts.23.up_proj.weight": "model-00001-of-000001.safetensors",
772 "model.layers.2.mlp.experts.23.down_proj.weight": "model-00001-of-000001.safetensors",
773 "model.layers.2.mlp.experts.24.gate_proj.weight": "model-00001-of-000001.safetensors",
774 "model.layers.2.mlp.experts.24.up_proj.weight": "model-00001-of-000001.safetensors",
775 "model.layers.2.mlp.experts.24.down_proj.weight": "model-00001-of-000001.safetensors",
776 "model.layers.2.mlp.experts.25.gate_proj.weight": "model-00001-of-000001.safetensors",
777 "model.layers.2.mlp.experts.25.up_proj.weight": "model-00001-of-000001.safetensors",
778 "model.layers.2.mlp.experts.25.down_proj.weight": "model-00001-of-000001.safetensors",
779 "model.layers.2.mlp.experts.26.gate_proj.weight": "model-00001-of-000001.safetensors",
780 "model.layers.2.mlp.experts.26.up_proj.weight": "model-00001-of-000001.safetensors",
781 "model.layers.2.mlp.experts.26.down_proj.weight": "model-00001-of-000001.safetensors",
782 "model.layers.2.mlp.experts.27.gate_proj.weight": "model-00001-of-000001.safetensors",
783 "model.layers.2.mlp.experts.27.up_proj.weight": "model-00001-of-000001.safetensors",
784 "model.layers.2.mlp.experts.27.down_proj.weight": "model-00001-of-000001.safetensors",
785 "model.layers.2.mlp.experts.28.gate_proj.weight": "model-00001-of-000001.safetensors",
786 "model.layers.2.mlp.experts.28.up_proj.weight": "model-00001-of-000001.safetensors",
787 "model.layers.2.mlp.experts.28.down_proj.weight": "model-00001-of-000001.safetensors",
788 "model.layers.2.mlp.experts.29.gate_proj.weight": "model-00001-of-000001.safetensors",
789 "model.layers.2.mlp.experts.29.up_proj.weight": "model-00001-of-000001.safetensors",
790 "model.layers.2.mlp.experts.29.down_proj.weight": "model-00001-of-000001.safetensors",
791 "model.layers.2.mlp.experts.30.gate_proj.weight": "model-00001-of-000001.safetensors",
792 "model.layers.2.mlp.experts.30.up_proj.weight": "model-00001-of-000001.safetensors",
793 "model.layers.2.mlp.experts.30.down_proj.weight": "model-00001-of-000001.safetensors",
794 "model.layers.2.mlp.experts.31.gate_proj.weight": "model-00001-of-000001.safetensors",
795 "model.layers.2.mlp.experts.31.up_proj.weight": "model-00001-of-000001.safetensors",
796 "model.layers.2.mlp.experts.31.down_proj.weight": "model-00001-of-000001.safetensors",
797 "model.layers.2.mlp.experts.32.gate_proj.weight": "model-00001-of-000001.safetensors",
798 "model.layers.2.mlp.experts.32.up_proj.weight": "model-00001-of-000001.safetensors",
799 "model.layers.2.mlp.experts.32.down_proj.weight": "model-00001-of-000001.safetensors",
800 "model.layers.2.mlp.experts.33.gate_proj.weight": "model-00001-of-000001.safetensors",
801 "model.layers.2.mlp.experts.33.up_proj.weight": "model-00001-of-000001.safetensors",
802 "model.layers.2.mlp.experts.33.down_proj.weight": "model-00001-of-000001.safetensors",
803 "model.layers.2.mlp.experts.34.gate_proj.weight": "model-00001-of-000001.safetensors",
804 "model.layers.2.mlp.experts.34.up_proj.weight": "model-00001-of-000001.safetensors",
805 "model.layers.2.mlp.experts.34.down_proj.weight": "model-00001-of-000001.safetensors",
806 "model.layers.2.mlp.experts.35.gate_proj.weight": "model-00001-of-000001.safetensors",
807 "model.layers.2.mlp.experts.35.up_proj.weight": "model-00001-of-000001.safetensors",
808 "model.layers.2.mlp.experts.35.down_proj.weight": "model-00001-of-000001.safetensors",
809 "model.layers.2.mlp.experts.36.gate_proj.weight": "model-00001-of-000001.safetensors",
810 "model.layers.2.mlp.experts.36.up_proj.weight": "model-00001-of-000001.safetensors",
811 "model.layers.2.mlp.experts.36.down_proj.weight": "model-00001-of-000001.safetensors",
812 "model.layers.2.mlp.experts.37.gate_proj.weight": "model-00001-of-000001.safetensors",
813 "model.layers.2.mlp.experts.37.up_proj.weight": "model-00001-of-000001.safetensors",
814 "model.layers.2.mlp.experts.37.down_proj.weight": "model-00001-of-000001.safetensors",
815 "model.layers.2.mlp.experts.38.gate_proj.weight": "model-00001-of-000001.safetensors",
816 "model.layers.2.mlp.experts.38.up_proj.weight": "model-00001-of-000001.safetensors",
817 "model.layers.2.mlp.experts.38.down_proj.weight": "model-00001-of-000001.safetensors",
818 "model.layers.2.mlp.experts.39.gate_proj.weight": "model-00001-of-000001.safetensors",
819 "model.layers.2.mlp.experts.39.up_proj.weight": "model-00001-of-000001.safetensors",
820 "model.layers.2.mlp.experts.39.down_proj.weight": "model-00001-of-000001.safetensors",
821 "model.layers.2.mlp.experts.40.gate_proj.weight": "model-00001-of-000001.safetensors",
822 "model.layers.2.mlp.experts.40.up_proj.weight": "model-00001-of-000001.safetensors",
823 "model.layers.2.mlp.experts.40.down_proj.weight": "model-00001-of-000001.safetensors",
824 "model.layers.2.mlp.experts.41.gate_proj.weight": "model-00001-of-000001.safetensors",
825 "model.layers.2.mlp.experts.41.up_proj.weight": "model-00001-of-000001.safetensors",
826 "model.layers.2.mlp.experts.41.down_proj.weight": "model-00001-of-000001.safetensors",
827 "model.layers.2.mlp.experts.42.gate_proj.weight": "model-00001-of-000001.safetensors",
828 "model.layers.2.mlp.experts.42.up_proj.weight": "model-00001-of-000001.safetensors",
829 "model.layers.2.mlp.experts.42.down_proj.weight": "model-00001-of-000001.safetensors",
830 "model.layers.2.mlp.experts.43.gate_proj.weight": "model-00001-of-000001.safetensors",
831 "model.layers.2.mlp.experts.43.up_proj.weight": "model-00001-of-000001.safetensors",
832 "model.layers.2.mlp.experts.43.down_proj.weight": "model-00001-of-000001.safetensors",
833 "model.layers.2.mlp.experts.44.gate_proj.weight": "model-00001-of-000001.safetensors",
834 "model.layers.2.mlp.experts.44.up_proj.weight": "model-00001-of-000001.safetensors",
835 "model.layers.2.mlp.experts.44.down_proj.weight": "model-00001-of-000001.safetensors",
836 "model.layers.2.mlp.experts.45.gate_proj.weight": "model-00001-of-000001.safetensors",
837 "model.layers.2.mlp.experts.45.up_proj.weight": "model-00001-of-000001.safetensors",
838 "model.layers.2.mlp.experts.45.down_proj.weight": "model-00001-of-000001.safetensors",
839 "model.layers.2.mlp.experts.46.gate_proj.weight": "model-00001-of-000001.safetensors",
840 "model.layers.2.mlp.experts.46.up_proj.weight": "model-00001-of-000001.safetensors",
841 "model.layers.2.mlp.experts.46.down_proj.weight": "model-00001-of-000001.safetensors",
842 "model.layers.2.mlp.experts.47.gate_proj.weight": "model-00001-of-000001.safetensors",
843 "model.layers.2.mlp.experts.47.up_proj.weight": "model-00001-of-000001.safetensors",
844 "model.layers.2.mlp.experts.47.down_proj.weight": "model-00001-of-000001.safetensors",
845 "model.layers.2.mlp.experts.48.gate_proj.weight": "model-00001-of-000001.safetensors",
846 "model.layers.2.mlp.experts.48.up_proj.weight": "model-00001-of-000001.safetensors",
847 "model.layers.2.mlp.experts.48.down_proj.weight": "model-00001-of-000001.safetensors",
848 "model.layers.2.mlp.experts.49.gate_proj.weight": "model-00001-of-000001.safetensors",
849 "model.layers.2.mlp.experts.49.up_proj.weight": "model-00001-of-000001.safetensors",
850 "model.layers.2.mlp.experts.49.down_proj.weight": "model-00001-of-000001.safetensors",
851 "model.layers.2.mlp.experts.50.gate_proj.weight": "model-00001-of-000001.safetensors",
852 "model.layers.2.mlp.experts.50.up_proj.weight": "model-00001-of-000001.safetensors",
853 "model.layers.2.mlp.experts.50.down_proj.weight": "model-00001-of-000001.safetensors",
854 "model.layers.2.mlp.experts.51.gate_proj.weight": "model-00001-of-000001.safetensors",
855 "model.layers.2.mlp.experts.51.up_proj.weight": "model-00001-of-000001.safetensors",
856 "model.layers.2.mlp.experts.51.down_proj.weight": "model-00001-of-000001.safetensors",
857 "model.layers.2.mlp.experts.52.gate_proj.weight": "model-00001-of-000001.safetensors",
858 "model.layers.2.mlp.experts.52.up_proj.weight": "model-00001-of-000001.safetensors",
859 "model.layers.2.mlp.experts.52.down_proj.weight": "model-00001-of-000001.safetensors",
860 "model.layers.2.mlp.experts.53.gate_proj.weight": "model-00001-of-000001.safetensors",
861 "model.layers.2.mlp.experts.53.up_proj.weight": "model-00001-of-000001.safetensors",
862 "model.layers.2.mlp.experts.53.down_proj.weight": "model-00001-of-000001.safetensors",
863 "model.layers.2.mlp.experts.54.gate_proj.weight": "model-00001-of-000001.safetensors",
864 "model.layers.2.mlp.experts.54.up_proj.weight": "model-00001-of-000001.safetensors",
865 "model.layers.2.mlp.experts.54.down_proj.weight": "model-00001-of-000001.safetensors",
866 "model.layers.2.mlp.experts.55.gate_proj.weight": "model-00001-of-000001.safetensors",
867 "model.layers.2.mlp.experts.55.up_proj.weight": "model-00001-of-000001.safetensors",
868 "model.layers.2.mlp.experts.55.down_proj.weight": "model-00001-of-000001.safetensors",
869 "model.layers.2.mlp.experts.56.gate_proj.weight": "model-00001-of-000001.safetensors",
870 "model.layers.2.mlp.experts.56.up_proj.weight": "model-00001-of-000001.safetensors",
871 "model.layers.2.mlp.experts.56.down_proj.weight": "model-00001-of-000001.safetensors",
872 "model.layers.2.mlp.experts.57.gate_proj.weight": "model-00001-of-000001.safetensors",
873 "model.layers.2.mlp.experts.57.up_proj.weight": "model-00001-of-000001.safetensors",
874 "model.layers.2.mlp.experts.57.down_proj.weight": "model-00001-of-000001.safetensors",
875 "model.layers.2.mlp.experts.58.gate_proj.weight": "model-00001-of-000001.safetensors",
876 "model.layers.2.mlp.experts.58.up_proj.weight": "model-00001-of-000001.safetensors",
877 "model.layers.2.mlp.experts.58.down_proj.weight": "model-00001-of-000001.safetensors",
878 "model.layers.2.mlp.experts.59.gate_proj.weight": "model-00001-of-000001.safetensors",
879 "model.layers.2.mlp.experts.59.up_proj.weight": "model-00001-of-000001.safetensors",
880 "model.layers.2.mlp.experts.59.down_proj.weight": "model-00001-of-000001.safetensors",
881 "model.layers.2.mlp.experts.60.gate_proj.weight": "model-00001-of-000001.safetensors",
882 "model.layers.2.mlp.experts.60.up_proj.weight": "model-00001-of-000001.safetensors",
883 "model.layers.2.mlp.experts.60.down_proj.weight": "model-00001-of-000001.safetensors",
884 "model.layers.2.mlp.experts.61.gate_proj.weight": "model-00001-of-000001.safetensors",
885 "model.layers.2.mlp.experts.61.up_proj.weight": "model-00001-of-000001.safetensors",
886 "model.layers.2.mlp.experts.61.down_proj.weight": "model-00001-of-000001.safetensors",
887 "model.layers.2.mlp.experts.62.gate_proj.weight": "model-00001-of-000001.safetensors",
888 "model.layers.2.mlp.experts.62.up_proj.weight": "model-00001-of-000001.safetensors",
889 "model.layers.2.mlp.experts.62.down_proj.weight": "model-00001-of-000001.safetensors",
890 "model.layers.2.mlp.experts.63.gate_proj.weight": "model-00001-of-000001.safetensors",
891 "model.layers.2.mlp.experts.63.up_proj.weight": "model-00001-of-000001.safetensors",
892 "model.layers.2.mlp.experts.63.down_proj.weight": "model-00001-of-000001.safetensors",
893 "model.layers.2.input_layernorm.weight": "model-00001-of-000001.safetensors",
894 "model.layers.2.post_attention_layernorm.weight": "model-00001-of-000001.safetensors",
895 "model.layers.3.self_attn.q_proj.weight": "model-00001-of-000001.safetensors",
896 "model.layers.3.self_attn.k_proj.weight": "model-00001-of-000001.safetensors",
897 "model.layers.3.self_attn.v_proj.weight": "model-00001-of-000001.safetensors",
898 "model.layers.3.self_attn.o_proj.weight": "model-00001-of-000001.safetensors",
899 "model.layers.3.mlp.gate.weight": "model-00001-of-000001.safetensors",
900 "model.layers.3.mlp.shared_experts.gate_proj.weight": "model-00001-of-000001.safetensors",
901 "model.layers.3.mlp.shared_experts.up_proj.weight": "model-00001-of-000001.safetensors",
902 "model.layers.3.mlp.shared_experts.down_proj.weight": "model-00001-of-000001.safetensors",
903 "model.layers.3.mlp.experts.0.gate_proj.weight": "model-00001-of-000001.safetensors",
904 "model.layers.3.mlp.experts.0.up_proj.weight": "model-00001-of-000001.safetensors",
905 "model.layers.3.mlp.experts.0.down_proj.weight": "model-00001-of-000001.safetensors",
906 "model.layers.3.mlp.experts.1.gate_proj.weight": "model-00001-of-000001.safetensors",
907 "model.layers.3.mlp.experts.1.up_proj.weight": "model-00001-of-000001.safetensors",
908 "model.layers.3.mlp.experts.1.down_proj.weight": "model-00001-of-000001.safetensors",
909 "model.layers.3.mlp.experts.2.gate_proj.weight": "model-00001-of-000001.safetensors",
910 "model.layers.3.mlp.experts.2.up_proj.weight": "model-00001-of-000001.safetensors",
911 "model.layers.3.mlp.experts.2.down_proj.weight": "model-00001-of-000001.safetensors",
912 "model.layers.3.mlp.experts.3.gate_proj.weight": "model-00001-of-000001.safetensors",
913 "model.layers.3.mlp.experts.3.up_proj.weight": "model-00001-of-000001.safetensors",
914 "model.layers.3.mlp.experts.3.down_proj.weight": "model-00001-of-000001.safetensors",
915 "model.layers.3.mlp.experts.4.gate_proj.weight": "model-00001-of-000001.safetensors",
916 "model.layers.3.mlp.experts.4.up_proj.weight": "model-00001-of-000001.safetensors",
917 "model.layers.3.mlp.experts.4.down_proj.weight": "model-00001-of-000001.safetensors",
918 "model.layers.3.mlp.experts.5.gate_proj.weight": "model-00001-of-000001.safetensors",
919 "model.layers.3.mlp.experts.5.up_proj.weight": "model-00001-of-000001.safetensors",
920 "model.layers.3.mlp.experts.5.down_proj.weight": "model-00001-of-000001.safetensors",
921 "model.layers.3.mlp.experts.6.gate_proj.weight": "model-00001-of-000001.safetensors",
922 "model.layers.3.mlp.experts.6.up_proj.weight": "model-00001-of-000001.safetensors",
923 "model.layers.3.mlp.experts.6.down_proj.weight": "model-00001-of-000001.safetensors",
924 "model.layers.3.mlp.experts.7.gate_proj.weight": "model-00001-of-000001.safetensors",
925 "model.layers.3.mlp.experts.7.up_proj.weight": "model-00001-of-000001.safetensors",
926 "model.layers.3.mlp.experts.7.down_proj.weight": "model-00001-of-000001.safetensors",
927 "model.layers.3.mlp.experts.8.gate_proj.weight": "model-00001-of-000001.safetensors",
928 "model.layers.3.mlp.experts.8.up_proj.weight": "model-00001-of-000001.safetensors",
929 "model.layers.3.mlp.experts.8.down_proj.weight": "model-00001-of-000001.safetensors",
930 "model.layers.3.mlp.experts.9.gate_proj.weight": "model-00001-of-000001.safetensors",
931 "model.layers.3.mlp.experts.9.up_proj.weight": "model-00001-of-000001.safetensors",
932 "model.layers.3.mlp.experts.9.down_proj.weight": "model-00001-of-000001.safetensors",
933 "model.layers.3.mlp.experts.10.gate_proj.weight": "model-00001-of-000001.safetensors",
934 "model.layers.3.mlp.experts.10.up_proj.weight": "model-00001-of-000001.safetensors",
935 "model.layers.3.mlp.experts.10.down_proj.weight": "model-00001-of-000001.safetensors",
936 "model.layers.3.mlp.experts.11.gate_proj.weight": "model-00001-of-000001.safetensors",
937 "model.layers.3.mlp.experts.11.up_proj.weight": "model-00001-of-000001.safetensors",
938 "model.layers.3.mlp.experts.11.down_proj.weight": "model-00001-of-000001.safetensors",
939 "model.layers.3.mlp.experts.12.gate_proj.weight": "model-00001-of-000001.safetensors",
940 "model.layers.3.mlp.experts.12.up_proj.weight": "model-00001-of-000001.safetensors",
941 "model.layers.3.mlp.experts.12.down_proj.weight": "model-00001-of-000001.safetensors",
942 "model.layers.3.mlp.experts.13.gate_proj.weight": "model-00001-of-000001.safetensors",
943 "model.layers.3.mlp.experts.13.up_proj.weight": "model-00001-of-000001.safetensors",
944 "model.layers.3.mlp.experts.13.down_proj.weight": "model-00001-of-000001.safetensors",
945 "model.layers.3.mlp.experts.14.gate_proj.weight": "model-00001-of-000001.safetensors",
946 "model.layers.3.mlp.experts.14.up_proj.weight": "model-00001-of-000001.safetensors",
947 "model.layers.3.mlp.experts.14.down_proj.weight": "model-00001-of-000001.safetensors",
948 "model.layers.3.mlp.experts.15.gate_proj.weight": "model-00001-of-000001.safetensors",
949 "model.layers.3.mlp.experts.15.up_proj.weight": "model-00001-of-000001.safetensors",
950 "model.layers.3.mlp.experts.15.down_proj.weight": "model-00001-of-000001.safetensors",
951 "model.layers.3.mlp.experts.16.gate_proj.weight": "model-00001-of-000001.safetensors",
952 "model.layers.3.mlp.experts.16.up_proj.weight": "model-00001-of-000001.safetensors",
953 "model.layers.3.mlp.experts.16.down_proj.weight": "model-00001-of-000001.safetensors",
954 "model.layers.3.mlp.experts.17.gate_proj.weight": "model-00001-of-000001.safetensors",
955 "model.layers.3.mlp.experts.17.up_proj.weight": "model-00001-of-000001.safetensors",
956 "model.layers.3.mlp.experts.17.down_proj.weight": "model-00001-of-000001.safetensors",
957 "model.layers.3.mlp.experts.18.gate_proj.weight": "model-00001-of-000001.safetensors",
958 "model.layers.3.mlp.experts.18.up_proj.weight": "model-00001-of-000001.safetensors",
959 "model.layers.3.mlp.experts.18.down_proj.weight": "model-00001-of-000001.safetensors",
960 "model.layers.3.mlp.experts.19.gate_proj.weight": "model-00001-of-000001.safetensors",
961 "model.layers.3.mlp.experts.19.up_proj.weight": "model-00001-of-000001.safetensors",
962 "model.layers.3.mlp.experts.19.down_proj.weight": "model-00001-of-000001.safetensors",
963 "model.layers.3.mlp.experts.20.gate_proj.weight": "model-00001-of-000001.safetensors",
964 "model.layers.3.mlp.experts.20.up_proj.weight": "model-00001-of-000001.safetensors",
965 "model.layers.3.mlp.experts.20.down_proj.weight": "model-00001-of-000001.safetensors",
966 "model.layers.3.mlp.experts.21.gate_proj.weight": "model-00001-of-000001.safetensors",
967 "model.layers.3.mlp.experts.21.up_proj.weight": "model-00001-of-000001.safetensors",
968 "model.layers.3.mlp.experts.21.down_proj.weight": "model-00001-of-000001.safetensors",
969 "model.layers.3.mlp.experts.22.gate_proj.weight": "model-00001-of-000001.safetensors",
970 "model.layers.3.mlp.experts.22.up_proj.weight": "model-00001-of-000001.safetensors",
971 "model.layers.3.mlp.experts.22.down_proj.weight": "model-00001-of-000001.safetensors",
972 "model.layers.3.mlp.experts.23.gate_proj.weight": "model-00001-of-000001.safetensors",
973 "model.layers.3.mlp.experts.23.up_proj.weight": "model-00001-of-000001.safetensors",
974 "model.layers.3.mlp.experts.23.down_proj.weight": "model-00001-of-000001.safetensors",
975 "model.layers.3.mlp.experts.24.gate_proj.weight": "model-00001-of-000001.safetensors",
976 "model.layers.3.mlp.experts.24.up_proj.weight": "model-00001-of-000001.safetensors",
977 "model.layers.3.mlp.experts.24.down_proj.weight": "model-00001-of-000001.safetensors",
978 "model.layers.3.mlp.experts.25.gate_proj.weight": "model-00001-of-000001.safetensors",
979 "model.layers.3.mlp.experts.25.up_proj.weight": "model-00001-of-000001.safetensors",
980 "model.layers.3.mlp.experts.25.down_proj.weight": "model-00001-of-000001.safetensors",
981 "model.layers.3.mlp.experts.26.gate_proj.weight": "model-00001-of-000001.safetensors",
982 "model.layers.3.mlp.experts.26.up_proj.weight": "model-00001-of-000001.safetensors",
983 "model.layers.3.mlp.experts.26.down_proj.weight": "model-00001-of-000001.safetensors",
984 "model.layers.3.mlp.experts.27.gate_proj.weight": "model-00001-of-000001.safetensors",
985 "model.layers.3.mlp.experts.27.up_proj.weight": "model-00001-of-000001.safetensors",
986 "model.layers.3.mlp.experts.27.down_proj.weight": "model-00001-of-000001.safetensors",
987 "model.layers.3.mlp.experts.28.gate_proj.weight": "model-00001-of-000001.safetensors",
988 "model.layers.3.mlp.experts.28.up_proj.weight": "model-00001-of-000001.safetensors",
989 "model.layers.3.mlp.experts.28.down_proj.weight": "model-00001-of-000001.safetensors",
990 "model.layers.3.mlp.experts.29.gate_proj.weight": "model-00001-of-000001.safetensors",
991 "model.layers.3.mlp.experts.29.up_proj.weight": "model-00001-of-000001.safetensors",
992 "model.layers.3.mlp.experts.29.down_proj.weight": "model-00001-of-000001.safetensors",
993 "model.layers.3.mlp.experts.30.gate_proj.weight": "model-00001-of-000001.safetensors",
994 "model.layers.3.mlp.experts.30.up_proj.weight": "model-00001-of-000001.safetensors",
995 "model.layers.3.mlp.experts.30.down_proj.weight": "model-00001-of-000001.safetensors",
996 "model.layers.3.mlp.experts.31.gate_proj.weight": "model-00001-of-000001.safetensors",
997 "model.layers.3.mlp.experts.31.up_proj.weight": "model-00001-of-000001.safetensors",
998 "model.layers.3.mlp.experts.31.down_proj.weight": "model-00001-of-000001.safetensors",
999 "model.layers.3.mlp.experts.32.gate_proj.weight": "model-00001-of-000001.safetensors",
1000 "model.layers.3.mlp.experts.32.up_proj.weight": "model-00001-of-000001.safetensors",
1001 "model.layers.3.mlp.experts.32.down_proj.weight": "model-00001-of-000001.safetensors",
1002 "model.layers.3.mlp.experts.33.gate_proj.weight": "model-00001-of-000001.safetensors",
1003 "model.layers.3.mlp.experts.33.up_proj.weight": "model-00001-of-000001.safetensors",
1004 "model.layers.3.mlp.experts.33.down_proj.weight": "model-00001-of-000001.safetensors",
1005 "model.layers.3.mlp.experts.34.gate_proj.weight": "model-00001-of-000001.safetensors",
1006 "model.layers.3.mlp.experts.34.up_proj.weight": "model-00001-of-000001.safetensors",
1007 "model.layers.3.mlp.experts.34.down_proj.weight": "model-00001-of-000001.safetensors",
1008 "model.layers.3.mlp.experts.35.gate_proj.weight": "model-00001-of-000001.safetensors",
1009 "model.layers.3.mlp.experts.35.up_proj.weight": "model-00001-of-000001.safetensors",
1010 "model.layers.3.mlp.experts.35.down_proj.weight": "model-00001-of-000001.safetensors",
1011 "model.layers.3.mlp.experts.36.gate_proj.weight": "model-00001-of-000001.safetensors",
1012 "model.layers.3.mlp.experts.36.up_proj.weight": "model-00001-of-000001.safetensors",
1013 "model.layers.3.mlp.experts.36.down_proj.weight": "model-00001-of-000001.safetensors",
1014 "model.layers.3.mlp.experts.37.gate_proj.weight": "model-00001-of-000001.safetensors",
1015 "model.layers.3.mlp.experts.37.up_proj.weight": "model-00001-of-000001.safetensors",
1016 "model.layers.3.mlp.experts.37.down_proj.weight": "model-00001-of-000001.safetensors",
1017 "model.layers.3.mlp.experts.38.gate_proj.weight": "model-00001-of-000001.safetensors",
1018 "model.layers.3.mlp.experts.38.up_proj.weight": "model-00001-of-000001.safetensors",
1019 "model.layers.3.mlp.experts.38.down_proj.weight": "model-00001-of-000001.safetensors",
1020 "model.layers.3.mlp.experts.39.gate_proj.weight": "model-00001-of-000001.safetensors",
1021 "model.layers.3.mlp.experts.39.up_proj.weight": "model-00001-of-000001.safetensors",
1022 "model.layers.3.mlp.experts.39.down_proj.weight": "model-00001-of-000001.safetensors",
1023 "model.layers.3.mlp.experts.40.gate_proj.weight": "model-00001-of-000001.safetensors",
1024 "model.layers.3.mlp.experts.40.up_proj.weight": "model-00001-of-000001.safetensors",
1025 "model.layers.3.mlp.experts.40.down_proj.weight": "model-00001-of-000001.safetensors",
1026 "model.layers.3.mlp.experts.41.gate_proj.weight": "model-00001-of-000001.safetensors",
1027 "model.layers.3.mlp.experts.41.up_proj.weight": "model-00001-of-000001.safetensors",
1028 "model.layers.3.mlp.experts.41.down_proj.weight": "model-00001-of-000001.safetensors",
1029 "model.layers.3.mlp.experts.42.gate_proj.weight": "model-00001-of-000001.safetensors",
1030 "model.layers.3.mlp.experts.42.up_proj.weight": "model-00001-of-000001.safetensors",
1031 "model.layers.3.mlp.experts.42.down_proj.weight": "model-00001-of-000001.safetensors",
1032 "model.layers.3.mlp.experts.43.gate_proj.weight": "model-00001-of-000001.safetensors",
1033 "model.layers.3.mlp.experts.43.up_proj.weight": "model-00001-of-000001.safetensors",
1034 "model.layers.3.mlp.experts.43.down_proj.weight": "model-00001-of-000001.safetensors",
1035 "model.layers.3.mlp.experts.44.gate_proj.weight": "model-00001-of-000001.safetensors",
1036 "model.layers.3.mlp.experts.44.up_proj.weight": "model-00001-of-000001.safetensors",
1037 "model.layers.3.mlp.experts.44.down_proj.weight": "model-00001-of-000001.safetensors",
1038 "model.layers.3.mlp.experts.45.gate_proj.weight": "model-00001-of-000001.safetensors",
1039 "model.layers.3.mlp.experts.45.up_proj.weight": "model-00001-of-000001.safetensors",
1040 "model.layers.3.mlp.experts.45.down_proj.weight": "model-00001-of-000001.safetensors",
1041 "model.layers.3.mlp.experts.46.gate_proj.weight": "model-00001-of-000001.safetensors",
1042 "model.layers.3.mlp.experts.46.up_proj.weight": "model-00001-of-000001.safetensors",
1043 "model.layers.3.mlp.experts.46.down_proj.weight": "model-00001-of-000001.safetensors",
1044 "model.layers.3.mlp.experts.47.gate_proj.weight": "model-00001-of-000001.safetensors",
1045 "model.layers.3.mlp.experts.47.up_proj.weight": "model-00001-of-000001.safetensors",
1046 "model.layers.3.mlp.experts.47.down_proj.weight": "model-00001-of-000001.safetensors",
1047 "model.layers.3.mlp.experts.48.gate_proj.weight": "model-00001-of-000001.safetensors",
1048 "model.layers.3.mlp.experts.48.up_proj.weight": "model-00001-of-000001.safetensors",
1049 "model.layers.3.mlp.experts.48.down_proj.weight": "model-00001-of-000001.safetensors",
1050 "model.layers.3.mlp.experts.49.gate_proj.weight": "model-00001-of-000001.safetensors",
1051 "model.layers.3.mlp.experts.49.up_proj.weight": "model-00001-of-000001.safetensors",
1052 "model.layers.3.mlp.experts.49.down_proj.weight": "model-00001-of-000001.safetensors",
1053 "model.layers.3.mlp.experts.50.gate_proj.weight": "model-00001-of-000001.safetensors",
1054 "model.layers.3.mlp.experts.50.up_proj.weight": "model-00001-of-000001.safetensors",
1055 "model.layers.3.mlp.experts.50.down_proj.weight": "model-00001-of-000001.safetensors",
1056 "model.layers.3.mlp.experts.51.gate_proj.weight": "model-00001-of-000001.safetensors",
1057 "model.layers.3.mlp.experts.51.up_proj.weight": "model-00001-of-000001.safetensors",
1058 "model.layers.3.mlp.experts.51.down_proj.weight": "model-00001-of-000001.safetensors",
1059 "model.layers.3.mlp.experts.52.gate_proj.weight": "model-00001-of-000001.safetensors",
1060 "model.layers.3.mlp.experts.52.up_proj.weight": "model-00001-of-000001.safetensors",
1061 "model.layers.3.mlp.experts.52.down_proj.weight": "model-00001-of-000001.safetensors",
1062 "model.layers.3.mlp.experts.53.gate_proj.weight": "model-00001-of-000001.safetensors",
1063 "model.layers.3.mlp.experts.53.up_proj.weight": "model-00001-of-000001.safetensors",
1064 "model.layers.3.mlp.experts.53.down_proj.weight": "model-00001-of-000001.safetensors",
1065 "model.layers.3.mlp.experts.54.gate_proj.weight": "model-00001-of-000001.safetensors",
1066 "model.layers.3.mlp.experts.54.up_proj.weight": "model-00001-of-000001.safetensors",
1067 "model.layers.3.mlp.experts.54.down_proj.weight": "model-00001-of-000001.safetensors",
1068 "model.layers.3.mlp.experts.55.gate_proj.weight": "model-00001-of-000001.safetensors",
1069 "model.layers.3.mlp.experts.55.up_proj.weight": "model-00001-of-000001.safetensors",
1070 "model.layers.3.mlp.experts.55.down_proj.weight": "model-00001-of-000001.safetensors",
1071 "model.layers.3.mlp.experts.56.gate_proj.weight": "model-00001-of-000001.safetensors",
1072 "model.layers.3.mlp.experts.56.up_proj.weight": "model-00001-of-000001.safetensors",
1073 "model.layers.3.mlp.experts.56.down_proj.weight": "model-00001-of-000001.safetensors",
1074 "model.layers.3.mlp.experts.57.gate_proj.weight": "model-00001-of-000001.safetensors",
1075 "model.layers.3.mlp.experts.57.up_proj.weight": "model-00001-of-000001.safetensors",
1076 "model.layers.3.mlp.experts.57.down_proj.weight": "model-00001-of-000001.safetensors",
1077 "model.layers.3.mlp.experts.58.gate_proj.weight": "model-00001-of-000001.safetensors",
1078 "model.layers.3.mlp.experts.58.up_proj.weight": "model-00001-of-000001.safetensors",
1079 "model.layers.3.mlp.experts.58.down_proj.weight": "model-00001-of-000001.safetensors",
1080 "model.layers.3.mlp.experts.59.gate_proj.weight": "model-00001-of-000001.safetensors",
1081 "model.layers.3.mlp.experts.59.up_proj.weight": "model-00001-of-000001.safetensors",
1082 "model.layers.3.mlp.experts.59.down_proj.weight": "model-00001-of-000001.safetensors",
1083 "model.layers.3.mlp.experts.60.gate_proj.weight": "model-00001-of-000001.safetensors",
1084 "model.layers.3.mlp.experts.60.up_proj.weight": "model-00001-of-000001.safetensors",
1085 "model.layers.3.mlp.experts.60.down_proj.weight": "model-00001-of-000001.safetensors",
1086 "model.layers.3.mlp.experts.61.gate_proj.weight": "model-00001-of-000001.safetensors",
1087 "model.layers.3.mlp.experts.61.up_proj.weight": "model-00001-of-000001.safetensors",
1088 "model.layers.3.mlp.experts.61.down_proj.weight": "model-00001-of-000001.safetensors",
1089 "model.layers.3.mlp.experts.62.gate_proj.weight": "model-00001-of-000001.safetensors",
1090 "model.layers.3.mlp.experts.62.up_proj.weight": "model-00001-of-000001.safetensors",
1091 "model.layers.3.mlp.experts.62.down_proj.weight": "model-00001-of-000001.safetensors",
1092 "model.layers.3.mlp.experts.63.gate_proj.weight": "model-00001-of-000001.safetensors",
1093 "model.layers.3.mlp.experts.63.up_proj.weight": "model-00001-of-000001.safetensors",
1094 "model.layers.3.mlp.experts.63.down_proj.weight": "model-00001-of-000001.safetensors",
1095 "model.layers.3.input_layernorm.weight": "model-00001-of-000001.safetensors",
1096 "model.layers.3.post_attention_layernorm.weight": "model-00001-of-000001.safetensors",
1097 "model.layers.4.self_attn.q_proj.weight": "model-00001-of-000001.safetensors",
1098 "model.layers.4.self_attn.k_proj.weight": "model-00001-of-000001.safetensors",
1099 "model.layers.4.self_attn.v_proj.weight": "model-00001-of-000001.safetensors",
1100 "model.layers.4.self_attn.o_proj.weight": "model-00001-of-000001.safetensors",
1101 "model.layers.4.mlp.gate.weight": "model-00001-of-000001.safetensors",
1102 "model.layers.4.mlp.shared_experts.gate_proj.weight": "model-00001-of-000001.safetensors",
1103 "model.layers.4.mlp.shared_experts.up_proj.weight": "model-00001-of-000001.safetensors",
1104 "model.layers.4.mlp.shared_experts.down_proj.weight": "model-00001-of-000001.safetensors",
1105 "model.layers.4.mlp.experts.0.gate_proj.weight": "model-00001-of-000001.safetensors",
1106 "model.layers.4.mlp.experts.0.up_proj.weight": "model-00001-of-000001.safetensors",
1107 "model.layers.4.mlp.experts.0.down_proj.weight": "model-00001-of-000001.safetensors",
1108 "model.layers.4.mlp.experts.1.gate_proj.weight": "model-00001-of-000001.safetensors",
1109 "model.layers.4.mlp.experts.1.up_proj.weight": "model-00001-of-000001.safetensors",
1110 "model.layers.4.mlp.experts.1.down_proj.weight": "model-00001-of-000001.safetensors",
1111 "model.layers.4.mlp.experts.2.gate_proj.weight": "model-00001-of-000001.safetensors",
1112 "model.layers.4.mlp.experts.2.up_proj.weight": "model-00001-of-000001.safetensors",
1113 "model.layers.4.mlp.experts.2.down_proj.weight": "model-00001-of-000001.safetensors",
1114 "model.layers.4.mlp.experts.3.gate_proj.weight": "model-00001-of-000001.safetensors",
1115 "model.layers.4.mlp.experts.3.up_proj.weight": "model-00001-of-000001.safetensors",
1116 "model.layers.4.mlp.experts.3.down_proj.weight": "model-00001-of-000001.safetensors",
1117 "model.layers.4.mlp.experts.4.gate_proj.weight": "model-00001-of-000001.safetensors",
1118 "model.layers.4.mlp.experts.4.up_proj.weight": "model-00001-of-000001.safetensors",
1119 "model.layers.4.mlp.experts.4.down_proj.weight": "model-00001-of-000001.safetensors",
1120 "model.layers.4.mlp.experts.5.gate_proj.weight": "model-00001-of-000001.safetensors",
1121 "model.layers.4.mlp.experts.5.up_proj.weight": "model-00001-of-000001.safetensors",
1122 "model.layers.4.mlp.experts.5.down_proj.weight": "model-00001-of-000001.safetensors",
1123 "model.layers.4.mlp.experts.6.gate_proj.weight": "model-00001-of-000001.safetensors",
1124 "model.layers.4.mlp.experts.6.up_proj.weight": "model-00001-of-000001.safetensors",
1125 "model.layers.4.mlp.experts.6.down_proj.weight": "model-00001-of-000001.safetensors",
1126 "model.layers.4.mlp.experts.7.gate_proj.weight": "model-00001-of-000001.safetensors",
1127 "model.layers.4.mlp.experts.7.up_proj.weight": "model-00001-of-000001.safetensors",
1128 "model.layers.4.mlp.experts.7.down_proj.weight": "model-00001-of-000001.safetensors",
1129 "model.layers.4.mlp.experts.8.gate_proj.weight": "model-00001-of-000001.safetensors",
1130 "model.layers.4.mlp.experts.8.up_proj.weight": "model-00001-of-000001.safetensors",
1131 "model.layers.4.mlp.experts.8.down_proj.weight": "model-00001-of-000001.safetensors",
1132 "model.layers.4.mlp.experts.9.gate_proj.weight": "model-00001-of-000001.safetensors",
1133 "model.layers.4.mlp.experts.9.up_proj.weight": "model-00001-of-000001.safetensors",
1134 "model.layers.4.mlp.experts.9.down_proj.weight": "model-00001-of-000001.safetensors",
1135 "model.layers.4.mlp.experts.10.gate_proj.weight": "model-00001-of-000001.safetensors",
1136 "model.layers.4.mlp.experts.10.up_proj.weight": "model-00001-of-000001.safetensors",
1137 "model.layers.4.mlp.experts.10.down_proj.weight": "model-00001-of-000001.safetensors",
1138 "model.layers.4.mlp.experts.11.gate_proj.weight": "model-00001-of-000001.safetensors",
1139 "model.layers.4.mlp.experts.11.up_proj.weight": "model-00001-of-000001.safetensors",
1140 "model.layers.4.mlp.experts.11.down_proj.weight": "model-00001-of-000001.safetensors",
1141 "model.layers.4.mlp.experts.12.gate_proj.weight": "model-00001-of-000001.safetensors",
1142 "model.layers.4.mlp.experts.12.up_proj.weight": "model-00001-of-000001.safetensors",
1143 "model.layers.4.mlp.experts.12.down_proj.weight": "model-00001-of-000001.safetensors",
1144 "model.layers.4.mlp.experts.13.gate_proj.weight": "model-00001-of-000001.safetensors",
1145 "model.layers.4.mlp.experts.13.up_proj.weight": "model-00001-of-000001.safetensors",
1146 "model.layers.4.mlp.experts.13.down_proj.weight": "model-00001-of-000001.safetensors",
1147 "model.layers.4.mlp.experts.14.gate_proj.weight": "model-00001-of-000001.safetensors",
1148 "model.layers.4.mlp.experts.14.up_proj.weight": "model-00001-of-000001.safetensors",
1149 "model.layers.4.mlp.experts.14.down_proj.weight": "model-00001-of-000001.safetensors",
1150 "model.layers.4.mlp.experts.15.gate_proj.weight": "model-00001-of-000001.safetensors",
1151 "model.layers.4.mlp.experts.15.up_proj.weight": "model-00001-of-000001.safetensors",
1152 "model.layers.4.mlp.experts.15.down_proj.weight": "model-00001-of-000001.safetensors",
1153 "model.layers.4.mlp.experts.16.gate_proj.weight": "model-00001-of-000001.safetensors",
1154 "model.layers.4.mlp.experts.16.up_proj.weight": "model-00001-of-000001.safetensors",
1155 "model.layers.4.mlp.experts.16.down_proj.weight": "model-00001-of-000001.safetensors",
1156 "model.layers.4.mlp.experts.17.gate_proj.weight": "model-00001-of-000001.safetensors",
1157 "model.layers.4.mlp.experts.17.up_proj.weight": "model-00001-of-000001.safetensors",
1158 "model.layers.4.mlp.experts.17.down_proj.weight": "model-00001-of-000001.safetensors",
1159 "model.layers.4.mlp.experts.18.gate_proj.weight": "model-00001-of-000001.safetensors",
1160 "model.layers.4.mlp.experts.18.up_proj.weight": "model-00001-of-000001.safetensors",
1161 "model.layers.4.mlp.experts.18.down_proj.weight": "model-00001-of-000001.safetensors",
1162 "model.layers.4.mlp.experts.19.gate_proj.weight": "model-00001-of-000001.safetensors",
1163 "model.layers.4.mlp.experts.19.up_proj.weight": "model-00001-of-000001.safetensors",
1164 "model.layers.4.mlp.experts.19.down_proj.weight": "model-00001-of-000001.safetensors",
1165 "model.layers.4.mlp.experts.20.gate_proj.weight": "model-00001-of-000001.safetensors",
1166 "model.layers.4.mlp.experts.20.up_proj.weight": "model-00001-of-000001.safetensors",
1167 "model.layers.4.mlp.experts.20.down_proj.weight": "model-00001-of-000001.safetensors",
1168 "model.layers.4.mlp.experts.21.gate_proj.weight": "model-00001-of-000001.safetensors",
1169 "model.layers.4.mlp.experts.21.up_proj.weight": "model-00001-of-000001.safetensors",
1170 "model.layers.4.mlp.experts.21.down_proj.weight": "model-00001-of-000001.safetensors",
1171 "model.layers.4.mlp.experts.22.gate_proj.weight": "model-00001-of-000001.safetensors",
1172 "model.layers.4.mlp.experts.22.up_proj.weight": "model-00001-of-000001.safetensors",
1173 "model.layers.4.mlp.experts.22.down_proj.weight": "model-00001-of-000001.safetensors",
1174 "model.layers.4.mlp.experts.23.gate_proj.weight": "model-00001-of-000001.safetensors",
1175 "model.layers.4.mlp.experts.23.up_proj.weight": "model-00001-of-000001.safetensors",
1176 "model.layers.4.mlp.experts.23.down_proj.weight": "model-00001-of-000001.safetensors",
1177 "model.layers.4.mlp.experts.24.gate_proj.weight": "model-00001-of-000001.safetensors",
1178 "model.layers.4.mlp.experts.24.up_proj.weight": "model-00001-of-000001.safetensors",
1179 "model.layers.4.mlp.experts.24.down_proj.weight": "model-00001-of-000001.safetensors",
1180 "model.layers.4.mlp.experts.25.gate_proj.weight": "model-00001-of-000001.safetensors",
1181 "model.layers.4.mlp.experts.25.up_proj.weight": "model-00001-of-000001.safetensors",
1182 "model.layers.4.mlp.experts.25.down_proj.weight": "model-00001-of-000001.safetensors",
1183 "model.layers.4.mlp.experts.26.gate_proj.weight": "model-00001-of-000001.safetensors",
1184 "model.layers.4.mlp.experts.26.up_proj.weight": "model-00001-of-000001.safetensors",
1185 "model.layers.4.mlp.experts.26.down_proj.weight": "model-00001-of-000001.safetensors",
1186 "model.layers.4.mlp.experts.27.gate_proj.weight": "model-00001-of-000001.safetensors",
1187 "model.layers.4.mlp.experts.27.up_proj.weight": "model-00001-of-000001.safetensors",
1188 "model.layers.4.mlp.experts.27.down_proj.weight": "model-00001-of-000001.safetensors",
1189 "model.layers.4.mlp.experts.28.gate_proj.weight": "model-00001-of-000001.safetensors",
1190 "model.layers.4.mlp.experts.28.up_proj.weight": "model-00001-of-000001.safetensors",
1191 "model.layers.4.mlp.experts.28.down_proj.weight": "model-00001-of-000001.safetensors",
1192 "model.layers.4.mlp.experts.29.gate_proj.weight": "model-00001-of-000001.safetensors",
1193 "model.layers.4.mlp.experts.29.up_proj.weight": "model-00001-of-000001.safetensors",
1194 "model.layers.4.mlp.experts.29.down_proj.weight": "model-00001-of-000001.safetensors",
1195 "model.layers.4.mlp.experts.30.gate_proj.weight": "model-00001-of-000001.safetensors",
1196 "model.layers.4.mlp.experts.30.up_proj.weight": "model-00001-of-000001.safetensors",
1197 "model.layers.4.mlp.experts.30.down_proj.weight": "model-00001-of-000001.safetensors",
1198 "model.layers.4.mlp.experts.31.gate_proj.weight": "model-00001-of-000001.safetensors",
1199 "model.layers.4.mlp.experts.31.up_proj.weight": "model-00001-of-000001.safetensors",
1200 "model.layers.4.mlp.experts.31.down_proj.weight": "model-00001-of-000001.safetensors",
1201 "model.layers.4.mlp.experts.32.gate_proj.weight": "model-00001-of-000001.safetensors",
1202 "model.layers.4.mlp.experts.32.up_proj.weight": "model-00001-of-000001.safetensors",
1203 "model.layers.4.mlp.experts.32.down_proj.weight": "model-00001-of-000001.safetensors",
1204 "model.layers.4.mlp.experts.33.gate_proj.weight": "model-00001-of-000001.safetensors",
1205 "model.layers.4.mlp.experts.33.up_proj.weight": "model-00001-of-000001.safetensors",
1206 "model.layers.4.mlp.experts.33.down_proj.weight": "model-00001-of-000001.safetensors",
1207 "model.layers.4.mlp.experts.34.gate_proj.weight": "model-00001-of-000001.safetensors",
1208 "model.layers.4.mlp.experts.34.up_proj.weight": "model-00001-of-000001.safetensors",
1209 "model.layers.4.mlp.experts.34.down_proj.weight": "model-00001-of-000001.safetensors",
1210 "model.layers.4.mlp.experts.35.gate_proj.weight": "model-00001-of-000001.safetensors",
1211 "model.layers.4.mlp.experts.35.up_proj.weight": "model-00001-of-000001.safetensors",
1212 "model.layers.4.mlp.experts.35.down_proj.weight": "model-00001-of-000001.safetensors",
1213 "model.layers.4.mlp.experts.36.gate_proj.weight": "model-00001-of-000001.safetensors",
1214 "model.layers.4.mlp.experts.36.up_proj.weight": "model-00001-of-000001.safetensors",
1215 "model.layers.4.mlp.experts.36.down_proj.weight": "model-00001-of-000001.safetensors",
1216 "model.layers.4.mlp.experts.37.gate_proj.weight": "model-00001-of-000001.safetensors",
1217 "model.layers.4.mlp.experts.37.up_proj.weight": "model-00001-of-000001.safetensors",
1218 "model.layers.4.mlp.experts.37.down_proj.weight": "model-00001-of-000001.safetensors",
1219 "model.layers.4.mlp.experts.38.gate_proj.weight": "model-00001-of-000001.safetensors",
1220 "model.layers.4.mlp.experts.38.up_proj.weight": "model-00001-of-000001.safetensors",
1221 "model.layers.4.mlp.experts.38.down_proj.weight": "model-00001-of-000001.safetensors",
1222 "model.layers.4.mlp.experts.39.gate_proj.weight": "model-00001-of-000001.safetensors",
1223 "model.layers.4.mlp.experts.39.up_proj.weight": "model-00001-of-000001.safetensors",
1224 "model.layers.4.mlp.experts.39.down_proj.weight": "model-00001-of-000001.safetensors",
1225 "model.layers.4.mlp.experts.40.gate_proj.weight": "model-00001-of-000001.safetensors",
1226 "model.layers.4.mlp.experts.40.up_proj.weight": "model-00001-of-000001.safetensors",
1227 "model.layers.4.mlp.experts.40.down_proj.weight": "model-00001-of-000001.safetensors",
1228 "model.layers.4.mlp.experts.41.gate_proj.weight": "model-00001-of-000001.safetensors",
1229 "model.layers.4.mlp.experts.41.up_proj.weight": "model-00001-of-000001.safetensors",
1230 "model.layers.4.mlp.experts.41.down_proj.weight": "model-00001-of-000001.safetensors",
1231 "model.layers.4.mlp.experts.42.gate_proj.weight": "model-00001-of-000001.safetensors",
1232 "model.layers.4.mlp.experts.42.up_proj.weight": "model-00001-of-000001.safetensors",
1233 "model.layers.4.mlp.experts.42.down_proj.weight": "model-00001-of-000001.safetensors",
1234 "model.layers.4.mlp.experts.43.gate_proj.weight": "model-00001-of-000001.safetensors",
1235 "model.layers.4.mlp.experts.43.up_proj.weight": "model-00001-of-000001.safetensors",
1236 "model.layers.4.mlp.experts.43.down_proj.weight": "model-00001-of-000001.safetensors",
1237 "model.layers.4.mlp.experts.44.gate_proj.weight": "model-00001-of-000001.safetensors",
1238 "model.layers.4.mlp.experts.44.up_proj.weight": "model-00001-of-000001.safetensors",
1239 "model.layers.4.mlp.experts.44.down_proj.weight": "model-00001-of-000001.safetensors",
1240 "model.layers.4.mlp.experts.45.gate_proj.weight": "model-00001-of-000001.safetensors",
1241 "model.layers.4.mlp.experts.45.up_proj.weight": "model-00001-of-000001.safetensors",
1242 "model.layers.4.mlp.experts.45.down_proj.weight": "model-00001-of-000001.safetensors",
1243 "model.layers.4.mlp.experts.46.gate_proj.weight": "model-00001-of-000001.safetensors",
1244 "model.layers.4.mlp.experts.46.up_proj.weight": "model-00001-of-000001.safetensors",
1245 "model.layers.4.mlp.experts.46.down_proj.weight": "model-00001-of-000001.safetensors",
1246 "model.layers.4.mlp.experts.47.gate_proj.weight": "model-00001-of-000001.safetensors",
1247 "model.layers.4.mlp.experts.47.up_proj.weight": "model-00001-of-000001.safetensors",
1248 "model.layers.4.mlp.experts.47.down_proj.weight": "model-00001-of-000001.safetensors",
1249 "model.layers.4.mlp.experts.48.gate_proj.weight": "model-00001-of-000001.safetensors",
1250 "model.layers.4.mlp.experts.48.up_proj.weight": "model-00001-of-000001.safetensors",
1251 "model.layers.4.mlp.experts.48.down_proj.weight": "model-00001-of-000001.safetensors",
1252 "model.layers.4.mlp.experts.49.gate_proj.weight": "model-00001-of-000001.safetensors",
1253 "model.layers.4.mlp.experts.49.up_proj.weight": "model-00001-of-000001.safetensors",
1254 "model.layers.4.mlp.experts.49.down_proj.weight": "model-00001-of-000001.safetensors",
1255 "model.layers.4.mlp.experts.50.gate_proj.weight": "model-00001-of-000001.safetensors",
1256 "model.layers.4.mlp.experts.50.up_proj.weight": "model-00001-of-000001.safetensors",
1257 "model.layers.4.mlp.experts.50.down_proj.weight": "model-00001-of-000001.safetensors",
1258 "model.layers.4.mlp.experts.51.gate_proj.weight": "model-00001-of-000001.safetensors",
1259 "model.layers.4.mlp.experts.51.up_proj.weight": "model-00001-of-000001.safetensors",
1260 "model.layers.4.mlp.experts.51.down_proj.weight": "model-00001-of-000001.safetensors",
1261 "model.layers.4.mlp.experts.52.gate_proj.weight": "model-00001-of-000001.safetensors",
1262 "model.layers.4.mlp.experts.52.up_proj.weight": "model-00001-of-000001.safetensors",
1263 "model.layers.4.mlp.experts.52.down_proj.weight": "model-00001-of-000001.safetensors",
1264 "model.layers.4.mlp.experts.53.gate_proj.weight": "model-00001-of-000001.safetensors",
1265 "model.layers.4.mlp.experts.53.up_proj.weight": "model-00001-of-000001.safetensors",
1266 "model.layers.4.mlp.experts.53.down_proj.weight": "model-00001-of-000001.safetensors",
1267 "model.layers.4.mlp.experts.54.gate_proj.weight": "model-00001-of-000001.safetensors",
1268 "model.layers.4.mlp.experts.54.up_proj.weight": "model-00001-of-000001.safetensors",
1269 "model.layers.4.mlp.experts.54.down_proj.weight": "model-00001-of-000001.safetensors",
1270 "model.layers.4.mlp.experts.55.gate_proj.weight": "model-00001-of-000001.safetensors",
1271 "model.layers.4.mlp.experts.55.up_proj.weight": "model-00001-of-000001.safetensors",
1272 "model.layers.4.mlp.experts.55.down_proj.weight": "model-00001-of-000001.safetensors",
1273 "model.layers.4.mlp.experts.56.gate_proj.weight": "model-00001-of-000001.safetensors",
1274 "model.layers.4.mlp.experts.56.up_proj.weight": "model-00001-of-000001.safetensors",
1275 "model.layers.4.mlp.experts.56.down_proj.weight": "model-00001-of-000001.safetensors",
1276 "model.layers.4.mlp.experts.57.gate_proj.weight": "model-00001-of-000001.safetensors",
1277 "model.layers.4.mlp.experts.57.up_proj.weight": "model-00001-of-000001.safetensors",
1278 "model.layers.4.mlp.experts.57.down_proj.weight": "model-00001-of-000001.safetensors",
1279 "model.layers.4.mlp.experts.58.gate_proj.weight": "model-00001-of-000001.safetensors",
1280 "model.layers.4.mlp.experts.58.up_proj.weight": "model-00001-of-000001.safetensors",
1281 "model.layers.4.mlp.experts.58.down_proj.weight": "model-00001-of-000001.safetensors",
1282 "model.layers.4.mlp.experts.59.gate_proj.weight": "model-00001-of-000001.safetensors",
1283 "model.layers.4.mlp.experts.59.up_proj.weight": "model-00001-of-000001.safetensors",
1284 "model.layers.4.mlp.experts.59.down_proj.weight": "model-00001-of-000001.safetensors",
1285 "model.layers.4.mlp.experts.60.gate_proj.weight": "model-00001-of-000001.safetensors",
1286 "model.layers.4.mlp.experts.60.up_proj.weight": "model-00001-of-000001.safetensors",
1287 "model.layers.4.mlp.experts.60.down_proj.weight": "model-00001-of-000001.safetensors",
1288 "model.layers.4.mlp.experts.61.gate_proj.weight": "model-00001-of-000001.safetensors",
1289 "model.layers.4.mlp.experts.61.up_proj.weight": "model-00001-of-000001.safetensors",
1290 "model.layers.4.mlp.experts.61.down_proj.weight": "model-00001-of-000001.safetensors",
1291 "model.layers.4.mlp.experts.62.gate_proj.weight": "model-00001-of-000001.safetensors",
1292 "model.layers.4.mlp.experts.62.up_proj.weight": "model-00001-of-000001.safetensors",
1293 "model.layers.4.mlp.experts.62.down_proj.weight": "model-00001-of-000001.safetensors",
1294 "model.layers.4.mlp.experts.63.gate_proj.weight": "model-00001-of-000001.safetensors",
1295 "model.layers.4.mlp.experts.63.up_proj.weight": "model-00001-of-000001.safetensors",
1296 "model.layers.4.mlp.experts.63.down_proj.weight": "model-00001-of-000001.safetensors",
1297 "model.layers.4.input_layernorm.weight": "model-00001-of-000001.safetensors",
1298 "model.layers.4.post_attention_layernorm.weight": "model-00001-of-000001.safetensors",
1299 "model.layers.5.self_attn.q_proj.weight": "model-00001-of-000001.safetensors",
1300 "model.layers.5.self_attn.k_proj.weight": "model-00001-of-000001.safetensors",
1301 "model.layers.5.self_attn.v_proj.weight": "model-00001-of-000001.safetensors",
1302 "model.layers.5.self_attn.o_proj.weight": "model-00001-of-000001.safetensors",
1303 "model.layers.5.mlp.gate.weight": "model-00001-of-000001.safetensors",
1304 "model.layers.5.mlp.shared_experts.gate_proj.weight": "model-00001-of-000001.safetensors",
1305 "model.layers.5.mlp.shared_experts.up_proj.weight": "model-00001-of-000001.safetensors",
1306 "model.layers.5.mlp.shared_experts.down_proj.weight": "model-00001-of-000001.safetensors",
1307 "model.layers.5.mlp.experts.0.gate_proj.weight": "model-00001-of-000001.safetensors",
1308 "model.layers.5.mlp.experts.0.up_proj.weight": "model-00001-of-000001.safetensors",
1309 "model.layers.5.mlp.experts.0.down_proj.weight": "model-00001-of-000001.safetensors",
1310 "model.layers.5.mlp.experts.1.gate_proj.weight": "model-00001-of-000001.safetensors",
1311 "model.layers.5.mlp.experts.1.up_proj.weight": "model-00001-of-000001.safetensors",
1312 "model.layers.5.mlp.experts.1.down_proj.weight": "model-00001-of-000001.safetensors",
1313 "model.layers.5.mlp.experts.2.gate_proj.weight": "model-00001-of-000001.safetensors",
1314 "model.layers.5.mlp.experts.2.up_proj.weight": "model-00001-of-000001.safetensors",
1315 "model.layers.5.mlp.experts.2.down_proj.weight": "model-00001-of-000001.safetensors",
1316 "model.layers.5.mlp.experts.3.gate_proj.weight": "model-00001-of-000001.safetensors",
1317 "model.layers.5.mlp.experts.3.up_proj.weight": "model-00001-of-000001.safetensors",
1318 "model.layers.5.mlp.experts.3.down_proj.weight": "model-00001-of-000001.safetensors",
1319 "model.layers.5.mlp.experts.4.gate_proj.weight": "model-00001-of-000001.safetensors",
1320 "model.layers.5.mlp.experts.4.up_proj.weight": "model-00001-of-000001.safetensors",
1321 "model.layers.5.mlp.experts.4.down_proj.weight": "model-00001-of-000001.safetensors",
1322 "model.layers.5.mlp.experts.5.gate_proj.weight": "model-00001-of-000001.safetensors",
1323 "model.layers.5.mlp.experts.5.up_proj.weight": "model-00001-of-000001.safetensors",
1324 "model.layers.5.mlp.experts.5.down_proj.weight": "model-00001-of-000001.safetensors",
1325 "model.layers.5.mlp.experts.6.gate_proj.weight": "model-00001-of-000001.safetensors",
1326 "model.layers.5.mlp.experts.6.up_proj.weight": "model-00001-of-000001.safetensors",
1327 "model.layers.5.mlp.experts.6.down_proj.weight": "model-00001-of-000001.safetensors",
1328 "model.layers.5.mlp.experts.7.gate_proj.weight": "model-00001-of-000001.safetensors",
1329 "model.layers.5.mlp.experts.7.up_proj.weight": "model-00001-of-000001.safetensors",
1330 "model.layers.5.mlp.experts.7.down_proj.weight": "model-00001-of-000001.safetensors",
1331 "model.layers.5.mlp.experts.8.gate_proj.weight": "model-00001-of-000001.safetensors",
1332 "model.layers.5.mlp.experts.8.up_proj.weight": "model-00001-of-000001.safetensors",
1333 "model.layers.5.mlp.experts.8.down_proj.weight": "model-00001-of-000001.safetensors",
1334 "model.layers.5.mlp.experts.9.gate_proj.weight": "model-00001-of-000001.safetensors",
1335 "model.layers.5.mlp.experts.9.up_proj.weight": "model-00001-of-000001.safetensors",
1336 "model.layers.5.mlp.experts.9.down_proj.weight": "model-00001-of-000001.safetensors",
1337 "model.layers.5.mlp.experts.10.gate_proj.weight": "model-00001-of-000001.safetensors",
1338 "model.layers.5.mlp.experts.10.up_proj.weight": "model-00001-of-000001.safetensors",
1339 "model.layers.5.mlp.experts.10.down_proj.weight": "model-00001-of-000001.safetensors",
1340 "model.layers.5.mlp.experts.11.gate_proj.weight": "model-00001-of-000001.safetensors",
1341 "model.layers.5.mlp.experts.11.up_proj.weight": "model-00001-of-000001.safetensors",
1342 "model.layers.5.mlp.experts.11.down_proj.weight": "model-00001-of-000001.safetensors",
1343 "model.layers.5.mlp.experts.12.gate_proj.weight": "model-00001-of-000001.safetensors",
1344 "model.layers.5.mlp.experts.12.up_proj.weight": "model-00001-of-000001.safetensors",
1345 "model.layers.5.mlp.experts.12.down_proj.weight": "model-00001-of-000001.safetensors",
1346 "model.layers.5.mlp.experts.13.gate_proj.weight": "model-00001-of-000001.safetensors",
1347 "model.layers.5.mlp.experts.13.up_proj.weight": "model-00001-of-000001.safetensors",
1348 "model.layers.5.mlp.experts.13.down_proj.weight": "model-00001-of-000001.safetensors",
1349 "model.layers.5.mlp.experts.14.gate_proj.weight": "model-00001-of-000001.safetensors",
1350 "model.layers.5.mlp.experts.14.up_proj.weight": "model-00001-of-000001.safetensors",
1351 "model.layers.5.mlp.experts.14.down_proj.weight": "model-00001-of-000001.safetensors",
1352 "model.layers.5.mlp.experts.15.gate_proj.weight": "model-00001-of-000001.safetensors",
1353 "model.layers.5.mlp.experts.15.up_proj.weight": "model-00001-of-000001.safetensors",
1354 "model.layers.5.mlp.experts.15.down_proj.weight": "model-00001-of-000001.safetensors",
1355 "model.layers.5.mlp.experts.16.gate_proj.weight": "model-00001-of-000001.safetensors",
1356 "model.layers.5.mlp.experts.16.up_proj.weight": "model-00001-of-000001.safetensors",
1357 "model.layers.5.mlp.experts.16.down_proj.weight": "model-00001-of-000001.safetensors",
1358 "model.layers.5.mlp.experts.17.gate_proj.weight": "model-00001-of-000001.safetensors",
1359 "model.layers.5.mlp.experts.17.up_proj.weight": "model-00001-of-000001.safetensors",
1360 "model.layers.5.mlp.experts.17.down_proj.weight": "model-00001-of-000001.safetensors",
1361 "model.layers.5.mlp.experts.18.gate_proj.weight": "model-00001-of-000001.safetensors",
1362 "model.layers.5.mlp.experts.18.up_proj.weight": "model-00001-of-000001.safetensors",
1363 "model.layers.5.mlp.experts.18.down_proj.weight": "model-00001-of-000001.safetensors",
1364 "model.layers.5.mlp.experts.19.gate_proj.weight": "model-00001-of-000001.safetensors",
1365 "model.layers.5.mlp.experts.19.up_proj.weight": "model-00001-of-000001.safetensors",
1366 "model.layers.5.mlp.experts.19.down_proj.weight": "model-00001-of-000001.safetensors",
1367 "model.layers.5.mlp.experts.20.gate_proj.weight": "model-00001-of-000001.safetensors",
1368 "model.layers.5.mlp.experts.20.up_proj.weight": "model-00001-of-000001.safetensors",
1369 "model.layers.5.mlp.experts.20.down_proj.weight": "model-00001-of-000001.safetensors",
1370 "model.layers.5.mlp.experts.21.gate_proj.weight": "model-00001-of-000001.safetensors",
1371 "model.layers.5.mlp.experts.21.up_proj.weight": "model-00001-of-000001.safetensors",
1372 "model.layers.5.mlp.experts.21.down_proj.weight": "model-00001-of-000001.safetensors",
1373 "model.layers.5.mlp.experts.22.gate_proj.weight": "model-00001-of-000001.safetensors",
1374 "model.layers.5.mlp.experts.22.up_proj.weight": "model-00001-of-000001.safetensors",
1375 "model.layers.5.mlp.experts.22.down_proj.weight": "model-00001-of-000001.safetensors",
1376 "model.layers.5.mlp.experts.23.gate_proj.weight": "model-00001-of-000001.safetensors",
1377 "model.layers.5.mlp.experts.23.up_proj.weight": "model-00001-of-000001.safetensors",
1378 "model.layers.5.mlp.experts.23.down_proj.weight": "model-00001-of-000001.safetensors",
1379 "model.layers.5.mlp.experts.24.gate_proj.weight": "model-00001-of-000001.safetensors",
1380 "model.layers.5.mlp.experts.24.up_proj.weight": "model-00001-of-000001.safetensors",
1381 "model.layers.5.mlp.experts.24.down_proj.weight": "model-00001-of-000001.safetensors",
1382 "model.layers.5.mlp.experts.25.gate_proj.weight": "model-00001-of-000001.safetensors",
1383 "model.layers.5.mlp.experts.25.up_proj.weight": "model-00001-of-000001.safetensors",
1384 "model.layers.5.mlp.experts.25.down_proj.weight": "model-00001-of-000001.safetensors",
1385 "model.layers.5.mlp.experts.26.gate_proj.weight": "model-00001-of-000001.safetensors",
1386 "model.layers.5.mlp.experts.26.up_proj.weight": "model-00001-of-000001.safetensors",
1387 "model.layers.5.mlp.experts.26.down_proj.weight": "model-00001-of-000001.safetensors",
1388 "model.layers.5.mlp.experts.27.gate_proj.weight": "model-00001-of-000001.safetensors",
1389 "model.layers.5.mlp.experts.27.up_proj.weight": "model-00001-of-000001.safetensors",
1390 "model.layers.5.mlp.experts.27.down_proj.weight": "model-00001-of-000001.safetensors",
1391 "model.layers.5.mlp.experts.28.gate_proj.weight": "model-00001-of-000001.safetensors",
1392 "model.layers.5.mlp.experts.28.up_proj.weight": "model-00001-of-000001.safetensors",
1393 "model.layers.5.mlp.experts.28.down_proj.weight": "model-00001-of-000001.safetensors",
1394 "model.layers.5.mlp.experts.29.gate_proj.weight": "model-00001-of-000001.safetensors",
1395 "model.layers.5.mlp.experts.29.up_proj.weight": "model-00001-of-000001.safetensors",
1396 "model.layers.5.mlp.experts.29.down_proj.weight": "model-00001-of-000001.safetensors",
1397 "model.layers.5.mlp.experts.30.gate_proj.weight": "model-00001-of-000001.safetensors",
1398 "model.layers.5.mlp.experts.30.up_proj.weight": "model-00001-of-000001.safetensors",
1399 "model.layers.5.mlp.experts.30.down_proj.weight": "model-00001-of-000001.safetensors",
1400 "model.layers.5.mlp.experts.31.gate_proj.weight": "model-00001-of-000001.safetensors",
1401 "model.layers.5.mlp.experts.31.up_proj.weight": "model-00001-of-000001.safetensors",
1402 "model.layers.5.mlp.experts.31.down_proj.weight": "model-00001-of-000001.safetensors",
1403 "model.layers.5.mlp.experts.32.gate_proj.weight": "model-00001-of-000001.safetensors",
1404 "model.layers.5.mlp.experts.32.up_proj.weight": "model-00001-of-000001.safetensors",
1405 "model.layers.5.mlp.experts.32.down_proj.weight": "model-00001-of-000001.safetensors",
1406 "model.layers.5.mlp.experts.33.gate_proj.weight": "model-00001-of-000001.safetensors",
1407 "model.layers.5.mlp.experts.33.up_proj.weight": "model-00001-of-000001.safetensors",
1408 "model.layers.5.mlp.experts.33.down_proj.weight": "model-00001-of-000001.safetensors",
1409 "model.layers.5.mlp.experts.34.gate_proj.weight": "model-00001-of-000001.safetensors",
1410 "model.layers.5.mlp.experts.34.up_proj.weight": "model-00001-of-000001.safetensors",
1411 "model.layers.5.mlp.experts.34.down_proj.weight": "model-00001-of-000001.safetensors",
1412 "model.layers.5.mlp.experts.35.gate_proj.weight": "model-00001-of-000001.safetensors",
1413 "model.layers.5.mlp.experts.35.up_proj.weight": "model-00001-of-000001.safetensors",
1414 "model.layers.5.mlp.experts.35.down_proj.weight": "model-00001-of-000001.safetensors",
1415 "model.layers.5.mlp.experts.36.gate_proj.weight": "model-00001-of-000001.safetensors",
1416 "model.layers.5.mlp.experts.36.up_proj.weight": "model-00001-of-000001.safetensors",
1417 "model.layers.5.mlp.experts.36.down_proj.weight": "model-00001-of-000001.safetensors",
1418 "model.layers.5.mlp.experts.37.gate_proj.weight": "model-00001-of-000001.safetensors",
1419 "model.layers.5.mlp.experts.37.up_proj.weight": "model-00001-of-000001.safetensors",
1420 "model.layers.5.mlp.experts.37.down_proj.weight": "model-00001-of-000001.safetensors",
1421 "model.layers.5.mlp.experts.38.gate_proj.weight": "model-00001-of-000001.safetensors",
1422 "model.layers.5.mlp.experts.38.up_proj.weight": "model-00001-of-000001.safetensors",
1423 "model.layers.5.mlp.experts.38.down_proj.weight": "model-00001-of-000001.safetensors",
1424 "model.layers.5.mlp.experts.39.gate_proj.weight": "model-00001-of-000001.safetensors",
1425 "model.layers.5.mlp.experts.39.up_proj.weight": "model-00001-of-000001.safetensors",
1426 "model.layers.5.mlp.experts.39.down_proj.weight": "model-00001-of-000001.safetensors",
1427 "model.layers.5.mlp.experts.40.gate_proj.weight": "model-00001-of-000001.safetensors",
1428 "model.layers.5.mlp.experts.40.up_proj.weight": "model-00001-of-000001.safetensors",
1429 "model.layers.5.mlp.experts.40.down_proj.weight": "model-00001-of-000001.safetensors",
1430 "model.layers.5.mlp.experts.41.gate_proj.weight": "model-00001-of-000001.safetensors",
1431 "model.layers.5.mlp.experts.41.up_proj.weight": "model-00001-of-000001.safetensors",
1432 "model.layers.5.mlp.experts.41.down_proj.weight": "model-00001-of-000001.safetensors",
1433 "model.layers.5.mlp.experts.42.gate_proj.weight": "model-00001-of-000001.safetensors",
1434 "model.layers.5.mlp.experts.42.up_proj.weight": "model-00001-of-000001.safetensors",
1435 "model.layers.5.mlp.experts.42.down_proj.weight": "model-00001-of-000001.safetensors",
1436 "model.layers.5.mlp.experts.43.gate_proj.weight": "model-00001-of-000001.safetensors",
1437 "model.layers.5.mlp.experts.43.up_proj.weight": "model-00001-of-000001.safetensors",
1438 "model.layers.5.mlp.experts.43.down_proj.weight": "model-00001-of-000001.safetensors",
1439 "model.layers.5.mlp.experts.44.gate_proj.weight": "model-00001-of-000001.safetensors",
1440 "model.layers.5.mlp.experts.44.up_proj.weight": "model-00001-of-000001.safetensors",
1441 "model.layers.5.mlp.experts.44.down_proj.weight": "model-00001-of-000001.safetensors",
1442 "model.layers.5.mlp.experts.45.gate_proj.weight": "model-00001-of-000001.safetensors",
1443 "model.layers.5.mlp.experts.45.up_proj.weight": "model-00001-of-000001.safetensors",
1444 "model.layers.5.mlp.experts.45.down_proj.weight": "model-00001-of-000001.safetensors",
1445 "model.layers.5.mlp.experts.46.gate_proj.weight": "model-00001-of-000001.safetensors",
1446 "model.layers.5.mlp.experts.46.up_proj.weight": "model-00001-of-000001.safetensors",
1447 "model.layers.5.mlp.experts.46.down_proj.weight": "model-00001-of-000001.safetensors",
1448 "model.layers.5.mlp.experts.47.gate_proj.weight": "model-00001-of-000001.safetensors",
1449 "model.layers.5.mlp.experts.47.up_proj.weight": "model-00001-of-000001.safetensors",
1450 "model.layers.5.mlp.experts.47.down_proj.weight": "model-00001-of-000001.safetensors",
1451 "model.layers.5.mlp.experts.48.gate_proj.weight": "model-00001-of-000001.safetensors",
1452 "model.layers.5.mlp.experts.48.up_proj.weight": "model-00001-of-000001.safetensors",
1453 "model.layers.5.mlp.experts.48.down_proj.weight": "model-00001-of-000001.safetensors",
1454 "model.layers.5.mlp.experts.49.gate_proj.weight": "model-00001-of-000001.safetensors",
1455 "model.layers.5.mlp.experts.49.up_proj.weight": "model-00001-of-000001.safetensors",
1456 "model.layers.5.mlp.experts.49.down_proj.weight": "model-00001-of-000001.safetensors",
1457 "model.layers.5.mlp.experts.50.gate_proj.weight": "model-00001-of-000001.safetensors",
1458 "model.layers.5.mlp.experts.50.up_proj.weight": "model-00001-of-000001.safetensors",
1459 "model.layers.5.mlp.experts.50.down_proj.weight": "model-00001-of-000001.safetensors",
1460 "model.layers.5.mlp.experts.51.gate_proj.weight": "model-00001-of-000001.safetensors",
1461 "model.layers.5.mlp.experts.51.up_proj.weight": "model-00001-of-000001.safetensors",
1462 "model.layers.5.mlp.experts.51.down_proj.weight": "model-00001-of-000001.safetensors",
1463 "model.layers.5.mlp.experts.52.gate_proj.weight": "model-00001-of-000001.safetensors",
1464 "model.layers.5.mlp.experts.52.up_proj.weight": "model-00001-of-000001.safetensors",
1465 "model.layers.5.mlp.experts.52.down_proj.weight": "model-00001-of-000001.safetensors",
1466 "model.layers.5.mlp.experts.53.gate_proj.weight": "model-00001-of-000001.safetensors",
1467 "model.layers.5.mlp.experts.53.up_proj.weight": "model-00001-of-000001.safetensors",
1468 "model.layers.5.mlp.experts.53.down_proj.weight": "model-00001-of-000001.safetensors",
1469 "model.layers.5.mlp.experts.54.gate_proj.weight": "model-00001-of-000001.safetensors",
1470 "model.layers.5.mlp.experts.54.up_proj.weight": "model-00001-of-000001.safetensors",
1471 "model.layers.5.mlp.experts.54.down_proj.weight": "model-00001-of-000001.safetensors",
1472 "model.layers.5.mlp.experts.55.gate_proj.weight": "model-00001-of-000001.safetensors",
1473 "model.layers.5.mlp.experts.55.up_proj.weight": "model-00001-of-000001.safetensors",
1474 "model.layers.5.mlp.experts.55.down_proj.weight": "model-00001-of-000001.safetensors",
1475 "model.layers.5.mlp.experts.56.gate_proj.weight": "model-00001-of-000001.safetensors",
1476 "model.layers.5.mlp.experts.56.up_proj.weight": "model-00001-of-000001.safetensors",
1477 "model.layers.5.mlp.experts.56.down_proj.weight": "model-00001-of-000001.safetensors",
1478 "model.layers.5.mlp.experts.57.gate_proj.weight": "model-00001-of-000001.safetensors",
1479 "model.layers.5.mlp.experts.57.up_proj.weight": "model-00001-of-000001.safetensors",
1480 "model.layers.5.mlp.experts.57.down_proj.weight": "model-00001-of-000001.safetensors",
1481 "model.layers.5.mlp.experts.58.gate_proj.weight": "model-00001-of-000001.safetensors",
1482 "model.layers.5.mlp.experts.58.up_proj.weight": "model-00001-of-000001.safetensors",
1483 "model.layers.5.mlp.experts.58.down_proj.weight": "model-00001-of-000001.safetensors",
1484 "model.layers.5.mlp.experts.59.gate_proj.weight": "model-00001-of-000001.safetensors",
1485 "model.layers.5.mlp.experts.59.up_proj.weight": "model-00001-of-000001.safetensors",
1486 "model.layers.5.mlp.experts.59.down_proj.weight": "model-00001-of-000001.safetensors",
1487 "model.layers.5.mlp.experts.60.gate_proj.weight": "model-00001-of-000001.safetensors",
1488 "model.layers.5.mlp.experts.60.up_proj.weight": "model-00001-of-000001.safetensors",
1489 "model.layers.5.mlp.experts.60.down_proj.weight": "model-00001-of-000001.safetensors",
1490 "model.layers.5.mlp.experts.61.gate_proj.weight": "model-00001-of-000001.safetensors",
1491 "model.layers.5.mlp.experts.61.up_proj.weight": "model-00001-of-000001.safetensors",
1492 "model.layers.5.mlp.experts.61.down_proj.weight": "model-00001-of-000001.safetensors",
1493 "model.layers.5.mlp.experts.62.gate_proj.weight": "model-00001-of-000001.safetensors",
1494 "model.layers.5.mlp.experts.62.up_proj.weight": "model-00001-of-000001.safetensors",
1495 "model.layers.5.mlp.experts.62.down_proj.weight": "model-00001-of-000001.safetensors",
1496 "model.layers.5.mlp.experts.63.gate_proj.weight": "model-00001-of-000001.safetensors",
1497 "model.layers.5.mlp.experts.63.up_proj.weight": "model-00001-of-000001.safetensors",
1498 "model.layers.5.mlp.experts.63.down_proj.weight": "model-00001-of-000001.safetensors",
1499 "model.layers.5.input_layernorm.weight": "model-00001-of-000001.safetensors",
1500 "model.layers.5.post_attention_layernorm.weight": "model-00001-of-000001.safetensors",
1501 "model.layers.6.self_attn.q_proj.weight": "model-00001-of-000001.safetensors",
1502 "model.layers.6.self_attn.k_proj.weight": "model-00001-of-000001.safetensors",
1503 "model.layers.6.self_attn.v_proj.weight": "model-00001-of-000001.safetensors",
1504 "model.layers.6.self_attn.o_proj.weight": "model-00001-of-000001.safetensors",
1505 "model.layers.6.mlp.gate.weight": "model-00001-of-000001.safetensors",
1506 "model.layers.6.mlp.shared_experts.gate_proj.weight": "model-00001-of-000001.safetensors",
1507 "model.layers.6.mlp.shared_experts.up_proj.weight": "model-00001-of-000001.safetensors",
1508 "model.layers.6.mlp.shared_experts.down_proj.weight": "model-00001-of-000001.safetensors",
1509 "model.layers.6.mlp.experts.0.gate_proj.weight": "model-00001-of-000001.safetensors",
1510 "model.layers.6.mlp.experts.0.up_proj.weight": "model-00001-of-000001.safetensors",
1511 "model.layers.6.mlp.experts.0.down_proj.weight": "model-00001-of-000001.safetensors",
1512 "model.layers.6.mlp.experts.1.gate_proj.weight": "model-00001-of-000001.safetensors",
1513 "model.layers.6.mlp.experts.1.up_proj.weight": "model-00001-of-000001.safetensors",
1514 "model.layers.6.mlp.experts.1.down_proj.weight": "model-00001-of-000001.safetensors",
1515 "model.layers.6.mlp.experts.2.gate_proj.weight": "model-00001-of-000001.safetensors",
1516 "model.layers.6.mlp.experts.2.up_proj.weight": "model-00001-of-000001.safetensors",
1517 "model.layers.6.mlp.experts.2.down_proj.weight": "model-00001-of-000001.safetensors",
1518 "model.layers.6.mlp.experts.3.gate_proj.weight": "model-00001-of-000001.safetensors",
1519 "model.layers.6.mlp.experts.3.up_proj.weight": "model-00001-of-000001.safetensors",
1520 "model.layers.6.mlp.experts.3.down_proj.weight": "model-00001-of-000001.safetensors",
1521 "model.layers.6.mlp.experts.4.gate_proj.weight": "model-00001-of-000001.safetensors",
1522 "model.layers.6.mlp.experts.4.up_proj.weight": "model-00001-of-000001.safetensors",
1523 "model.layers.6.mlp.experts.4.down_proj.weight": "model-00001-of-000001.safetensors",
1524 "model.layers.6.mlp.experts.5.gate_proj.weight": "model-00001-of-000001.safetensors",
1525 "model.layers.6.mlp.experts.5.up_proj.weight": "model-00001-of-000001.safetensors",
1526 "model.layers.6.mlp.experts.5.down_proj.weight": "model-00001-of-000001.safetensors",
1527 "model.layers.6.mlp.experts.6.gate_proj.weight": "model-00001-of-000001.safetensors",
1528 "model.layers.6.mlp.experts.6.up_proj.weight": "model-00001-of-000001.safetensors",
1529 "model.layers.6.mlp.experts.6.down_proj.weight": "model-00001-of-000001.safetensors",
1530 "model.layers.6.mlp.experts.7.gate_proj.weight": "model-00001-of-000001.safetensors",
1531 "model.layers.6.mlp.experts.7.up_proj.weight": "model-00001-of-000001.safetensors",
1532 "model.layers.6.mlp.experts.7.down_proj.weight": "model-00001-of-000001.safetensors",
1533 "model.layers.6.mlp.experts.8.gate_proj.weight": "model-00001-of-000001.safetensors",
1534 "model.layers.6.mlp.experts.8.up_proj.weight": "model-00001-of-000001.safetensors",
1535 "model.layers.6.mlp.experts.8.down_proj.weight": "model-00001-of-000001.safetensors",
1536 "model.layers.6.mlp.experts.9.gate_proj.weight": "model-00001-of-000001.safetensors",
1537 "model.layers.6.mlp.experts.9.up_proj.weight": "model-00001-of-000001.safetensors",
1538 "model.layers.6.mlp.experts.9.down_proj.weight": "model-00001-of-000001.safetensors",
1539 "model.layers.6.mlp.experts.10.gate_proj.weight": "model-00001-of-000001.safetensors",
1540 "model.layers.6.mlp.experts.10.up_proj.weight": "model-00001-of-000001.safetensors",
1541 "model.layers.6.mlp.experts.10.down_proj.weight": "model-00001-of-000001.safetensors",
1542 "model.layers.6.mlp.experts.11.gate_proj.weight": "model-00001-of-000001.safetensors",
1543 "model.layers.6.mlp.experts.11.up_proj.weight": "model-00001-of-000001.safetensors",
1544 "model.layers.6.mlp.experts.11.down_proj.weight": "model-00001-of-000001.safetensors",
1545 "model.layers.6.mlp.experts.12.gate_proj.weight": "model-00001-of-000001.safetensors",
1546 "model.layers.6.mlp.experts.12.up_proj.weight": "model-00001-of-000001.safetensors",
1547 "model.layers.6.mlp.experts.12.down_proj.weight": "model-00001-of-000001.safetensors",
1548 "model.layers.6.mlp.experts.13.gate_proj.weight": "model-00001-of-000001.safetensors",
1549 "model.layers.6.mlp.experts.13.up_proj.weight": "model-00001-of-000001.safetensors",
1550 "model.layers.6.mlp.experts.13.down_proj.weight": "model-00001-of-000001.safetensors",
1551 "model.layers.6.mlp.experts.14.gate_proj.weight": "model-00001-of-000001.safetensors",
1552 "model.layers.6.mlp.experts.14.up_proj.weight": "model-00001-of-000001.safetensors",
1553 "model.layers.6.mlp.experts.14.down_proj.weight": "model-00001-of-000001.safetensors",
1554 "model.layers.6.mlp.experts.15.gate_proj.weight": "model-00001-of-000001.safetensors",
1555 "model.layers.6.mlp.experts.15.up_proj.weight": "model-00001-of-000001.safetensors",
1556 "model.layers.6.mlp.experts.15.down_proj.weight": "model-00001-of-000001.safetensors",
1557 "model.layers.6.mlp.experts.16.gate_proj.weight": "model-00001-of-000001.safetensors",
1558 "model.layers.6.mlp.experts.16.up_proj.weight": "model-00001-of-000001.safetensors",
1559 "model.layers.6.mlp.experts.16.down_proj.weight": "model-00001-of-000001.safetensors",
1560 "model.layers.6.mlp.experts.17.gate_proj.weight": "model-00001-of-000001.safetensors",
1561 "model.layers.6.mlp.experts.17.up_proj.weight": "model-00001-of-000001.safetensors",
1562 "model.layers.6.mlp.experts.17.down_proj.weight": "model-00001-of-000001.safetensors",
1563 "model.layers.6.mlp.experts.18.gate_proj.weight": "model-00001-of-000001.safetensors",
1564 "model.layers.6.mlp.experts.18.up_proj.weight": "model-00001-of-000001.safetensors",
1565 "model.layers.6.mlp.experts.18.down_proj.weight": "model-00001-of-000001.safetensors",
1566 "model.layers.6.mlp.experts.19.gate_proj.weight": "model-00001-of-000001.safetensors",
1567 "model.layers.6.mlp.experts.19.up_proj.weight": "model-00001-of-000001.safetensors",
1568 "model.layers.6.mlp.experts.19.down_proj.weight": "model-00001-of-000001.safetensors",
1569 "model.layers.6.mlp.experts.20.gate_proj.weight": "model-00001-of-000001.safetensors",
1570 "model.layers.6.mlp.experts.20.up_proj.weight": "model-00001-of-000001.safetensors",
1571 "model.layers.6.mlp.experts.20.down_proj.weight": "model-00001-of-000001.safetensors",
1572 "model.layers.6.mlp.experts.21.gate_proj.weight": "model-00001-of-000001.safetensors",
1573 "model.layers.6.mlp.experts.21.up_proj.weight": "model-00001-of-000001.safetensors",
1574 "model.layers.6.mlp.experts.21.down_proj.weight": "model-00001-of-000001.safetensors",
1575 "model.layers.6.mlp.experts.22.gate_proj.weight": "model-00001-of-000001.safetensors",
1576 "model.layers.6.mlp.experts.22.up_proj.weight": "model-00001-of-000001.safetensors",
1577 "model.layers.6.mlp.experts.22.down_proj.weight": "model-00001-of-000001.safetensors",
1578 "model.layers.6.mlp.experts.23.gate_proj.weight": "model-00001-of-000001.safetensors",
1579 "model.layers.6.mlp.experts.23.up_proj.weight": "model-00001-of-000001.safetensors",
1580 "model.layers.6.mlp.experts.23.down_proj.weight": "model-00001-of-000001.safetensors",
1581 "model.layers.6.mlp.experts.24.gate_proj.weight": "model-00001-of-000001.safetensors",
1582 "model.layers.6.mlp.experts.24.up_proj.weight": "model-00001-of-000001.safetensors",
1583 "model.layers.6.mlp.experts.24.down_proj.weight": "model-00001-of-000001.safetensors",
1584 "model.layers.6.mlp.experts.25.gate_proj.weight": "model-00001-of-000001.safetensors",
1585 "model.layers.6.mlp.experts.25.up_proj.weight": "model-00001-of-000001.safetensors",
1586 "model.layers.6.mlp.experts.25.down_proj.weight": "model-00001-of-000001.safetensors",
1587 "model.layers.6.mlp.experts.26.gate_proj.weight": "model-00001-of-000001.safetensors",
1588 "model.layers.6.mlp.experts.26.up_proj.weight": "model-00001-of-000001.safetensors",
1589 "model.layers.6.mlp.experts.26.down_proj.weight": "model-00001-of-000001.safetensors",
1590 "model.layers.6.mlp.experts.27.gate_proj.weight": "model-00001-of-000001.safetensors",
1591 "model.layers.6.mlp.experts.27.up_proj.weight": "model-00001-of-000001.safetensors",
1592 "model.layers.6.mlp.experts.27.down_proj.weight": "model-00001-of-000001.safetensors",
1593 "model.layers.6.mlp.experts.28.gate_proj.weight": "model-00001-of-000001.safetensors",
1594 "model.layers.6.mlp.experts.28.up_proj.weight": "model-00001-of-000001.safetensors",
1595 "model.layers.6.mlp.experts.28.down_proj.weight": "model-00001-of-000001.safetensors",
1596 "model.layers.6.mlp.experts.29.gate_proj.weight": "model-00001-of-000001.safetensors",
1597 "model.layers.6.mlp.experts.29.up_proj.weight": "model-00001-of-000001.safetensors",
1598 "model.layers.6.mlp.experts.29.down_proj.weight": "model-00001-of-000001.safetensors",
1599 "model.layers.6.mlp.experts.30.gate_proj.weight": "model-00001-of-000001.safetensors",
1600 "model.layers.6.mlp.experts.30.up_proj.weight": "model-00001-of-000001.safetensors",
1601 "model.layers.6.mlp.experts.30.down_proj.weight": "model-00001-of-000001.safetensors",
1602 "model.layers.6.mlp.experts.31.gate_proj.weight": "model-00001-of-000001.safetensors",
1603 "model.layers.6.mlp.experts.31.up_proj.weight": "model-00001-of-000001.safetensors",
1604 "model.layers.6.mlp.experts.31.down_proj.weight": "model-00001-of-000001.safetensors",
1605 "model.layers.6.mlp.experts.32.gate_proj.weight": "model-00001-of-000001.safetensors",
1606 "model.layers.6.mlp.experts.32.up_proj.weight": "model-00001-of-000001.safetensors",
1607 "model.layers.6.mlp.experts.32.down_proj.weight": "model-00001-of-000001.safetensors",
1608 "model.layers.6.mlp.experts.33.gate_proj.weight": "model-00001-of-000001.safetensors",
1609 "model.layers.6.mlp.experts.33.up_proj.weight": "model-00001-of-000001.safetensors",
1610 "model.layers.6.mlp.experts.33.down_proj.weight": "model-00001-of-000001.safetensors",
1611 "model.layers.6.mlp.experts.34.gate_proj.weight": "model-00001-of-000001.safetensors",
1612 "model.layers.6.mlp.experts.34.up_proj.weight": "model-00001-of-000001.safetensors",
1613 "model.layers.6.mlp.experts.34.down_proj.weight": "model-00001-of-000001.safetensors",
1614 "model.layers.6.mlp.experts.35.gate_proj.weight": "model-00001-of-000001.safetensors",
1615 "model.layers.6.mlp.experts.35.up_proj.weight": "model-00001-of-000001.safetensors",
1616 "model.layers.6.mlp.experts.35.down_proj.weight": "model-00001-of-000001.safetensors",
1617 "model.layers.6.mlp.experts.36.gate_proj.weight": "model-00001-of-000001.safetensors",
1618 "model.layers.6.mlp.experts.36.up_proj.weight": "model-00001-of-000001.safetensors",
1619 "model.layers.6.mlp.experts.36.down_proj.weight": "model-00001-of-000001.safetensors",
1620 "model.layers.6.mlp.experts.37.gate_proj.weight": "model-00001-of-000001.safetensors",
1621 "model.layers.6.mlp.experts.37.up_proj.weight": "model-00001-of-000001.safetensors",
1622 "model.layers.6.mlp.experts.37.down_proj.weight": "model-00001-of-000001.safetensors",
1623 "model.layers.6.mlp.experts.38.gate_proj.weight": "model-00001-of-000001.safetensors",
1624 "model.layers.6.mlp.experts.38.up_proj.weight": "model-00001-of-000001.safetensors",
1625 "model.layers.6.mlp.experts.38.down_proj.weight": "model-00001-of-000001.safetensors",
1626 "model.layers.6.mlp.experts.39.gate_proj.weight": "model-00001-of-000001.safetensors",
1627 "model.layers.6.mlp.experts.39.up_proj.weight": "model-00001-of-000001.safetensors",
1628 "model.layers.6.mlp.experts.39.down_proj.weight": "model-00001-of-000001.safetensors",
1629 "model.layers.6.mlp.experts.40.gate_proj.weight": "model-00001-of-000001.safetensors",
1630 "model.layers.6.mlp.experts.40.up_proj.weight": "model-00001-of-000001.safetensors",
1631 "model.layers.6.mlp.experts.40.down_proj.weight": "model-00001-of-000001.safetensors",
1632 "model.layers.6.mlp.experts.41.gate_proj.weight": "model-00001-of-000001.safetensors",
1633 "model.layers.6.mlp.experts.41.up_proj.weight": "model-00001-of-000001.safetensors",
1634 "model.layers.6.mlp.experts.41.down_proj.weight": "model-00001-of-000001.safetensors",
1635 "model.layers.6.mlp.experts.42.gate_proj.weight": "model-00001-of-000001.safetensors",
1636 "model.layers.6.mlp.experts.42.up_proj.weight": "model-00001-of-000001.safetensors",
1637 "model.layers.6.mlp.experts.42.down_proj.weight": "model-00001-of-000001.safetensors",
1638 "model.layers.6.mlp.experts.43.gate_proj.weight": "model-00001-of-000001.safetensors",
1639 "model.layers.6.mlp.experts.43.up_proj.weight": "model-00001-of-000001.safetensors",
1640 "model.layers.6.mlp.experts.43.down_proj.weight": "model-00001-of-000001.safetensors",
1641 "model.layers.6.mlp.experts.44.gate_proj.weight": "model-00001-of-000001.safetensors",
1642 "model.layers.6.mlp.experts.44.up_proj.weight": "model-00001-of-000001.safetensors",
1643 "model.layers.6.mlp.experts.44.down_proj.weight": "model-00001-of-000001.safetensors",
1644 "model.layers.6.mlp.experts.45.gate_proj.weight": "model-00001-of-000001.safetensors",
1645 "model.layers.6.mlp.experts.45.up_proj.weight": "model-00001-of-000001.safetensors",
1646 "model.layers.6.mlp.experts.45.down_proj.weight": "model-00001-of-000001.safetensors",
1647 "model.layers.6.mlp.experts.46.gate_proj.weight": "model-00001-of-000001.safetensors",
1648 "model.layers.6.mlp.experts.46.up_proj.weight": "model-00001-of-000001.safetensors",
1649 "model.layers.6.mlp.experts.46.down_proj.weight": "model-00001-of-000001.safetensors",
1650 "model.layers.6.mlp.experts.47.gate_proj.weight": "model-00001-of-000001.safetensors",
1651 "model.layers.6.mlp.experts.47.up_proj.weight": "model-00001-of-000001.safetensors",
1652 "model.layers.6.mlp.experts.47.down_proj.weight": "model-00001-of-000001.safetensors",
1653 "model.layers.6.mlp.experts.48.gate_proj.weight": "model-00001-of-000001.safetensors",
1654 "model.layers.6.mlp.experts.48.up_proj.weight": "model-00001-of-000001.safetensors",
1655 "model.layers.6.mlp.experts.48.down_proj.weight": "model-00001-of-000001.safetensors",
1656 "model.layers.6.mlp.experts.49.gate_proj.weight": "model-00001-of-000001.safetensors",
1657 "model.layers.6.mlp.experts.49.up_proj.weight": "model-00001-of-000001.safetensors",
1658 "model.layers.6.mlp.experts.49.down_proj.weight": "model-00001-of-000001.safetensors",
1659 "model.layers.6.mlp.experts.50.gate_proj.weight": "model-00001-of-000001.safetensors",
1660 "model.layers.6.mlp.experts.50.up_proj.weight": "model-00001-of-000001.safetensors",
1661 "model.layers.6.mlp.experts.50.down_proj.weight": "model-00001-of-000001.safetensors",
1662 "model.layers.6.mlp.experts.51.gate_proj.weight": "model-00001-of-000001.safetensors",
1663 "model.layers.6.mlp.experts.51.up_proj.weight": "model-00001-of-000001.safetensors",
1664 "model.layers.6.mlp.experts.51.down_proj.weight": "model-00001-of-000001.safetensors",
1665 "model.layers.6.mlp.experts.52.gate_proj.weight": "model-00001-of-000001.safetensors",
1666 "model.layers.6.mlp.experts.52.up_proj.weight": "model-00001-of-000001.safetensors",
1667 "model.layers.6.mlp.experts.52.down_proj.weight": "model-00001-of-000001.safetensors",
1668 "model.layers.6.mlp.experts.53.gate_proj.weight": "model-00001-of-000001.safetensors",
1669 "model.layers.6.mlp.experts.53.up_proj.weight": "model-00001-of-000001.safetensors",
1670 "model.layers.6.mlp.experts.53.down_proj.weight": "model-00001-of-000001.safetensors",
1671 "model.layers.6.mlp.experts.54.gate_proj.weight": "model-00001-of-000001.safetensors",
1672 "model.layers.6.mlp.experts.54.up_proj.weight": "model-00001-of-000001.safetensors",
1673 "model.layers.6.mlp.experts.54.down_proj.weight": "model-00001-of-000001.safetensors",
1674 "model.layers.6.mlp.experts.55.gate_proj.weight": "model-00001-of-000001.safetensors",
1675 "model.layers.6.mlp.experts.55.up_proj.weight": "model-00001-of-000001.safetensors",
1676 "model.layers.6.mlp.experts.55.down_proj.weight": "model-00001-of-000001.safetensors",
1677 "model.layers.6.mlp.experts.56.gate_proj.weight": "model-00001-of-000001.safetensors",
1678 "model.layers.6.mlp.experts.56.up_proj.weight": "model-00001-of-000001.safetensors",
1679 "model.layers.6.mlp.experts.56.down_proj.weight": "model-00001-of-000001.safetensors",
1680 "model.layers.6.mlp.experts.57.gate_proj.weight": "model-00001-of-000001.safetensors",
1681 "model.layers.6.mlp.experts.57.up_proj.weight": "model-00001-of-000001.safetensors",
1682 "model.layers.6.mlp.experts.57.down_proj.weight": "model-00001-of-000001.safetensors",
1683 "model.layers.6.mlp.experts.58.gate_proj.weight": "model-00001-of-000001.safetensors",
1684 "model.layers.6.mlp.experts.58.up_proj.weight": "model-00001-of-000001.safetensors",
1685 "model.layers.6.mlp.experts.58.down_proj.weight": "model-00001-of-000001.safetensors",
1686 "model.layers.6.mlp.experts.59.gate_proj.weight": "model-00001-of-000001.safetensors",
1687 "model.layers.6.mlp.experts.59.up_proj.weight": "model-00001-of-000001.safetensors",
1688 "model.layers.6.mlp.experts.59.down_proj.weight": "model-00001-of-000001.safetensors",
1689 "model.layers.6.mlp.experts.60.gate_proj.weight": "model-00001-of-000001.safetensors",
1690 "model.layers.6.mlp.experts.60.up_proj.weight": "model-00001-of-000001.safetensors",
1691 "model.layers.6.mlp.experts.60.down_proj.weight": "model-00001-of-000001.safetensors",
1692 "model.layers.6.mlp.experts.61.gate_proj.weight": "model-00001-of-000001.safetensors",
1693 "model.layers.6.mlp.experts.61.up_proj.weight": "model-00001-of-000001.safetensors",
1694 "model.layers.6.mlp.experts.61.down_proj.weight": "model-00001-of-000001.safetensors",
1695 "model.layers.6.mlp.experts.62.gate_proj.weight": "model-00001-of-000001.safetensors",
1696 "model.layers.6.mlp.experts.62.up_proj.weight": "model-00001-of-000001.safetensors",
1697 "model.layers.6.mlp.experts.62.down_proj.weight": "model-00001-of-000001.safetensors",
1698 "model.layers.6.mlp.experts.63.gate_proj.weight": "model-00001-of-000001.safetensors",
1699 "model.layers.6.mlp.experts.63.up_proj.weight": "model-00001-of-000001.safetensors",
1700 "model.layers.6.mlp.experts.63.down_proj.weight": "model-00001-of-000001.safetensors",
1701 "model.layers.6.input_layernorm.weight": "model-00001-of-000001.safetensors",
1702 "model.layers.6.post_attention_layernorm.weight": "model-00001-of-000001.safetensors",
1703 "model.layers.7.self_attn.q_proj.weight": "model-00001-of-000001.safetensors",
1704 "model.layers.7.self_attn.k_proj.weight": "model-00001-of-000001.safetensors",
1705 "model.layers.7.self_attn.v_proj.weight": "model-00001-of-000001.safetensors",
1706 "model.layers.7.self_attn.o_proj.weight": "model-00001-of-000001.safetensors",
1707 "model.layers.7.mlp.gate.weight": "model-00001-of-000001.safetensors",
1708 "model.layers.7.mlp.shared_experts.gate_proj.weight": "model-00001-of-000001.safetensors",
1709 "model.layers.7.mlp.shared_experts.up_proj.weight": "model-00001-of-000001.safetensors",
1710 "model.layers.7.mlp.shared_experts.down_proj.weight": "model-00001-of-000001.safetensors",
1711 "model.layers.7.mlp.experts.0.gate_proj.weight": "model-00001-of-000001.safetensors",
1712 "model.layers.7.mlp.experts.0.up_proj.weight": "model-00001-of-000001.safetensors",
1713 "model.layers.7.mlp.experts.0.down_proj.weight": "model-00001-of-000001.safetensors",
1714 "model.layers.7.mlp.experts.1.gate_proj.weight": "model-00001-of-000001.safetensors",
1715 "model.layers.7.mlp.experts.1.up_proj.weight": "model-00001-of-000001.safetensors",
1716 "model.layers.7.mlp.experts.1.down_proj.weight": "model-00001-of-000001.safetensors",
1717 "model.layers.7.mlp.experts.2.gate_proj.weight": "model-00001-of-000001.safetensors",
1718 "model.layers.7.mlp.experts.2.up_proj.weight": "model-00001-of-000001.safetensors",
1719 "model.layers.7.mlp.experts.2.down_proj.weight": "model-00001-of-000001.safetensors",
1720 "model.layers.7.mlp.experts.3.gate_proj.weight": "model-00001-of-000001.safetensors",
1721 "model.layers.7.mlp.experts.3.up_proj.weight": "model-00001-of-000001.safetensors",
1722 "model.layers.7.mlp.experts.3.down_proj.weight": "model-00001-of-000001.safetensors",
1723 "model.layers.7.mlp.experts.4.gate_proj.weight": "model-00001-of-000001.safetensors",
1724 "model.layers.7.mlp.experts.4.up_proj.weight": "model-00001-of-000001.safetensors",
1725 "model.layers.7.mlp.experts.4.down_proj.weight": "model-00001-of-000001.safetensors",
1726 "model.layers.7.mlp.experts.5.gate_proj.weight": "model-00001-of-000001.safetensors",
1727 "model.layers.7.mlp.experts.5.up_proj.weight": "model-00001-of-000001.safetensors",
1728 "model.layers.7.mlp.experts.5.down_proj.weight": "model-00001-of-000001.safetensors",
1729 "model.layers.7.mlp.experts.6.gate_proj.weight": "model-00001-of-000001.safetensors",
1730 "model.layers.7.mlp.experts.6.up_proj.weight": "model-00001-of-000001.safetensors",
1731 "model.layers.7.mlp.experts.6.down_proj.weight": "model-00001-of-000001.safetensors",
1732 "model.layers.7.mlp.experts.7.gate_proj.weight": "model-00001-of-000001.safetensors",
1733 "model.layers.7.mlp.experts.7.up_proj.weight": "model-00001-of-000001.safetensors",
1734 "model.layers.7.mlp.experts.7.down_proj.weight": "model-00001-of-000001.safetensors",
1735 "model.layers.7.mlp.experts.8.gate_proj.weight": "model-00001-of-000001.safetensors",
1736 "model.layers.7.mlp.experts.8.up_proj.weight": "model-00001-of-000001.safetensors",
1737 "model.layers.7.mlp.experts.8.down_proj.weight": "model-00001-of-000001.safetensors",
1738 "model.layers.7.mlp.experts.9.gate_proj.weight": "model-00001-of-000001.safetensors",
1739 "model.layers.7.mlp.experts.9.up_proj.weight": "model-00001-of-000001.safetensors",
1740 "model.layers.7.mlp.experts.9.down_proj.weight": "model-00001-of-000001.safetensors",
1741 "model.layers.7.mlp.experts.10.gate_proj.weight": "model-00001-of-000001.safetensors",
1742 "model.layers.7.mlp.experts.10.up_proj.weight": "model-00001-of-000001.safetensors",
1743 "model.layers.7.mlp.experts.10.down_proj.weight": "model-00001-of-000001.safetensors",
1744 "model.layers.7.mlp.experts.11.gate_proj.weight": "model-00001-of-000001.safetensors",
1745 "model.layers.7.mlp.experts.11.up_proj.weight": "model-00001-of-000001.safetensors",
1746 "model.layers.7.mlp.experts.11.down_proj.weight": "model-00001-of-000001.safetensors",
1747 "model.layers.7.mlp.experts.12.gate_proj.weight": "model-00001-of-000001.safetensors",
1748 "model.layers.7.mlp.experts.12.up_proj.weight": "model-00001-of-000001.safetensors",
1749 "model.layers.7.mlp.experts.12.down_proj.weight": "model-00001-of-000001.safetensors",
1750 "model.layers.7.mlp.experts.13.gate_proj.weight": "model-00001-of-000001.safetensors",
1751 "model.layers.7.mlp.experts.13.up_proj.weight": "model-00001-of-000001.safetensors",
1752 "model.layers.7.mlp.experts.13.down_proj.weight": "model-00001-of-000001.safetensors",
1753 "model.layers.7.mlp.experts.14.gate_proj.weight": "model-00001-of-000001.safetensors",
1754 "model.layers.7.mlp.experts.14.up_proj.weight": "model-00001-of-000001.safetensors",
1755 "model.layers.7.mlp.experts.14.down_proj.weight": "model-00001-of-000001.safetensors",
1756 "model.layers.7.mlp.experts.15.gate_proj.weight": "model-00001-of-000001.safetensors",
1757 "model.layers.7.mlp.experts.15.up_proj.weight": "model-00001-of-000001.safetensors",
1758 "model.layers.7.mlp.experts.15.down_proj.weight": "model-00001-of-000001.safetensors",
1759 "model.layers.7.mlp.experts.16.gate_proj.weight": "model-00001-of-000001.safetensors",
1760 "model.layers.7.mlp.experts.16.up_proj.weight": "model-00001-of-000001.safetensors",
1761 "model.layers.7.mlp.experts.16.down_proj.weight": "model-00001-of-000001.safetensors",
1762 "model.layers.7.mlp.experts.17.gate_proj.weight": "model-00001-of-000001.safetensors",
1763 "model.layers.7.mlp.experts.17.up_proj.weight": "model-00001-of-000001.safetensors",
1764 "model.layers.7.mlp.experts.17.down_proj.weight": "model-00001-of-000001.safetensors",
1765 "model.layers.7.mlp.experts.18.gate_proj.weight": "model-00001-of-000001.safetensors",
1766 "model.layers.7.mlp.experts.18.up_proj.weight": "model-00001-of-000001.safetensors",
1767 "model.layers.7.mlp.experts.18.down_proj.weight": "model-00001-of-000001.safetensors",
1768 "model.layers.7.mlp.experts.19.gate_proj.weight": "model-00001-of-000001.safetensors",
1769 "model.layers.7.mlp.experts.19.up_proj.weight": "model-00001-of-000001.safetensors",
1770 "model.layers.7.mlp.experts.19.down_proj.weight": "model-00001-of-000001.safetensors",
1771 "model.layers.7.mlp.experts.20.gate_proj.weight": "model-00001-of-000001.safetensors",
1772 "model.layers.7.mlp.experts.20.up_proj.weight": "model-00001-of-000001.safetensors",
1773 "model.layers.7.mlp.experts.20.down_proj.weight": "model-00001-of-000001.safetensors",
1774 "model.layers.7.mlp.experts.21.gate_proj.weight": "model-00001-of-000001.safetensors",
1775 "model.layers.7.mlp.experts.21.up_proj.weight": "model-00001-of-000001.safetensors",
1776 "model.layers.7.mlp.experts.21.down_proj.weight": "model-00001-of-000001.safetensors",
1777 "model.layers.7.mlp.experts.22.gate_proj.weight": "model-00001-of-000001.safetensors",
1778 "model.layers.7.mlp.experts.22.up_proj.weight": "model-00001-of-000001.safetensors",
1779 "model.layers.7.mlp.experts.22.down_proj.weight": "model-00001-of-000001.safetensors",
1780 "model.layers.7.mlp.experts.23.gate_proj.weight": "model-00001-of-000001.safetensors",
1781 "model.layers.7.mlp.experts.23.up_proj.weight": "model-00001-of-000001.safetensors",
1782 "model.layers.7.mlp.experts.23.down_proj.weight": "model-00001-of-000001.safetensors",
1783 "model.layers.7.mlp.experts.24.gate_proj.weight": "model-00001-of-000001.safetensors",
1784 "model.layers.7.mlp.experts.24.up_proj.weight": "model-00001-of-000001.safetensors",
1785 "model.layers.7.mlp.experts.24.down_proj.weight": "model-00001-of-000001.safetensors",
1786 "model.layers.7.mlp.experts.25.gate_proj.weight": "model-00001-of-000001.safetensors",
1787 "model.layers.7.mlp.experts.25.up_proj.weight": "model-00001-of-000001.safetensors",
1788 "model.layers.7.mlp.experts.25.down_proj.weight": "model-00001-of-000001.safetensors",
1789 "model.layers.7.mlp.experts.26.gate_proj.weight": "model-00001-of-000001.safetensors",
1790 "model.layers.7.mlp.experts.26.up_proj.weight": "model-00001-of-000001.safetensors",
1791 "model.layers.7.mlp.experts.26.down_proj.weight": "model-00001-of-000001.safetensors",
1792 "model.layers.7.mlp.experts.27.gate_proj.weight": "model-00001-of-000001.safetensors",
1793 "model.layers.7.mlp.experts.27.up_proj.weight": "model-00001-of-000001.safetensors",
1794 "model.layers.7.mlp.experts.27.down_proj.weight": "model-00001-of-000001.safetensors",
1795 "model.layers.7.mlp.experts.28.gate_proj.weight": "model-00001-of-000001.safetensors",
1796 "model.layers.7.mlp.experts.28.up_proj.weight": "model-00001-of-000001.safetensors",
1797 "model.layers.7.mlp.experts.28.down_proj.weight": "model-00001-of-000001.safetensors",
1798 "model.layers.7.mlp.experts.29.gate_proj.weight": "model-00001-of-000001.safetensors",
1799 "model.layers.7.mlp.experts.29.up_proj.weight": "model-00001-of-000001.safetensors",
1800 "model.layers.7.mlp.experts.29.down_proj.weight": "model-00001-of-000001.safetensors",
1801 "model.layers.7.mlp.experts.30.gate_proj.weight": "model-00001-of-000001.safetensors",
1802 "model.layers.7.mlp.experts.30.up_proj.weight": "model-00001-of-000001.safetensors",
1803 "model.layers.7.mlp.experts.30.down_proj.weight": "model-00001-of-000001.safetensors",
1804 "model.layers.7.mlp.experts.31.gate_proj.weight": "model-00001-of-000001.safetensors",
1805 "model.layers.7.mlp.experts.31.up_proj.weight": "model-00001-of-000001.safetensors",
1806 "model.layers.7.mlp.experts.31.down_proj.weight": "model-00001-of-000001.safetensors",
1807 "model.layers.7.mlp.experts.32.gate_proj.weight": "model-00001-of-000001.safetensors",
1808 "model.layers.7.mlp.experts.32.up_proj.weight": "model-00001-of-000001.safetensors",
1809 "model.layers.7.mlp.experts.32.down_proj.weight": "model-00001-of-000001.safetensors",
1810 "model.layers.7.mlp.experts.33.gate_proj.weight": "model-00001-of-000001.safetensors",
1811 "model.layers.7.mlp.experts.33.up_proj.weight": "model-00001-of-000001.safetensors",
1812 "model.layers.7.mlp.experts.33.down_proj.weight": "model-00001-of-000001.safetensors",
1813 "model.layers.7.mlp.experts.34.gate_proj.weight": "model-00001-of-000001.safetensors",
1814 "model.layers.7.mlp.experts.34.up_proj.weight": "model-00001-of-000001.safetensors",
1815 "model.layers.7.mlp.experts.34.down_proj.weight": "model-00001-of-000001.safetensors",
1816 "model.layers.7.mlp.experts.35.gate_proj.weight": "model-00001-of-000001.safetensors",
1817 "model.layers.7.mlp.experts.35.up_proj.weight": "model-00001-of-000001.safetensors",
1818 "model.layers.7.mlp.experts.35.down_proj.weight": "model-00001-of-000001.safetensors",
1819 "model.layers.7.mlp.experts.36.gate_proj.weight": "model-00001-of-000001.safetensors",
1820 "model.layers.7.mlp.experts.36.up_proj.weight": "model-00001-of-000001.safetensors",
1821 "model.layers.7.mlp.experts.36.down_proj.weight": "model-00001-of-000001.safetensors",
1822 "model.layers.7.mlp.experts.37.gate_proj.weight": "model-00001-of-000001.safetensors",
1823 "model.layers.7.mlp.experts.37.up_proj.weight": "model-00001-of-000001.safetensors",
1824 "model.layers.7.mlp.experts.37.down_proj.weight": "model-00001-of-000001.safetensors",
1825 "model.layers.7.mlp.experts.38.gate_proj.weight": "model-00001-of-000001.safetensors",
1826 "model.layers.7.mlp.experts.38.up_proj.weight": "model-00001-of-000001.safetensors",
1827 "model.layers.7.mlp.experts.38.down_proj.weight": "model-00001-of-000001.safetensors",
1828 "model.layers.7.mlp.experts.39.gate_proj.weight": "model-00001-of-000001.safetensors",
1829 "model.layers.7.mlp.experts.39.up_proj.weight": "model-00001-of-000001.safetensors",
1830 "model.layers.7.mlp.experts.39.down_proj.weight": "model-00001-of-000001.safetensors",
1831 "model.layers.7.mlp.experts.40.gate_proj.weight": "model-00001-of-000001.safetensors",
1832 "model.layers.7.mlp.experts.40.up_proj.weight": "model-00001-of-000001.safetensors",
1833 "model.layers.7.mlp.experts.40.down_proj.weight": "model-00001-of-000001.safetensors",
1834 "model.layers.7.mlp.experts.41.gate_proj.weight": "model-00001-of-000001.safetensors",
1835 "model.layers.7.mlp.experts.41.up_proj.weight": "model-00001-of-000001.safetensors",
1836 "model.layers.7.mlp.experts.41.down_proj.weight": "model-00001-of-000001.safetensors",
1837 "model.layers.7.mlp.experts.42.gate_proj.weight": "model-00001-of-000001.safetensors",
1838 "model.layers.7.mlp.experts.42.up_proj.weight": "model-00001-of-000001.safetensors",
1839 "model.layers.7.mlp.experts.42.down_proj.weight": "model-00001-of-000001.safetensors",
1840 "model.layers.7.mlp.experts.43.gate_proj.weight": "model-00001-of-000001.safetensors",
1841 "model.layers.7.mlp.experts.43.up_proj.weight": "model-00001-of-000001.safetensors",
1842 "model.layers.7.mlp.experts.43.down_proj.weight": "model-00001-of-000001.safetensors",
1843 "model.layers.7.mlp.experts.44.gate_proj.weight": "model-00001-of-000001.safetensors",
1844 "model.layers.7.mlp.experts.44.up_proj.weight": "model-00001-of-000001.safetensors",
1845 "model.layers.7.mlp.experts.44.down_proj.weight": "model-00001-of-000001.safetensors",
1846 "model.layers.7.mlp.experts.45.gate_proj.weight": "model-00001-of-000001.safetensors",
1847 "model.layers.7.mlp.experts.45.up_proj.weight": "model-00001-of-000001.safetensors",
1848 "model.layers.7.mlp.experts.45.down_proj.weight": "model-00001-of-000001.safetensors",
1849 "model.layers.7.mlp.experts.46.gate_proj.weight": "model-00001-of-000001.safetensors",
1850 "model.layers.7.mlp.experts.46.up_proj.weight": "model-00001-of-000001.safetensors",
1851 "model.layers.7.mlp.experts.46.down_proj.weight": "model-00001-of-000001.safetensors",
1852 "model.layers.7.mlp.experts.47.gate_proj.weight": "model-00001-of-000001.safetensors",
1853 "model.layers.7.mlp.experts.47.up_proj.weight": "model-00001-of-000001.safetensors",
1854 "model.layers.7.mlp.experts.47.down_proj.weight": "model-00001-of-000001.safetensors",
1855 "model.layers.7.mlp.experts.48.gate_proj.weight": "model-00001-of-000001.safetensors",
1856 "model.layers.7.mlp.experts.48.up_proj.weight": "model-00001-of-000001.safetensors",
1857 "model.layers.7.mlp.experts.48.down_proj.weight": "model-00001-of-000001.safetensors",
1858 "model.layers.7.mlp.experts.49.gate_proj.weight": "model-00001-of-000001.safetensors",
1859 "model.layers.7.mlp.experts.49.up_proj.weight": "model-00001-of-000001.safetensors",
1860 "model.layers.7.mlp.experts.49.down_proj.weight": "model-00001-of-000001.safetensors",
1861 "model.layers.7.mlp.experts.50.gate_proj.weight": "model-00001-of-000001.safetensors",
1862 "model.layers.7.mlp.experts.50.up_proj.weight": "model-00001-of-000001.safetensors",
1863 "model.layers.7.mlp.experts.50.down_proj.weight": "model-00001-of-000001.safetensors",
1864 "model.layers.7.mlp.experts.51.gate_proj.weight": "model-00001-of-000001.safetensors",
1865 "model.layers.7.mlp.experts.51.up_proj.weight": "model-00001-of-000001.safetensors",
1866 "model.layers.7.mlp.experts.51.down_proj.weight": "model-00001-of-000001.safetensors",
1867 "model.layers.7.mlp.experts.52.gate_proj.weight": "model-00001-of-000001.safetensors",
1868 "model.layers.7.mlp.experts.52.up_proj.weight": "model-00001-of-000001.safetensors",
1869 "model.layers.7.mlp.experts.52.down_proj.weight": "model-00001-of-000001.safetensors",
1870 "model.layers.7.mlp.experts.53.gate_proj.weight": "model-00001-of-000001.safetensors",
1871 "model.layers.7.mlp.experts.53.up_proj.weight": "model-00001-of-000001.safetensors",
1872 "model.layers.7.mlp.experts.53.down_proj.weight": "model-00001-of-000001.safetensors",
1873 "model.layers.7.mlp.experts.54.gate_proj.weight": "model-00001-of-000001.safetensors",
1874 "model.layers.7.mlp.experts.54.up_proj.weight": "model-00001-of-000001.safetensors",
1875 "model.layers.7.mlp.experts.54.down_proj.weight": "model-00001-of-000001.safetensors",
1876 "model.layers.7.mlp.experts.55.gate_proj.weight": "model-00001-of-000001.safetensors",
1877 "model.layers.7.mlp.experts.55.up_proj.weight": "model-00001-of-000001.safetensors",
1878 "model.layers.7.mlp.experts.55.down_proj.weight": "model-00001-of-000001.safetensors",
1879 "model.layers.7.mlp.experts.56.gate_proj.weight": "model-00001-of-000001.safetensors",
1880 "model.layers.7.mlp.experts.56.up_proj.weight": "model-00001-of-000001.safetensors",
1881 "model.layers.7.mlp.experts.56.down_proj.weight": "model-00001-of-000001.safetensors",
1882 "model.layers.7.mlp.experts.57.gate_proj.weight": "model-00001-of-000001.safetensors",
1883 "model.layers.7.mlp.experts.57.up_proj.weight": "model-00001-of-000001.safetensors",
1884 "model.layers.7.mlp.experts.57.down_proj.weight": "model-00001-of-000001.safetensors",
1885 "model.layers.7.mlp.experts.58.gate_proj.weight": "model-00001-of-000001.safetensors",
1886 "model.layers.7.mlp.experts.58.up_proj.weight": "model-00001-of-000001.safetensors",
1887 "model.layers.7.mlp.experts.58.down_proj.weight": "model-00001-of-000001.safetensors",
1888 "model.layers.7.mlp.experts.59.gate_proj.weight": "model-00001-of-000001.safetensors",
1889 "model.layers.7.mlp.experts.59.up_proj.weight": "model-00001-of-000001.safetensors",
1890 "model.layers.7.mlp.experts.59.down_proj.weight": "model-00001-of-000001.safetensors",
1891 "model.layers.7.mlp.experts.60.gate_proj.weight": "model-00001-of-000001.safetensors",
1892 "model.layers.7.mlp.experts.60.up_proj.weight": "model-00001-of-000001.safetensors",
1893 "model.layers.7.mlp.experts.60.down_proj.weight": "model-00001-of-000001.safetensors",
1894 "model.layers.7.mlp.experts.61.gate_proj.weight": "model-00001-of-000001.safetensors",
1895 "model.layers.7.mlp.experts.61.up_proj.weight": "model-00001-of-000001.safetensors",
1896 "model.layers.7.mlp.experts.61.down_proj.weight": "model-00001-of-000001.safetensors",
1897 "model.layers.7.mlp.experts.62.gate_proj.weight": "model-00001-of-000001.safetensors",
1898 "model.layers.7.mlp.experts.62.up_proj.weight": "model-00001-of-000001.safetensors",
1899 "model.layers.7.mlp.experts.62.down_proj.weight": "model-00001-of-000001.safetensors",
1900 "model.layers.7.mlp.experts.63.gate_proj.weight": "model-00001-of-000001.safetensors",
1901 "model.layers.7.mlp.experts.63.up_proj.weight": "model-00001-of-000001.safetensors",
1902 "model.layers.7.mlp.experts.63.down_proj.weight": "model-00001-of-000001.safetensors",
1903 "model.layers.7.input_layernorm.weight": "model-00001-of-000001.safetensors",
1904 "model.layers.7.post_attention_layernorm.weight": "model-00001-of-000001.safetensors",
1905 "model.layers.8.self_attn.q_proj.weight": "model-00001-of-000001.safetensors",
1906 "model.layers.8.self_attn.k_proj.weight": "model-00001-of-000001.safetensors",
1907 "model.layers.8.self_attn.v_proj.weight": "model-00001-of-000001.safetensors",
1908 "model.layers.8.self_attn.o_proj.weight": "model-00001-of-000001.safetensors",
1909 "model.layers.8.mlp.gate.weight": "model-00001-of-000001.safetensors",
1910 "model.layers.8.mlp.shared_experts.gate_proj.weight": "model-00001-of-000001.safetensors",
1911 "model.layers.8.mlp.shared_experts.up_proj.weight": "model-00001-of-000001.safetensors",
1912 "model.layers.8.mlp.shared_experts.down_proj.weight": "model-00001-of-000001.safetensors",
1913 "model.layers.8.mlp.experts.0.gate_proj.weight": "model-00001-of-000001.safetensors",
1914 "model.layers.8.mlp.experts.0.up_proj.weight": "model-00001-of-000001.safetensors",
1915 "model.layers.8.mlp.experts.0.down_proj.weight": "model-00001-of-000001.safetensors",
1916 "model.layers.8.mlp.experts.1.gate_proj.weight": "model-00001-of-000001.safetensors",
1917 "model.layers.8.mlp.experts.1.up_proj.weight": "model-00001-of-000001.safetensors",
1918 "model.layers.8.mlp.experts.1.down_proj.weight": "model-00001-of-000001.safetensors",
1919 "model.layers.8.mlp.experts.2.gate_proj.weight": "model-00001-of-000001.safetensors",
1920 "model.layers.8.mlp.experts.2.up_proj.weight": "model-00001-of-000001.safetensors",
1921 "model.layers.8.mlp.experts.2.down_proj.weight": "model-00001-of-000001.safetensors",
1922 "model.layers.8.mlp.experts.3.gate_proj.weight": "model-00001-of-000001.safetensors",
1923 "model.layers.8.mlp.experts.3.up_proj.weight": "model-00001-of-000001.safetensors",
1924 "model.layers.8.mlp.experts.3.down_proj.weight": "model-00001-of-000001.safetensors",
1925 "model.layers.8.mlp.experts.4.gate_proj.weight": "model-00001-of-000001.safetensors",
1926 "model.layers.8.mlp.experts.4.up_proj.weight": "model-00001-of-000001.safetensors",
1927 "model.layers.8.mlp.experts.4.down_proj.weight": "model-00001-of-000001.safetensors",
1928 "model.layers.8.mlp.experts.5.gate_proj.weight": "model-00001-of-000001.safetensors",
1929 "model.layers.8.mlp.experts.5.up_proj.weight": "model-00001-of-000001.safetensors",
1930 "model.layers.8.mlp.experts.5.down_proj.weight": "model-00001-of-000001.safetensors",
1931 "model.layers.8.mlp.experts.6.gate_proj.weight": "model-00001-of-000001.safetensors",
1932 "model.layers.8.mlp.experts.6.up_proj.weight": "model-00001-of-000001.safetensors",
1933 "model.layers.8.mlp.experts.6.down_proj.weight": "model-00001-of-000001.safetensors",
1934 "model.layers.8.mlp.experts.7.gate_proj.weight": "model-00001-of-000001.safetensors",
1935 "model.layers.8.mlp.experts.7.up_proj.weight": "model-00001-of-000001.safetensors",
1936 "model.layers.8.mlp.experts.7.down_proj.weight": "model-00001-of-000001.safetensors",
1937 "model.layers.8.mlp.experts.8.gate_proj.weight": "model-00001-of-000001.safetensors",
1938 "model.layers.8.mlp.experts.8.up_proj.weight": "model-00001-of-000001.safetensors",
1939 "model.layers.8.mlp.experts.8.down_proj.weight": "model-00001-of-000001.safetensors",
1940 "model.layers.8.mlp.experts.9.gate_proj.weight": "model-00001-of-000001.safetensors",
1941 "model.layers.8.mlp.experts.9.up_proj.weight": "model-00001-of-000001.safetensors",
1942 "model.layers.8.mlp.experts.9.down_proj.weight": "model-00001-of-000001.safetensors",
1943 "model.layers.8.mlp.experts.10.gate_proj.weight": "model-00001-of-000001.safetensors",
1944 "model.layers.8.mlp.experts.10.up_proj.weight": "model-00001-of-000001.safetensors",
1945 "model.layers.8.mlp.experts.10.down_proj.weight": "model-00001-of-000001.safetensors",
1946 "model.layers.8.mlp.experts.11.gate_proj.weight": "model-00001-of-000001.safetensors",
1947 "model.layers.8.mlp.experts.11.up_proj.weight": "model-00001-of-000001.safetensors",
1948 "model.layers.8.mlp.experts.11.down_proj.weight": "model-00001-of-000001.safetensors",
1949 "model.layers.8.mlp.experts.12.gate_proj.weight": "model-00001-of-000001.safetensors",
1950 "model.layers.8.mlp.experts.12.up_proj.weight": "model-00001-of-000001.safetensors",
1951 "model.layers.8.mlp.experts.12.down_proj.weight": "model-00001-of-000001.safetensors",
1952 "model.layers.8.mlp.experts.13.gate_proj.weight": "model-00001-of-000001.safetensors",
1953 "model.layers.8.mlp.experts.13.up_proj.weight": "model-00001-of-000001.safetensors",
1954 "model.layers.8.mlp.experts.13.down_proj.weight": "model-00001-of-000001.safetensors",
1955 "model.layers.8.mlp.experts.14.gate_proj.weight": "model-00001-of-000001.safetensors",
1956 "model.layers.8.mlp.experts.14.up_proj.weight": "model-00001-of-000001.safetensors",
1957 "model.layers.8.mlp.experts.14.down_proj.weight": "model-00001-of-000001.safetensors",
1958 "model.layers.8.mlp.experts.15.gate_proj.weight": "model-00001-of-000001.safetensors",
1959 "model.layers.8.mlp.experts.15.up_proj.weight": "model-00001-of-000001.safetensors",
1960 "model.layers.8.mlp.experts.15.down_proj.weight": "model-00001-of-000001.safetensors",
1961 "model.layers.8.mlp.experts.16.gate_proj.weight": "model-00001-of-000001.safetensors",
1962 "model.layers.8.mlp.experts.16.up_proj.weight": "model-00001-of-000001.safetensors",
1963 "model.layers.8.mlp.experts.16.down_proj.weight": "model-00001-of-000001.safetensors",
1964 "model.layers.8.mlp.experts.17.gate_proj.weight": "model-00001-of-000001.safetensors",
1965 "model.layers.8.mlp.experts.17.up_proj.weight": "model-00001-of-000001.safetensors",
1966 "model.layers.8.mlp.experts.17.down_proj.weight": "model-00001-of-000001.safetensors",
1967 "model.layers.8.mlp.experts.18.gate_proj.weight": "model-00001-of-000001.safetensors",
1968 "model.layers.8.mlp.experts.18.up_proj.weight": "model-00001-of-000001.safetensors",
1969 "model.layers.8.mlp.experts.18.down_proj.weight": "model-00001-of-000001.safetensors",
1970 "model.layers.8.mlp.experts.19.gate_proj.weight": "model-00001-of-000001.safetensors",
1971 "model.layers.8.mlp.experts.19.up_proj.weight": "model-00001-of-000001.safetensors",
1972 "model.layers.8.mlp.experts.19.down_proj.weight": "model-00001-of-000001.safetensors",
1973 "model.layers.8.mlp.experts.20.gate_proj.weight": "model-00001-of-000001.safetensors",
1974 "model.layers.8.mlp.experts.20.up_proj.weight": "model-00001-of-000001.safetensors",
1975 "model.layers.8.mlp.experts.20.down_proj.weight": "model-00001-of-000001.safetensors",
1976 "model.layers.8.mlp.experts.21.gate_proj.weight": "model-00001-of-000001.safetensors",
1977 "model.layers.8.mlp.experts.21.up_proj.weight": "model-00001-of-000001.safetensors",
1978 "model.layers.8.mlp.experts.21.down_proj.weight": "model-00001-of-000001.safetensors",
1979 "model.layers.8.mlp.experts.22.gate_proj.weight": "model-00001-of-000001.safetensors",
1980 "model.layers.8.mlp.experts.22.up_proj.weight": "model-00001-of-000001.safetensors",
1981 "model.layers.8.mlp.experts.22.down_proj.weight": "model-00001-of-000001.safetensors",
1982 "model.layers.8.mlp.experts.23.gate_proj.weight": "model-00001-of-000001.safetensors",
1983 "model.layers.8.mlp.experts.23.up_proj.weight": "model-00001-of-000001.safetensors",
1984 "model.layers.8.mlp.experts.23.down_proj.weight": "model-00001-of-000001.safetensors",
1985 "model.layers.8.mlp.experts.24.gate_proj.weight": "model-00001-of-000001.safetensors",
1986 "model.layers.8.mlp.experts.24.up_proj.weight": "model-00001-of-000001.safetensors",
1987 "model.layers.8.mlp.experts.24.down_proj.weight": "model-00001-of-000001.safetensors",
1988 "model.layers.8.mlp.experts.25.gate_proj.weight": "model-00001-of-000001.safetensors",
1989 "model.layers.8.mlp.experts.25.up_proj.weight": "model-00001-of-000001.safetensors",
1990 "model.layers.8.mlp.experts.25.down_proj.weight": "model-00001-of-000001.safetensors",
1991 "model.layers.8.mlp.experts.26.gate_proj.weight": "model-00001-of-000001.safetensors",
1992 "model.layers.8.mlp.experts.26.up_proj.weight": "model-00001-of-000001.safetensors",
1993 "model.layers.8.mlp.experts.26.down_proj.weight": "model-00001-of-000001.safetensors",
1994 "model.layers.8.mlp.experts.27.gate_proj.weight": "model-00001-of-000001.safetensors",
1995 "model.layers.8.mlp.experts.27.up_proj.weight": "model-00001-of-000001.safetensors",
1996 "model.layers.8.mlp.experts.27.down_proj.weight": "model-00001-of-000001.safetensors",
1997 "model.layers.8.mlp.experts.28.gate_proj.weight": "model-00001-of-000001.safetensors",
1998 "model.layers.8.mlp.experts.28.up_proj.weight": "model-00001-of-000001.safetensors",
1999 "model.layers.8.mlp.experts.28.down_proj.weight": "model-00001-of-000001.safetensors",
2000 "model.layers.8.mlp.experts.29.gate_proj.weight": "model-00001-of-000001.safetensors",
2001 "model.layers.8.mlp.experts.29.up_proj.weight": "model-00001-of-000001.safetensors",
2002 "model.layers.8.mlp.experts.29.down_proj.weight": "model-00001-of-000001.safetensors",
2003 "model.layers.8.mlp.experts.30.gate_proj.weight": "model-00001-of-000001.safetensors",
2004 "model.layers.8.mlp.experts.30.up_proj.weight": "model-00001-of-000001.safetensors",
2005 "model.layers.8.mlp.experts.30.down_proj.weight": "model-00001-of-000001.safetensors",
2006 "model.layers.8.mlp.experts.31.gate_proj.weight": "model-00001-of-000001.safetensors",
2007 "model.layers.8.mlp.experts.31.up_proj.weight": "model-00001-of-000001.safetensors",
2008 "model.layers.8.mlp.experts.31.down_proj.weight": "model-00001-of-000001.safetensors",
2009 "model.layers.8.mlp.experts.32.gate_proj.weight": "model-00001-of-000001.safetensors",
2010 "model.layers.8.mlp.experts.32.up_proj.weight": "model-00001-of-000001.safetensors",
2011 "model.layers.8.mlp.experts.32.down_proj.weight": "model-00001-of-000001.safetensors",
2012 "model.layers.8.mlp.experts.33.gate_proj.weight": "model-00001-of-000001.safetensors",
2013 "model.layers.8.mlp.experts.33.up_proj.weight": "model-00001-of-000001.safetensors",
2014 "model.layers.8.mlp.experts.33.down_proj.weight": "model-00001-of-000001.safetensors",
2015 "model.layers.8.mlp.experts.34.gate_proj.weight": "model-00001-of-000001.safetensors",
2016 "model.layers.8.mlp.experts.34.up_proj.weight": "model-00001-of-000001.safetensors",
2017 "model.layers.8.mlp.experts.34.down_proj.weight": "model-00001-of-000001.safetensors",
2018 "model.layers.8.mlp.experts.35.gate_proj.weight": "model-00001-of-000001.safetensors",
2019 "model.layers.8.mlp.experts.35.up_proj.weight": "model-00001-of-000001.safetensors",
2020 "model.layers.8.mlp.experts.35.down_proj.weight": "model-00001-of-000001.safetensors",
2021 "model.layers.8.mlp.experts.36.gate_proj.weight": "model-00001-of-000001.safetensors",
2022 "model.layers.8.mlp.experts.36.up_proj.weight": "model-00001-of-000001.safetensors",
2023 "model.layers.8.mlp.experts.36.down_proj.weight": "model-00001-of-000001.safetensors",
2024 "model.layers.8.mlp.experts.37.gate_proj.weight": "model-00001-of-000001.safetensors",
2025 "model.layers.8.mlp.experts.37.up_proj.weight": "model-00001-of-000001.safetensors",
2026 "model.layers.8.mlp.experts.37.down_proj.weight": "model-00001-of-000001.safetensors",
2027 "model.layers.8.mlp.experts.38.gate_proj.weight": "model-00001-of-000001.safetensors",
2028 "model.layers.8.mlp.experts.38.up_proj.weight": "model-00001-of-000001.safetensors",
2029 "model.layers.8.mlp.experts.38.down_proj.weight": "model-00001-of-000001.safetensors",
2030 "model.layers.8.mlp.experts.39.gate_proj.weight": "model-00001-of-000001.safetensors",
2031 "model.layers.8.mlp.experts.39.up_proj.weight": "model-00001-of-000001.safetensors",
2032 "model.layers.8.mlp.experts.39.down_proj.weight": "model-00001-of-000001.safetensors",
2033 "model.layers.8.mlp.experts.40.gate_proj.weight": "model-00001-of-000001.safetensors",
2034 "model.layers.8.mlp.experts.40.up_proj.weight": "model-00001-of-000001.safetensors",
2035 "model.layers.8.mlp.experts.40.down_proj.weight": "model-00001-of-000001.safetensors",
2036 "model.layers.8.mlp.experts.41.gate_proj.weight": "model-00001-of-000001.safetensors",
2037 "model.layers.8.mlp.experts.41.up_proj.weight": "model-00001-of-000001.safetensors",
2038 "model.layers.8.mlp.experts.41.down_proj.weight": "model-00001-of-000001.safetensors",
2039 "model.layers.8.mlp.experts.42.gate_proj.weight": "model-00001-of-000001.safetensors",
2040 "model.layers.8.mlp.experts.42.up_proj.weight": "model-00001-of-000001.safetensors",
2041 "model.layers.8.mlp.experts.42.down_proj.weight": "model-00001-of-000001.safetensors",
2042 "model.layers.8.mlp.experts.43.gate_proj.weight": "model-00001-of-000001.safetensors",
2043 "model.layers.8.mlp.experts.43.up_proj.weight": "model-00001-of-000001.safetensors",
2044 "model.layers.8.mlp.experts.43.down_proj.weight": "model-00001-of-000001.safetensors",
2045 "model.layers.8.mlp.experts.44.gate_proj.weight": "model-00001-of-000001.safetensors",
2046 "model.layers.8.mlp.experts.44.up_proj.weight": "model-00001-of-000001.safetensors",
2047 "model.layers.8.mlp.experts.44.down_proj.weight": "model-00001-of-000001.safetensors",
2048 "model.layers.8.mlp.experts.45.gate_proj.weight": "model-00001-of-000001.safetensors",
2049 "model.layers.8.mlp.experts.45.up_proj.weight": "model-00001-of-000001.safetensors",
2050 "model.layers.8.mlp.experts.45.down_proj.weight": "model-00001-of-000001.safetensors",
2051 "model.layers.8.mlp.experts.46.gate_proj.weight": "model-00001-of-000001.safetensors",
2052 "model.layers.8.mlp.experts.46.up_proj.weight": "model-00001-of-000001.safetensors",
2053 "model.layers.8.mlp.experts.46.down_proj.weight": "model-00001-of-000001.safetensors",
2054 "model.layers.8.mlp.experts.47.gate_proj.weight": "model-00001-of-000001.safetensors",
2055 "model.layers.8.mlp.experts.47.up_proj.weight": "model-00001-of-000001.safetensors",
2056 "model.layers.8.mlp.experts.47.down_proj.weight": "model-00001-of-000001.safetensors",
2057 "model.layers.8.mlp.experts.48.gate_proj.weight": "model-00001-of-000001.safetensors",
2058 "model.layers.8.mlp.experts.48.up_proj.weight": "model-00001-of-000001.safetensors",
2059 "model.layers.8.mlp.experts.48.down_proj.weight": "model-00001-of-000001.safetensors",
2060 "model.layers.8.mlp.experts.49.gate_proj.weight": "model-00001-of-000001.safetensors",
2061 "model.layers.8.mlp.experts.49.up_proj.weight": "model-00001-of-000001.safetensors",
2062 "model.layers.8.mlp.experts.49.down_proj.weight": "model-00001-of-000001.safetensors",
2063 "model.layers.8.mlp.experts.50.gate_proj.weight": "model-00001-of-000001.safetensors",
2064 "model.layers.8.mlp.experts.50.up_proj.weight": "model-00001-of-000001.safetensors",
2065 "model.layers.8.mlp.experts.50.down_proj.weight": "model-00001-of-000001.safetensors",
2066 "model.layers.8.mlp.experts.51.gate_proj.weight": "model-00001-of-000001.safetensors",
2067 "model.layers.8.mlp.experts.51.up_proj.weight": "model-00001-of-000001.safetensors",
2068 "model.layers.8.mlp.experts.51.down_proj.weight": "model-00001-of-000001.safetensors",
2069 "model.layers.8.mlp.experts.52.gate_proj.weight": "model-00001-of-000001.safetensors",
2070 "model.layers.8.mlp.experts.52.up_proj.weight": "model-00001-of-000001.safetensors",
2071 "model.layers.8.mlp.experts.52.down_proj.weight": "model-00001-of-000001.safetensors",
2072 "model.layers.8.mlp.experts.53.gate_proj.weight": "model-00001-of-000001.safetensors",
2073 "model.layers.8.mlp.experts.53.up_proj.weight": "model-00001-of-000001.safetensors",
2074 "model.layers.8.mlp.experts.53.down_proj.weight": "model-00001-of-000001.safetensors",
2075 "model.layers.8.mlp.experts.54.gate_proj.weight": "model-00001-of-000001.safetensors",
2076 "model.layers.8.mlp.experts.54.up_proj.weight": "model-00001-of-000001.safetensors",
2077 "model.layers.8.mlp.experts.54.down_proj.weight": "model-00001-of-000001.safetensors",
2078 "model.layers.8.mlp.experts.55.gate_proj.weight": "model-00001-of-000001.safetensors",
2079 "model.layers.8.mlp.experts.55.up_proj.weight": "model-00001-of-000001.safetensors",
2080 "model.layers.8.mlp.experts.55.down_proj.weight": "model-00001-of-000001.safetensors",
2081 "model.layers.8.mlp.experts.56.gate_proj.weight": "model-00001-of-000001.safetensors",
2082 "model.layers.8.mlp.experts.56.up_proj.weight": "model-00001-of-000001.safetensors",
2083 "model.layers.8.mlp.experts.56.down_proj.weight": "model-00001-of-000001.safetensors",
2084 "model.layers.8.mlp.experts.57.gate_proj.weight": "model-00001-of-000001.safetensors",
2085 "model.layers.8.mlp.experts.57.up_proj.weight": "model-00001-of-000001.safetensors",
2086 "model.layers.8.mlp.experts.57.down_proj.weight": "model-00001-of-000001.safetensors",
2087 "model.layers.8.mlp.experts.58.gate_proj.weight": "model-00001-of-000001.safetensors",
2088 "model.layers.8.mlp.experts.58.up_proj.weight": "model-00001-of-000001.safetensors",
2089 "model.layers.8.mlp.experts.58.down_proj.weight": "model-00001-of-000001.safetensors",
2090 "model.layers.8.mlp.experts.59.gate_proj.weight": "model-00001-of-000001.safetensors",
2091 "model.layers.8.mlp.experts.59.up_proj.weight": "model-00001-of-000001.safetensors",
2092 "model.layers.8.mlp.experts.59.down_proj.weight": "model-00001-of-000001.safetensors",
2093 "model.layers.8.mlp.experts.60.gate_proj.weight": "model-00001-of-000001.safetensors",
2094 "model.layers.8.mlp.experts.60.up_proj.weight": "model-00001-of-000001.safetensors",
2095 "model.layers.8.mlp.experts.60.down_proj.weight": "model-00001-of-000001.safetensors",
2096 "model.layers.8.mlp.experts.61.gate_proj.weight": "model-00001-of-000001.safetensors",
2097 "model.layers.8.mlp.experts.61.up_proj.weight": "model-00001-of-000001.safetensors",
2098 "model.layers.8.mlp.experts.61.down_proj.weight": "model-00001-of-000001.safetensors",
2099 "model.layers.8.mlp.experts.62.gate_proj.weight": "model-00001-of-000001.safetensors",
2100 "model.layers.8.mlp.experts.62.up_proj.weight": "model-00001-of-000001.safetensors",
2101 "model.layers.8.mlp.experts.62.down_proj.weight": "model-00001-of-000001.safetensors",
2102 "model.layers.8.mlp.experts.63.gate_proj.weight": "model-00001-of-000001.safetensors",
2103 "model.layers.8.mlp.experts.63.up_proj.weight": "model-00001-of-000001.safetensors",
2104 "model.layers.8.mlp.experts.63.down_proj.weight": "model-00001-of-000001.safetensors",
2105 "model.layers.8.input_layernorm.weight": "model-00001-of-000001.safetensors",
2106 "model.layers.8.post_attention_layernorm.weight": "model-00001-of-000001.safetensors",
2107 "model.layers.9.self_attn.q_proj.weight": "model-00001-of-000001.safetensors",
2108 "model.layers.9.self_attn.k_proj.weight": "model-00001-of-000001.safetensors",
2109 "model.layers.9.self_attn.v_proj.weight": "model-00001-of-000001.safetensors",
2110 "model.layers.9.self_attn.o_proj.weight": "model-00001-of-000001.safetensors",
2111 "model.layers.9.mlp.gate.weight": "model-00001-of-000001.safetensors",
2112 "model.layers.9.mlp.shared_experts.gate_proj.weight": "model-00001-of-000001.safetensors",
2113 "model.layers.9.mlp.shared_experts.up_proj.weight": "model-00001-of-000001.safetensors",
2114 "model.layers.9.mlp.shared_experts.down_proj.weight": "model-00001-of-000001.safetensors",
2115 "model.layers.9.mlp.experts.0.gate_proj.weight": "model-00001-of-000001.safetensors",
2116 "model.layers.9.mlp.experts.0.up_proj.weight": "model-00001-of-000001.safetensors",
2117 "model.layers.9.mlp.experts.0.down_proj.weight": "model-00001-of-000001.safetensors",
2118 "model.layers.9.mlp.experts.1.gate_proj.weight": "model-00001-of-000001.safetensors",
2119 "model.layers.9.mlp.experts.1.up_proj.weight": "model-00001-of-000001.safetensors",
2120 "model.layers.9.mlp.experts.1.down_proj.weight": "model-00001-of-000001.safetensors",
2121 "model.layers.9.mlp.experts.2.gate_proj.weight": "model-00001-of-000001.safetensors",
2122 "model.layers.9.mlp.experts.2.up_proj.weight": "model-00001-of-000001.safetensors",
2123 "model.layers.9.mlp.experts.2.down_proj.weight": "model-00001-of-000001.safetensors",
2124 "model.layers.9.mlp.experts.3.gate_proj.weight": "model-00001-of-000001.safetensors",
2125 "model.layers.9.mlp.experts.3.up_proj.weight": "model-00001-of-000001.safetensors",
2126 "model.layers.9.mlp.experts.3.down_proj.weight": "model-00001-of-000001.safetensors",
2127 "model.layers.9.mlp.experts.4.gate_proj.weight": "model-00001-of-000001.safetensors",
2128 "model.layers.9.mlp.experts.4.up_proj.weight": "model-00001-of-000001.safetensors",
2129 "model.layers.9.mlp.experts.4.down_proj.weight": "model-00001-of-000001.safetensors",
2130 "model.layers.9.mlp.experts.5.gate_proj.weight": "model-00001-of-000001.safetensors",
2131 "model.layers.9.mlp.experts.5.up_proj.weight": "model-00001-of-000001.safetensors",
2132 "model.layers.9.mlp.experts.5.down_proj.weight": "model-00001-of-000001.safetensors",
2133 "model.layers.9.mlp.experts.6.gate_proj.weight": "model-00001-of-000001.safetensors",
2134 "model.layers.9.mlp.experts.6.up_proj.weight": "model-00001-of-000001.safetensors",
2135 "model.layers.9.mlp.experts.6.down_proj.weight": "model-00001-of-000001.safetensors",
2136 "model.layers.9.mlp.experts.7.gate_proj.weight": "model-00001-of-000001.safetensors",
2137 "model.layers.9.mlp.experts.7.up_proj.weight": "model-00001-of-000001.safetensors",
2138 "model.layers.9.mlp.experts.7.down_proj.weight": "model-00001-of-000001.safetensors",
2139 "model.layers.9.mlp.experts.8.gate_proj.weight": "model-00001-of-000001.safetensors",
2140 "model.layers.9.mlp.experts.8.up_proj.weight": "model-00001-of-000001.safetensors",
2141 "model.layers.9.mlp.experts.8.down_proj.weight": "model-00001-of-000001.safetensors",
2142 "model.layers.9.mlp.experts.9.gate_proj.weight": "model-00001-of-000001.safetensors",
2143 "model.layers.9.mlp.experts.9.up_proj.weight": "model-00001-of-000001.safetensors",
2144 "model.layers.9.mlp.experts.9.down_proj.weight": "model-00001-of-000001.safetensors",
2145 "model.layers.9.mlp.experts.10.gate_proj.weight": "model-00001-of-000001.safetensors",
2146 "model.layers.9.mlp.experts.10.up_proj.weight": "model-00001-of-000001.safetensors",
2147 "model.layers.9.mlp.experts.10.down_proj.weight": "model-00001-of-000001.safetensors",
2148 "model.layers.9.mlp.experts.11.gate_proj.weight": "model-00001-of-000001.safetensors",
2149 "model.layers.9.mlp.experts.11.up_proj.weight": "model-00001-of-000001.safetensors",
2150 "model.layers.9.mlp.experts.11.down_proj.weight": "model-00001-of-000001.safetensors",
2151 "model.layers.9.mlp.experts.12.gate_proj.weight": "model-00001-of-000001.safetensors",
2152 "model.layers.9.mlp.experts.12.up_proj.weight": "model-00001-of-000001.safetensors",
2153 "model.layers.9.mlp.experts.12.down_proj.weight": "model-00001-of-000001.safetensors",
2154 "model.layers.9.mlp.experts.13.gate_proj.weight": "model-00001-of-000001.safetensors",
2155 "model.layers.9.mlp.experts.13.up_proj.weight": "model-00001-of-000001.safetensors",
2156 "model.layers.9.mlp.experts.13.down_proj.weight": "model-00001-of-000001.safetensors",
2157 "model.layers.9.mlp.experts.14.gate_proj.weight": "model-00001-of-000001.safetensors",
2158 "model.layers.9.mlp.experts.14.up_proj.weight": "model-00001-of-000001.safetensors",
2159 "model.layers.9.mlp.experts.14.down_proj.weight": "model-00001-of-000001.safetensors",
2160 "model.layers.9.mlp.experts.15.gate_proj.weight": "model-00001-of-000001.safetensors",
2161 "model.layers.9.mlp.experts.15.up_proj.weight": "model-00001-of-000001.safetensors",
2162 "model.layers.9.mlp.experts.15.down_proj.weight": "model-00001-of-000001.safetensors",
2163 "model.layers.9.mlp.experts.16.gate_proj.weight": "model-00001-of-000001.safetensors",
2164 "model.layers.9.mlp.experts.16.up_proj.weight": "model-00001-of-000001.safetensors",
2165 "model.layers.9.mlp.experts.16.down_proj.weight": "model-00001-of-000001.safetensors",
2166 "model.layers.9.mlp.experts.17.gate_proj.weight": "model-00001-of-000001.safetensors",
2167 "model.layers.9.mlp.experts.17.up_proj.weight": "model-00001-of-000001.safetensors",
2168 "model.layers.9.mlp.experts.17.down_proj.weight": "model-00001-of-000001.safetensors",
2169 "model.layers.9.mlp.experts.18.gate_proj.weight": "model-00001-of-000001.safetensors",
2170 "model.layers.9.mlp.experts.18.up_proj.weight": "model-00001-of-000001.safetensors",
2171 "model.layers.9.mlp.experts.18.down_proj.weight": "model-00001-of-000001.safetensors",
2172 "model.layers.9.mlp.experts.19.gate_proj.weight": "model-00001-of-000001.safetensors",
2173 "model.layers.9.mlp.experts.19.up_proj.weight": "model-00001-of-000001.safetensors",
2174 "model.layers.9.mlp.experts.19.down_proj.weight": "model-00001-of-000001.safetensors",
2175 "model.layers.9.mlp.experts.20.gate_proj.weight": "model-00001-of-000001.safetensors",
2176 "model.layers.9.mlp.experts.20.up_proj.weight": "model-00001-of-000001.safetensors",
2177 "model.layers.9.mlp.experts.20.down_proj.weight": "model-00001-of-000001.safetensors",
2178 "model.layers.9.mlp.experts.21.gate_proj.weight": "model-00001-of-000001.safetensors",
2179 "model.layers.9.mlp.experts.21.up_proj.weight": "model-00001-of-000001.safetensors",
2180 "model.layers.9.mlp.experts.21.down_proj.weight": "model-00001-of-000001.safetensors",
2181 "model.layers.9.mlp.experts.22.gate_proj.weight": "model-00001-of-000001.safetensors",
2182 "model.layers.9.mlp.experts.22.up_proj.weight": "model-00001-of-000001.safetensors",
2183 "model.layers.9.mlp.experts.22.down_proj.weight": "model-00001-of-000001.safetensors",
2184 "model.layers.9.mlp.experts.23.gate_proj.weight": "model-00001-of-000001.safetensors",
2185 "model.layers.9.mlp.experts.23.up_proj.weight": "model-00001-of-000001.safetensors",
2186 "model.layers.9.mlp.experts.23.down_proj.weight": "model-00001-of-000001.safetensors",
2187 "model.layers.9.mlp.experts.24.gate_proj.weight": "model-00001-of-000001.safetensors",
2188 "model.layers.9.mlp.experts.24.up_proj.weight": "model-00001-of-000001.safetensors",
2189 "model.layers.9.mlp.experts.24.down_proj.weight": "model-00001-of-000001.safetensors",
2190 "model.layers.9.mlp.experts.25.gate_proj.weight": "model-00001-of-000001.safetensors",
2191 "model.layers.9.mlp.experts.25.up_proj.weight": "model-00001-of-000001.safetensors",
2192 "model.layers.9.mlp.experts.25.down_proj.weight": "model-00001-of-000001.safetensors",
2193 "model.layers.9.mlp.experts.26.gate_proj.weight": "model-00001-of-000001.safetensors",
2194 "model.layers.9.mlp.experts.26.up_proj.weight": "model-00001-of-000001.safetensors",
2195 "model.layers.9.mlp.experts.26.down_proj.weight": "model-00001-of-000001.safetensors",
2196 "model.layers.9.mlp.experts.27.gate_proj.weight": "model-00001-of-000001.safetensors",
2197 "model.layers.9.mlp.experts.27.up_proj.weight": "model-00001-of-000001.safetensors",
2198 "model.layers.9.mlp.experts.27.down_proj.weight": "model-00001-of-000001.safetensors",
2199 "model.layers.9.mlp.experts.28.gate_proj.weight": "model-00001-of-000001.safetensors",
2200 "model.layers.9.mlp.experts.28.up_proj.weight": "model-00001-of-000001.safetensors",
2201 "model.layers.9.mlp.experts.28.down_proj.weight": "model-00001-of-000001.safetensors",
2202 "model.layers.9.mlp.experts.29.gate_proj.weight": "model-00001-of-000001.safetensors",
2203 "model.layers.9.mlp.experts.29.up_proj.weight": "model-00001-of-000001.safetensors",
2204 "model.layers.9.mlp.experts.29.down_proj.weight": "model-00001-of-000001.safetensors",
2205 "model.layers.9.mlp.experts.30.gate_proj.weight": "model-00001-of-000001.safetensors",
2206 "model.layers.9.mlp.experts.30.up_proj.weight": "model-00001-of-000001.safetensors",
2207 "model.layers.9.mlp.experts.30.down_proj.weight": "model-00001-of-000001.safetensors",
2208 "model.layers.9.mlp.experts.31.gate_proj.weight": "model-00001-of-000001.safetensors",
2209 "model.layers.9.mlp.experts.31.up_proj.weight": "model-00001-of-000001.safetensors",
2210 "model.layers.9.mlp.experts.31.down_proj.weight": "model-00001-of-000001.safetensors",
2211 "model.layers.9.mlp.experts.32.gate_proj.weight": "model-00001-of-000001.safetensors",
2212 "model.layers.9.mlp.experts.32.up_proj.weight": "model-00001-of-000001.safetensors",
2213 "model.layers.9.mlp.experts.32.down_proj.weight": "model-00001-of-000001.safetensors",
2214 "model.layers.9.mlp.experts.33.gate_proj.weight": "model-00001-of-000001.safetensors",
2215 "model.layers.9.mlp.experts.33.up_proj.weight": "model-00001-of-000001.safetensors",
2216 "model.layers.9.mlp.experts.33.down_proj.weight": "model-00001-of-000001.safetensors",
2217 "model.layers.9.mlp.experts.34.gate_proj.weight": "model-00001-of-000001.safetensors",
2218 "model.layers.9.mlp.experts.34.up_proj.weight": "model-00001-of-000001.safetensors",
2219 "model.layers.9.mlp.experts.34.down_proj.weight": "model-00001-of-000001.safetensors",
2220 "model.layers.9.mlp.experts.35.gate_proj.weight": "model-00001-of-000001.safetensors",
2221 "model.layers.9.mlp.experts.35.up_proj.weight": "model-00001-of-000001.safetensors",
2222 "model.layers.9.mlp.experts.35.down_proj.weight": "model-00001-of-000001.safetensors",
2223 "model.layers.9.mlp.experts.36.gate_proj.weight": "model-00001-of-000001.safetensors",
2224 "model.layers.9.mlp.experts.36.up_proj.weight": "model-00001-of-000001.safetensors",
2225 "model.layers.9.mlp.experts.36.down_proj.weight": "model-00001-of-000001.safetensors",
2226 "model.layers.9.mlp.experts.37.gate_proj.weight": "model-00001-of-000001.safetensors",
2227 "model.layers.9.mlp.experts.37.up_proj.weight": "model-00001-of-000001.safetensors",
2228 "model.layers.9.mlp.experts.37.down_proj.weight": "model-00001-of-000001.safetensors",
2229 "model.layers.9.mlp.experts.38.gate_proj.weight": "model-00001-of-000001.safetensors",
2230 "model.layers.9.mlp.experts.38.up_proj.weight": "model-00001-of-000001.safetensors",
2231 "model.layers.9.mlp.experts.38.down_proj.weight": "model-00001-of-000001.safetensors",
2232 "model.layers.9.mlp.experts.39.gate_proj.weight": "model-00001-of-000001.safetensors",
2233 "model.layers.9.mlp.experts.39.up_proj.weight": "model-00001-of-000001.safetensors",
2234 "model.layers.9.mlp.experts.39.down_proj.weight": "model-00001-of-000001.safetensors",
2235 "model.layers.9.mlp.experts.40.gate_proj.weight": "model-00001-of-000001.safetensors",
2236 "model.layers.9.mlp.experts.40.up_proj.weight": "model-00001-of-000001.safetensors",
2237 "model.layers.9.mlp.experts.40.down_proj.weight": "model-00001-of-000001.safetensors",
2238 "model.layers.9.mlp.experts.41.gate_proj.weight": "model-00001-of-000001.safetensors",
2239 "model.layers.9.mlp.experts.41.up_proj.weight": "model-00001-of-000001.safetensors",
2240 "model.layers.9.mlp.experts.41.down_proj.weight": "model-00001-of-000001.safetensors",
2241 "model.layers.9.mlp.experts.42.gate_proj.weight": "model-00001-of-000001.safetensors",
2242 "model.layers.9.mlp.experts.42.up_proj.weight": "model-00001-of-000001.safetensors",
2243 "model.layers.9.mlp.experts.42.down_proj.weight": "model-00001-of-000001.safetensors",
2244 "model.layers.9.mlp.experts.43.gate_proj.weight": "model-00001-of-000001.safetensors",
2245 "model.layers.9.mlp.experts.43.up_proj.weight": "model-00001-of-000001.safetensors",
2246 "model.layers.9.mlp.experts.43.down_proj.weight": "model-00001-of-000001.safetensors",
2247 "model.layers.9.mlp.experts.44.gate_proj.weight": "model-00001-of-000001.safetensors",
2248 "model.layers.9.mlp.experts.44.up_proj.weight": "model-00001-of-000001.safetensors",
2249 "model.layers.9.mlp.experts.44.down_proj.weight": "model-00001-of-000001.safetensors",
2250 "model.layers.9.mlp.experts.45.gate_proj.weight": "model-00001-of-000001.safetensors",
2251 "model.layers.9.mlp.experts.45.up_proj.weight": "model-00001-of-000001.safetensors",
2252 "model.layers.9.mlp.experts.45.down_proj.weight": "model-00001-of-000001.safetensors",
2253 "model.layers.9.mlp.experts.46.gate_proj.weight": "model-00001-of-000001.safetensors",
2254 "model.layers.9.mlp.experts.46.up_proj.weight": "model-00001-of-000001.safetensors",
2255 "model.layers.9.mlp.experts.46.down_proj.weight": "model-00001-of-000001.safetensors",
2256 "model.layers.9.mlp.experts.47.gate_proj.weight": "model-00001-of-000001.safetensors",
2257 "model.layers.9.mlp.experts.47.up_proj.weight": "model-00001-of-000001.safetensors",
2258 "model.layers.9.mlp.experts.47.down_proj.weight": "model-00001-of-000001.safetensors",
2259 "model.layers.9.mlp.experts.48.gate_proj.weight": "model-00001-of-000001.safetensors",
2260 "model.layers.9.mlp.experts.48.up_proj.weight": "model-00001-of-000001.safetensors",
2261 "model.layers.9.mlp.experts.48.down_proj.weight": "model-00001-of-000001.safetensors",
2262 "model.layers.9.mlp.experts.49.gate_proj.weight": "model-00001-of-000001.safetensors",
2263 "model.layers.9.mlp.experts.49.up_proj.weight": "model-00001-of-000001.safetensors",
2264 "model.layers.9.mlp.experts.49.down_proj.weight": "model-00001-of-000001.safetensors",
2265 "model.layers.9.mlp.experts.50.gate_proj.weight": "model-00001-of-000001.safetensors",
2266 "model.layers.9.mlp.experts.50.up_proj.weight": "model-00001-of-000001.safetensors",
2267 "model.layers.9.mlp.experts.50.down_proj.weight": "model-00001-of-000001.safetensors",
2268 "model.layers.9.mlp.experts.51.gate_proj.weight": "model-00001-of-000001.safetensors",
2269 "model.layers.9.mlp.experts.51.up_proj.weight": "model-00001-of-000001.safetensors",
2270 "model.layers.9.mlp.experts.51.down_proj.weight": "model-00001-of-000001.safetensors",
2271 "model.layers.9.mlp.experts.52.gate_proj.weight": "model-00001-of-000001.safetensors",
2272 "model.layers.9.mlp.experts.52.up_proj.weight": "model-00001-of-000001.safetensors",
2273 "model.layers.9.mlp.experts.52.down_proj.weight": "model-00001-of-000001.safetensors",
2274 "model.layers.9.mlp.experts.53.gate_proj.weight": "model-00001-of-000001.safetensors",
2275 "model.layers.9.mlp.experts.53.up_proj.weight": "model-00001-of-000001.safetensors",
2276 "model.layers.9.mlp.experts.53.down_proj.weight": "model-00001-of-000001.safetensors",
2277 "model.layers.9.mlp.experts.54.gate_proj.weight": "model-00001-of-000001.safetensors",
2278 "model.layers.9.mlp.experts.54.up_proj.weight": "model-00001-of-000001.safetensors",
2279 "model.layers.9.mlp.experts.54.down_proj.weight": "model-00001-of-000001.safetensors",
2280 "model.layers.9.mlp.experts.55.gate_proj.weight": "model-00001-of-000001.safetensors",
2281 "model.layers.9.mlp.experts.55.up_proj.weight": "model-00001-of-000001.safetensors",
2282 "model.layers.9.mlp.experts.55.down_proj.weight": "model-00001-of-000001.safetensors",
2283 "model.layers.9.mlp.experts.56.gate_proj.weight": "model-00001-of-000001.safetensors",
2284 "model.layers.9.mlp.experts.56.up_proj.weight": "model-00001-of-000001.safetensors",
2285 "model.layers.9.mlp.experts.56.down_proj.weight": "model-00001-of-000001.safetensors",
2286 "model.layers.9.mlp.experts.57.gate_proj.weight": "model-00001-of-000001.safetensors",
2287 "model.layers.9.mlp.experts.57.up_proj.weight": "model-00001-of-000001.safetensors",
2288 "model.layers.9.mlp.experts.57.down_proj.weight": "model-00001-of-000001.safetensors",
2289 "model.layers.9.mlp.experts.58.gate_proj.weight": "model-00001-of-000001.safetensors",
2290 "model.layers.9.mlp.experts.58.up_proj.weight": "model-00001-of-000001.safetensors",
2291 "model.layers.9.mlp.experts.58.down_proj.weight": "model-00001-of-000001.safetensors",
2292 "model.layers.9.mlp.experts.59.gate_proj.weight": "model-00001-of-000001.safetensors",
2293 "model.layers.9.mlp.experts.59.up_proj.weight": "model-00001-of-000001.safetensors",
2294 "model.layers.9.mlp.experts.59.down_proj.weight": "model-00001-of-000001.safetensors",
2295 "model.layers.9.mlp.experts.60.gate_proj.weight": "model-00001-of-000001.safetensors",
2296 "model.layers.9.mlp.experts.60.up_proj.weight": "model-00001-of-000001.safetensors",
2297 "model.layers.9.mlp.experts.60.down_proj.weight": "model-00001-of-000001.safetensors",
2298 "model.layers.9.mlp.experts.61.gate_proj.weight": "model-00001-of-000001.safetensors",
2299 "model.layers.9.mlp.experts.61.up_proj.weight": "model-00001-of-000001.safetensors",
2300 "model.layers.9.mlp.experts.61.down_proj.weight": "model-00001-of-000001.safetensors",
2301 "model.layers.9.mlp.experts.62.gate_proj.weight": "model-00001-of-000001.safetensors",
2302 "model.layers.9.mlp.experts.62.up_proj.weight": "model-00001-of-000001.safetensors",
2303 "model.layers.9.mlp.experts.62.down_proj.weight": "model-00001-of-000001.safetensors",
2304 "model.layers.9.mlp.experts.63.gate_proj.weight": "model-00001-of-000001.safetensors",
2305 "model.layers.9.mlp.experts.63.up_proj.weight": "model-00001-of-000001.safetensors",
2306 "model.layers.9.mlp.experts.63.down_proj.weight": "model-00001-of-000001.safetensors",
2307 "model.layers.9.input_layernorm.weight": "model-00001-of-000001.safetensors",
2308 "model.layers.9.post_attention_layernorm.weight": "model-00001-of-000001.safetensors",
2309 "model.layers.10.self_attn.q_proj.weight": "model-00001-of-000001.safetensors",
2310 "model.layers.10.self_attn.k_proj.weight": "model-00001-of-000001.safetensors",
2311 "model.layers.10.self_attn.v_proj.weight": "model-00001-of-000001.safetensors",
2312 "model.layers.10.self_attn.o_proj.weight": "model-00001-of-000001.safetensors",
2313 "model.layers.10.mlp.gate.weight": "model-00001-of-000001.safetensors",
2314 "model.layers.10.mlp.shared_experts.gate_proj.weight": "model-00001-of-000001.safetensors",
2315 "model.layers.10.mlp.shared_experts.up_proj.weight": "model-00001-of-000001.safetensors",
2316 "model.layers.10.mlp.shared_experts.down_proj.weight": "model-00001-of-000001.safetensors",
2317 "model.layers.10.mlp.experts.0.gate_proj.weight": "model-00001-of-000001.safetensors",
2318 "model.layers.10.mlp.experts.0.up_proj.weight": "model-00001-of-000001.safetensors",
2319 "model.layers.10.mlp.experts.0.down_proj.weight": "model-00001-of-000001.safetensors",
2320 "model.layers.10.mlp.experts.1.gate_proj.weight": "model-00001-of-000001.safetensors",
2321 "model.layers.10.mlp.experts.1.up_proj.weight": "model-00001-of-000001.safetensors",
2322 "model.layers.10.mlp.experts.1.down_proj.weight": "model-00001-of-000001.safetensors",
2323 "model.layers.10.mlp.experts.2.gate_proj.weight": "model-00001-of-000001.safetensors",
2324 "model.layers.10.mlp.experts.2.up_proj.weight": "model-00001-of-000001.safetensors",
2325 "model.layers.10.mlp.experts.2.down_proj.weight": "model-00001-of-000001.safetensors",
2326 "model.layers.10.mlp.experts.3.gate_proj.weight": "model-00001-of-000001.safetensors",
2327 "model.layers.10.mlp.experts.3.up_proj.weight": "model-00001-of-000001.safetensors",
2328 "model.layers.10.mlp.experts.3.down_proj.weight": "model-00001-of-000001.safetensors",
2329 "model.layers.10.mlp.experts.4.gate_proj.weight": "model-00001-of-000001.safetensors",
2330 "model.layers.10.mlp.experts.4.up_proj.weight": "model-00001-of-000001.safetensors",
2331 "model.layers.10.mlp.experts.4.down_proj.weight": "model-00001-of-000001.safetensors",
2332 "model.layers.10.mlp.experts.5.gate_proj.weight": "model-00001-of-000001.safetensors",
2333 "model.layers.10.mlp.experts.5.up_proj.weight": "model-00001-of-000001.safetensors",
2334 "model.layers.10.mlp.experts.5.down_proj.weight": "model-00001-of-000001.safetensors",
2335 "model.layers.10.mlp.experts.6.gate_proj.weight": "model-00001-of-000001.safetensors",
2336 "model.layers.10.mlp.experts.6.up_proj.weight": "model-00001-of-000001.safetensors",
2337 "model.layers.10.mlp.experts.6.down_proj.weight": "model-00001-of-000001.safetensors",
2338 "model.layers.10.mlp.experts.7.gate_proj.weight": "model-00001-of-000001.safetensors",
2339 "model.layers.10.mlp.experts.7.up_proj.weight": "model-00001-of-000001.safetensors",
2340 "model.layers.10.mlp.experts.7.down_proj.weight": "model-00001-of-000001.safetensors",
2341 "model.layers.10.mlp.experts.8.gate_proj.weight": "model-00001-of-000001.safetensors",
2342 "model.layers.10.mlp.experts.8.up_proj.weight": "model-00001-of-000001.safetensors",
2343 "model.layers.10.mlp.experts.8.down_proj.weight": "model-00001-of-000001.safetensors",
2344 "model.layers.10.mlp.experts.9.gate_proj.weight": "model-00001-of-000001.safetensors",
2345 "model.layers.10.mlp.experts.9.up_proj.weight": "model-00001-of-000001.safetensors",
2346 "model.layers.10.mlp.experts.9.down_proj.weight": "model-00001-of-000001.safetensors",
2347 "model.layers.10.mlp.experts.10.gate_proj.weight": "model-00001-of-000001.safetensors",
2348 "model.layers.10.mlp.experts.10.up_proj.weight": "model-00001-of-000001.safetensors",
2349 "model.layers.10.mlp.experts.10.down_proj.weight": "model-00001-of-000001.safetensors",
2350 "model.layers.10.mlp.experts.11.gate_proj.weight": "model-00001-of-000001.safetensors",
2351 "model.layers.10.mlp.experts.11.up_proj.weight": "model-00001-of-000001.safetensors",
2352 "model.layers.10.mlp.experts.11.down_proj.weight": "model-00001-of-000001.safetensors",
2353 "model.layers.10.mlp.experts.12.gate_proj.weight": "model-00001-of-000001.safetensors",
2354 "model.layers.10.mlp.experts.12.up_proj.weight": "model-00001-of-000001.safetensors",
2355 "model.layers.10.mlp.experts.12.down_proj.weight": "model-00001-of-000001.safetensors",
2356 "model.layers.10.mlp.experts.13.gate_proj.weight": "model-00001-of-000001.safetensors",
2357 "model.layers.10.mlp.experts.13.up_proj.weight": "model-00001-of-000001.safetensors",
2358 "model.layers.10.mlp.experts.13.down_proj.weight": "model-00001-of-000001.safetensors",
2359 "model.layers.10.mlp.experts.14.gate_proj.weight": "model-00001-of-000001.safetensors",
2360 "model.layers.10.mlp.experts.14.up_proj.weight": "model-00001-of-000001.safetensors",
2361 "model.layers.10.mlp.experts.14.down_proj.weight": "model-00001-of-000001.safetensors",
2362 "model.layers.10.mlp.experts.15.gate_proj.weight": "model-00001-of-000001.safetensors",
2363 "model.layers.10.mlp.experts.15.up_proj.weight": "model-00001-of-000001.safetensors",
2364 "model.layers.10.mlp.experts.15.down_proj.weight": "model-00001-of-000001.safetensors",
2365 "model.layers.10.mlp.experts.16.gate_proj.weight": "model-00001-of-000001.safetensors",
2366 "model.layers.10.mlp.experts.16.up_proj.weight": "model-00001-of-000001.safetensors",
2367 "model.layers.10.mlp.experts.16.down_proj.weight": "model-00001-of-000001.safetensors",
2368 "model.layers.10.mlp.experts.17.gate_proj.weight": "model-00001-of-000001.safetensors",
2369 "model.layers.10.mlp.experts.17.up_proj.weight": "model-00001-of-000001.safetensors",
2370 "model.layers.10.mlp.experts.17.down_proj.weight": "model-00001-of-000001.safetensors",
2371 "model.layers.10.mlp.experts.18.gate_proj.weight": "model-00001-of-000001.safetensors",
2372 "model.layers.10.mlp.experts.18.up_proj.weight": "model-00001-of-000001.safetensors",
2373 "model.layers.10.mlp.experts.18.down_proj.weight": "model-00001-of-000001.safetensors",
2374 "model.layers.10.mlp.experts.19.gate_proj.weight": "model-00001-of-000001.safetensors",
2375 "model.layers.10.mlp.experts.19.up_proj.weight": "model-00001-of-000001.safetensors",
2376 "model.layers.10.mlp.experts.19.down_proj.weight": "model-00001-of-000001.safetensors",
2377 "model.layers.10.mlp.experts.20.gate_proj.weight": "model-00001-of-000001.safetensors",
2378 "model.layers.10.mlp.experts.20.up_proj.weight": "model-00001-of-000001.safetensors",
2379 "model.layers.10.mlp.experts.20.down_proj.weight": "model-00001-of-000001.safetensors",
2380 "model.layers.10.mlp.experts.21.gate_proj.weight": "model-00001-of-000001.safetensors",
2381 "model.layers.10.mlp.experts.21.up_proj.weight": "model-00001-of-000001.safetensors",
2382 "model.layers.10.mlp.experts.21.down_proj.weight": "model-00001-of-000001.safetensors",
2383 "model.layers.10.mlp.experts.22.gate_proj.weight": "model-00001-of-000001.safetensors",
2384 "model.layers.10.mlp.experts.22.up_proj.weight": "model-00001-of-000001.safetensors",
2385 "model.layers.10.mlp.experts.22.down_proj.weight": "model-00001-of-000001.safetensors",
2386 "model.layers.10.mlp.experts.23.gate_proj.weight": "model-00001-of-000001.safetensors",
2387 "model.layers.10.mlp.experts.23.up_proj.weight": "model-00001-of-000001.safetensors",
2388 "model.layers.10.mlp.experts.23.down_proj.weight": "model-00001-of-000001.safetensors",
2389 "model.layers.10.mlp.experts.24.gate_proj.weight": "model-00001-of-000001.safetensors",
2390 "model.layers.10.mlp.experts.24.up_proj.weight": "model-00001-of-000001.safetensors",
2391 "model.layers.10.mlp.experts.24.down_proj.weight": "model-00001-of-000001.safetensors",
2392 "model.layers.10.mlp.experts.25.gate_proj.weight": "model-00001-of-000001.safetensors",
2393 "model.layers.10.mlp.experts.25.up_proj.weight": "model-00001-of-000001.safetensors",
2394 "model.layers.10.mlp.experts.25.down_proj.weight": "model-00001-of-000001.safetensors",
2395 "model.layers.10.mlp.experts.26.gate_proj.weight": "model-00001-of-000001.safetensors",
2396 "model.layers.10.mlp.experts.26.up_proj.weight": "model-00001-of-000001.safetensors",
2397 "model.layers.10.mlp.experts.26.down_proj.weight": "model-00001-of-000001.safetensors",
2398 "model.layers.10.mlp.experts.27.gate_proj.weight": "model-00001-of-000001.safetensors",
2399 "model.layers.10.mlp.experts.27.up_proj.weight": "model-00001-of-000001.safetensors",
2400 "model.layers.10.mlp.experts.27.down_proj.weight": "model-00001-of-000001.safetensors",
2401 "model.layers.10.mlp.experts.28.gate_proj.weight": "model-00001-of-000001.safetensors",
2402 "model.layers.10.mlp.experts.28.up_proj.weight": "model-00001-of-000001.safetensors",
2403 "model.layers.10.mlp.experts.28.down_proj.weight": "model-00001-of-000001.safetensors",
2404 "model.layers.10.mlp.experts.29.gate_proj.weight": "model-00001-of-000001.safetensors",
2405 "model.layers.10.mlp.experts.29.up_proj.weight": "model-00001-of-000001.safetensors",
2406 "model.layers.10.mlp.experts.29.down_proj.weight": "model-00001-of-000001.safetensors",
2407 "model.layers.10.mlp.experts.30.gate_proj.weight": "model-00001-of-000001.safetensors",
2408 "model.layers.10.mlp.experts.30.up_proj.weight": "model-00001-of-000001.safetensors",
2409 "model.layers.10.mlp.experts.30.down_proj.weight": "model-00001-of-000001.safetensors",
2410 "model.layers.10.mlp.experts.31.gate_proj.weight": "model-00001-of-000001.safetensors",
2411 "model.layers.10.mlp.experts.31.up_proj.weight": "model-00001-of-000001.safetensors",
2412 "model.layers.10.mlp.experts.31.down_proj.weight": "model-00001-of-000001.safetensors",
2413 "model.layers.10.mlp.experts.32.gate_proj.weight": "model-00001-of-000001.safetensors",
2414 "model.layers.10.mlp.experts.32.up_proj.weight": "model-00001-of-000001.safetensors",
2415 "model.layers.10.mlp.experts.32.down_proj.weight": "model-00001-of-000001.safetensors",
2416 "model.layers.10.mlp.experts.33.gate_proj.weight": "model-00001-of-000001.safetensors",
2417 "model.layers.10.mlp.experts.33.up_proj.weight": "model-00001-of-000001.safetensors",
2418 "model.layers.10.mlp.experts.33.down_proj.weight": "model-00001-of-000001.safetensors",
2419 "model.layers.10.mlp.experts.34.gate_proj.weight": "model-00001-of-000001.safetensors",
2420 "model.layers.10.mlp.experts.34.up_proj.weight": "model-00001-of-000001.safetensors",
2421 "model.layers.10.mlp.experts.34.down_proj.weight": "model-00001-of-000001.safetensors",
2422 "model.layers.10.mlp.experts.35.gate_proj.weight": "model-00001-of-000001.safetensors",
2423 "model.layers.10.mlp.experts.35.up_proj.weight": "model-00001-of-000001.safetensors",
2424 "model.layers.10.mlp.experts.35.down_proj.weight": "model-00001-of-000001.safetensors",
2425 "model.layers.10.mlp.experts.36.gate_proj.weight": "model-00001-of-000001.safetensors",
2426 "model.layers.10.mlp.experts.36.up_proj.weight": "model-00001-of-000001.safetensors",
2427 "model.layers.10.mlp.experts.36.down_proj.weight": "model-00001-of-000001.safetensors",
2428 "model.layers.10.mlp.experts.37.gate_proj.weight": "model-00001-of-000001.safetensors",
2429 "model.layers.10.mlp.experts.37.up_proj.weight": "model-00001-of-000001.safetensors",
2430 "model.layers.10.mlp.experts.37.down_proj.weight": "model-00001-of-000001.safetensors",
2431 "model.layers.10.mlp.experts.38.gate_proj.weight": "model-00001-of-000001.safetensors",
2432 "model.layers.10.mlp.experts.38.up_proj.weight": "model-00001-of-000001.safetensors",
2433 "model.layers.10.mlp.experts.38.down_proj.weight": "model-00001-of-000001.safetensors",
2434 "model.layers.10.mlp.experts.39.gate_proj.weight": "model-00001-of-000001.safetensors",
2435 "model.layers.10.mlp.experts.39.up_proj.weight": "model-00001-of-000001.safetensors",
2436 "model.layers.10.mlp.experts.39.down_proj.weight": "model-00001-of-000001.safetensors",
2437 "model.layers.10.mlp.experts.40.gate_proj.weight": "model-00001-of-000001.safetensors",
2438 "model.layers.10.mlp.experts.40.up_proj.weight": "model-00001-of-000001.safetensors",
2439 "model.layers.10.mlp.experts.40.down_proj.weight": "model-00001-of-000001.safetensors",
2440 "model.layers.10.mlp.experts.41.gate_proj.weight": "model-00001-of-000001.safetensors",
2441 "model.layers.10.mlp.experts.41.up_proj.weight": "model-00001-of-000001.safetensors",
2442 "model.layers.10.mlp.experts.41.down_proj.weight": "model-00001-of-000001.safetensors",
2443 "model.layers.10.mlp.experts.42.gate_proj.weight": "model-00001-of-000001.safetensors",
2444 "model.layers.10.mlp.experts.42.up_proj.weight": "model-00001-of-000001.safetensors",
2445 "model.layers.10.mlp.experts.42.down_proj.weight": "model-00001-of-000001.safetensors",
2446 "model.layers.10.mlp.experts.43.gate_proj.weight": "model-00001-of-000001.safetensors",
2447 "model.layers.10.mlp.experts.43.up_proj.weight": "model-00001-of-000001.safetensors",
2448 "model.layers.10.mlp.experts.43.down_proj.weight": "model-00001-of-000001.safetensors",
2449 "model.layers.10.mlp.experts.44.gate_proj.weight": "model-00001-of-000001.safetensors",
2450 "model.layers.10.mlp.experts.44.up_proj.weight": "model-00001-of-000001.safetensors",
2451 "model.layers.10.mlp.experts.44.down_proj.weight": "model-00001-of-000001.safetensors",
2452 "model.layers.10.mlp.experts.45.gate_proj.weight": "model-00001-of-000001.safetensors",
2453 "model.layers.10.mlp.experts.45.up_proj.weight": "model-00001-of-000001.safetensors",
2454 "model.layers.10.mlp.experts.45.down_proj.weight": "model-00001-of-000001.safetensors",
2455 "model.layers.10.mlp.experts.46.gate_proj.weight": "model-00001-of-000001.safetensors",
2456 "model.layers.10.mlp.experts.46.up_proj.weight": "model-00001-of-000001.safetensors",
2457 "model.layers.10.mlp.experts.46.down_proj.weight": "model-00001-of-000001.safetensors",
2458 "model.layers.10.mlp.experts.47.gate_proj.weight": "model-00001-of-000001.safetensors",
2459 "model.layers.10.mlp.experts.47.up_proj.weight": "model-00001-of-000001.safetensors",
2460 "model.layers.10.mlp.experts.47.down_proj.weight": "model-00001-of-000001.safetensors",
2461 "model.layers.10.mlp.experts.48.gate_proj.weight": "model-00001-of-000001.safetensors",
2462 "model.layers.10.mlp.experts.48.up_proj.weight": "model-00001-of-000001.safetensors",
2463 "model.layers.10.mlp.experts.48.down_proj.weight": "model-00001-of-000001.safetensors",
2464 "model.layers.10.mlp.experts.49.gate_proj.weight": "model-00001-of-000001.safetensors",
2465 "model.layers.10.mlp.experts.49.up_proj.weight": "model-00001-of-000001.safetensors",
2466 "model.layers.10.mlp.experts.49.down_proj.weight": "model-00001-of-000001.safetensors",
2467 "model.layers.10.mlp.experts.50.gate_proj.weight": "model-00001-of-000001.safetensors",
2468 "model.layers.10.mlp.experts.50.up_proj.weight": "model-00001-of-000001.safetensors",
2469 "model.layers.10.mlp.experts.50.down_proj.weight": "model-00001-of-000001.safetensors",
2470 "model.layers.10.mlp.experts.51.gate_proj.weight": "model-00001-of-000001.safetensors",
2471 "model.layers.10.mlp.experts.51.up_proj.weight": "model-00001-of-000001.safetensors",
2472 "model.layers.10.mlp.experts.51.down_proj.weight": "model-00001-of-000001.safetensors",
2473 "model.layers.10.mlp.experts.52.gate_proj.weight": "model-00001-of-000001.safetensors",
2474 "model.layers.10.mlp.experts.52.up_proj.weight": "model-00001-of-000001.safetensors",
2475 "model.layers.10.mlp.experts.52.down_proj.weight": "model-00001-of-000001.safetensors",
2476 "model.layers.10.mlp.experts.53.gate_proj.weight": "model-00001-of-000001.safetensors",
2477 "model.layers.10.mlp.experts.53.up_proj.weight": "model-00001-of-000001.safetensors",
2478 "model.layers.10.mlp.experts.53.down_proj.weight": "model-00001-of-000001.safetensors",
2479 "model.layers.10.mlp.experts.54.gate_proj.weight": "model-00001-of-000001.safetensors",
2480 "model.layers.10.mlp.experts.54.up_proj.weight": "model-00001-of-000001.safetensors",
2481 "model.layers.10.mlp.experts.54.down_proj.weight": "model-00001-of-000001.safetensors",
2482 "model.layers.10.mlp.experts.55.gate_proj.weight": "model-00001-of-000001.safetensors",
2483 "model.layers.10.mlp.experts.55.up_proj.weight": "model-00001-of-000001.safetensors",
2484 "model.layers.10.mlp.experts.55.down_proj.weight": "model-00001-of-000001.safetensors",
2485 "model.layers.10.mlp.experts.56.gate_proj.weight": "model-00001-of-000001.safetensors",
2486 "model.layers.10.mlp.experts.56.up_proj.weight": "model-00001-of-000001.safetensors",
2487 "model.layers.10.mlp.experts.56.down_proj.weight": "model-00001-of-000001.safetensors",
2488 "model.layers.10.mlp.experts.57.gate_proj.weight": "model-00001-of-000001.safetensors",
2489 "model.layers.10.mlp.experts.57.up_proj.weight": "model-00001-of-000001.safetensors",
2490 "model.layers.10.mlp.experts.57.down_proj.weight": "model-00001-of-000001.safetensors",
2491 "model.layers.10.mlp.experts.58.gate_proj.weight": "model-00001-of-000001.safetensors",
2492 "model.layers.10.mlp.experts.58.up_proj.weight": "model-00001-of-000001.safetensors",
2493 "model.layers.10.mlp.experts.58.down_proj.weight": "model-00001-of-000001.safetensors",
2494 "model.layers.10.mlp.experts.59.gate_proj.weight": "model-00001-of-000001.safetensors",
2495 "model.layers.10.mlp.experts.59.up_proj.weight": "model-00001-of-000001.safetensors",
2496 "model.layers.10.mlp.experts.59.down_proj.weight": "model-00001-of-000001.safetensors",
2497 "model.layers.10.mlp.experts.60.gate_proj.weight": "model-00001-of-000001.safetensors",
2498 "model.layers.10.mlp.experts.60.up_proj.weight": "model-00001-of-000001.safetensors",
2499 "model.layers.10.mlp.experts.60.down_proj.weight": "model-00001-of-000001.safetensors",
2500 "model.layers.10.mlp.experts.61.gate_proj.weight": "model-00001-of-000001.safetensors",
2501 "model.layers.10.mlp.experts.61.up_proj.weight": "model-00001-of-000001.safetensors",
2502 "model.layers.10.mlp.experts.61.down_proj.weight": "model-00001-of-000001.safetensors",
2503 "model.layers.10.mlp.experts.62.gate_proj.weight": "model-00001-of-000001.safetensors",
2504 "model.layers.10.mlp.experts.62.up_proj.weight": "model-00001-of-000001.safetensors",
2505 "model.layers.10.mlp.experts.62.down_proj.weight": "model-00001-of-000001.safetensors",
2506 "model.layers.10.mlp.experts.63.gate_proj.weight": "model-00001-of-000001.safetensors",
2507 "model.layers.10.mlp.experts.63.up_proj.weight": "model-00001-of-000001.safetensors",
2508 "model.layers.10.mlp.experts.63.down_proj.weight": "model-00001-of-000001.safetensors",
2509 "model.layers.10.input_layernorm.weight": "model-00001-of-000001.safetensors",
2510 "model.layers.10.post_attention_layernorm.weight": "model-00001-of-000001.safetensors",
2511 "model.layers.11.self_attn.q_proj.weight": "model-00001-of-000001.safetensors",
2512 "model.layers.11.self_attn.k_proj.weight": "model-00001-of-000001.safetensors",
2513 "model.layers.11.self_attn.v_proj.weight": "model-00001-of-000001.safetensors",
2514 "model.layers.11.self_attn.o_proj.weight": "model-00001-of-000001.safetensors",
2515 "model.layers.11.mlp.gate.weight": "model-00001-of-000001.safetensors",
2516 "model.layers.11.mlp.shared_experts.gate_proj.weight": "model-00001-of-000001.safetensors",
2517 "model.layers.11.mlp.shared_experts.up_proj.weight": "model-00001-of-000001.safetensors",
2518 "model.layers.11.mlp.shared_experts.down_proj.weight": "model-00001-of-000001.safetensors",
2519 "model.layers.11.mlp.experts.0.gate_proj.weight": "model-00001-of-000001.safetensors",
2520 "model.layers.11.mlp.experts.0.up_proj.weight": "model-00001-of-000001.safetensors",
2521 "model.layers.11.mlp.experts.0.down_proj.weight": "model-00001-of-000001.safetensors",
2522 "model.layers.11.mlp.experts.1.gate_proj.weight": "model-00001-of-000001.safetensors",
2523 "model.layers.11.mlp.experts.1.up_proj.weight": "model-00001-of-000001.safetensors",
2524 "model.layers.11.mlp.experts.1.down_proj.weight": "model-00001-of-000001.safetensors",
2525 "model.layers.11.mlp.experts.2.gate_proj.weight": "model-00001-of-000001.safetensors",
2526 "model.layers.11.mlp.experts.2.up_proj.weight": "model-00001-of-000001.safetensors",
2527 "model.layers.11.mlp.experts.2.down_proj.weight": "model-00001-of-000001.safetensors",
2528 "model.layers.11.mlp.experts.3.gate_proj.weight": "model-00001-of-000001.safetensors",
2529 "model.layers.11.mlp.experts.3.up_proj.weight": "model-00001-of-000001.safetensors",
2530 "model.layers.11.mlp.experts.3.down_proj.weight": "model-00001-of-000001.safetensors",
2531 "model.layers.11.mlp.experts.4.gate_proj.weight": "model-00001-of-000001.safetensors",
2532 "model.layers.11.mlp.experts.4.up_proj.weight": "model-00001-of-000001.safetensors",
2533 "model.layers.11.mlp.experts.4.down_proj.weight": "model-00001-of-000001.safetensors",
2534 "model.layers.11.mlp.experts.5.gate_proj.weight": "model-00001-of-000001.safetensors",
2535 "model.layers.11.mlp.experts.5.up_proj.weight": "model-00001-of-000001.safetensors",
2536 "model.layers.11.mlp.experts.5.down_proj.weight": "model-00001-of-000001.safetensors",
2537 "model.layers.11.mlp.experts.6.gate_proj.weight": "model-00001-of-000001.safetensors",
2538 "model.layers.11.mlp.experts.6.up_proj.weight": "model-00001-of-000001.safetensors",
2539 "model.layers.11.mlp.experts.6.down_proj.weight": "model-00001-of-000001.safetensors",
2540 "model.layers.11.mlp.experts.7.gate_proj.weight": "model-00001-of-000001.safetensors",
2541 "model.layers.11.mlp.experts.7.up_proj.weight": "model-00001-of-000001.safetensors",
2542 "model.layers.11.mlp.experts.7.down_proj.weight": "model-00001-of-000001.safetensors",
2543 "model.layers.11.mlp.experts.8.gate_proj.weight": "model-00001-of-000001.safetensors",
2544 "model.layers.11.mlp.experts.8.up_proj.weight": "model-00001-of-000001.safetensors",
2545 "model.layers.11.mlp.experts.8.down_proj.weight": "model-00001-of-000001.safetensors",
2546 "model.layers.11.mlp.experts.9.gate_proj.weight": "model-00001-of-000001.safetensors",
2547 "model.layers.11.mlp.experts.9.up_proj.weight": "model-00001-of-000001.safetensors",
2548 "model.layers.11.mlp.experts.9.down_proj.weight": "model-00001-of-000001.safetensors",
2549 "model.layers.11.mlp.experts.10.gate_proj.weight": "model-00001-of-000001.safetensors",
2550 "model.layers.11.mlp.experts.10.up_proj.weight": "model-00001-of-000001.safetensors",
2551 "model.layers.11.mlp.experts.10.down_proj.weight": "model-00001-of-000001.safetensors",
2552 "model.layers.11.mlp.experts.11.gate_proj.weight": "model-00001-of-000001.safetensors",
2553 "model.layers.11.mlp.experts.11.up_proj.weight": "model-00001-of-000001.safetensors",
2554 "model.layers.11.mlp.experts.11.down_proj.weight": "model-00001-of-000001.safetensors",
2555 "model.layers.11.mlp.experts.12.gate_proj.weight": "model-00001-of-000001.safetensors",
2556 "model.layers.11.mlp.experts.12.up_proj.weight": "model-00001-of-000001.safetensors",
2557 "model.layers.11.mlp.experts.12.down_proj.weight": "model-00001-of-000001.safetensors",
2558 "model.layers.11.mlp.experts.13.gate_proj.weight": "model-00001-of-000001.safetensors",
2559 "model.layers.11.mlp.experts.13.up_proj.weight": "model-00001-of-000001.safetensors",
2560 "model.layers.11.mlp.experts.13.down_proj.weight": "model-00001-of-000001.safetensors",
2561 "model.layers.11.mlp.experts.14.gate_proj.weight": "model-00001-of-000001.safetensors",
2562 "model.layers.11.mlp.experts.14.up_proj.weight": "model-00001-of-000001.safetensors",
2563 "model.layers.11.mlp.experts.14.down_proj.weight": "model-00001-of-000001.safetensors",
2564 "model.layers.11.mlp.experts.15.gate_proj.weight": "model-00001-of-000001.safetensors",
2565 "model.layers.11.mlp.experts.15.up_proj.weight": "model-00001-of-000001.safetensors",
2566 "model.layers.11.mlp.experts.15.down_proj.weight": "model-00001-of-000001.safetensors",
2567 "model.layers.11.mlp.experts.16.gate_proj.weight": "model-00001-of-000001.safetensors",
2568 "model.layers.11.mlp.experts.16.up_proj.weight": "model-00001-of-000001.safetensors",
2569 "model.layers.11.mlp.experts.16.down_proj.weight": "model-00001-of-000001.safetensors",
2570 "model.layers.11.mlp.experts.17.gate_proj.weight": "model-00001-of-000001.safetensors",
2571 "model.layers.11.mlp.experts.17.up_proj.weight": "model-00001-of-000001.safetensors",
2572 "model.layers.11.mlp.experts.17.down_proj.weight": "model-00001-of-000001.safetensors",
2573 "model.layers.11.mlp.experts.18.gate_proj.weight": "model-00001-of-000001.safetensors",
2574 "model.layers.11.mlp.experts.18.up_proj.weight": "model-00001-of-000001.safetensors",
2575 "model.layers.11.mlp.experts.18.down_proj.weight": "model-00001-of-000001.safetensors",
2576 "model.layers.11.mlp.experts.19.gate_proj.weight": "model-00001-of-000001.safetensors",
2577 "model.layers.11.mlp.experts.19.up_proj.weight": "model-00001-of-000001.safetensors",
2578 "model.layers.11.mlp.experts.19.down_proj.weight": "model-00001-of-000001.safetensors",
2579 "model.layers.11.mlp.experts.20.gate_proj.weight": "model-00001-of-000001.safetensors",
2580 "model.layers.11.mlp.experts.20.up_proj.weight": "model-00001-of-000001.safetensors",
2581 "model.layers.11.mlp.experts.20.down_proj.weight": "model-00001-of-000001.safetensors",
2582 "model.layers.11.mlp.experts.21.gate_proj.weight": "model-00001-of-000001.safetensors",
2583 "model.layers.11.mlp.experts.21.up_proj.weight": "model-00001-of-000001.safetensors",
2584 "model.layers.11.mlp.experts.21.down_proj.weight": "model-00001-of-000001.safetensors",
2585 "model.layers.11.mlp.experts.22.gate_proj.weight": "model-00001-of-000001.safetensors",
2586 "model.layers.11.mlp.experts.22.up_proj.weight": "model-00001-of-000001.safetensors",
2587 "model.layers.11.mlp.experts.22.down_proj.weight": "model-00001-of-000001.safetensors",
2588 "model.layers.11.mlp.experts.23.gate_proj.weight": "model-00001-of-000001.safetensors",
2589 "model.layers.11.mlp.experts.23.up_proj.weight": "model-00001-of-000001.safetensors",
2590 "model.layers.11.mlp.experts.23.down_proj.weight": "model-00001-of-000001.safetensors",
2591 "model.layers.11.mlp.experts.24.gate_proj.weight": "model-00001-of-000001.safetensors",
2592 "model.layers.11.mlp.experts.24.up_proj.weight": "model-00001-of-000001.safetensors",
2593 "model.layers.11.mlp.experts.24.down_proj.weight": "model-00001-of-000001.safetensors",
2594 "model.layers.11.mlp.experts.25.gate_proj.weight": "model-00001-of-000001.safetensors",
2595 "model.layers.11.mlp.experts.25.up_proj.weight": "model-00001-of-000001.safetensors",
2596 "model.layers.11.mlp.experts.25.down_proj.weight": "model-00001-of-000001.safetensors",
2597 "model.layers.11.mlp.experts.26.gate_proj.weight": "model-00001-of-000001.safetensors",
2598 "model.layers.11.mlp.experts.26.up_proj.weight": "model-00001-of-000001.safetensors",
2599 "model.layers.11.mlp.experts.26.down_proj.weight": "model-00001-of-000001.safetensors",
2600 "model.layers.11.mlp.experts.27.gate_proj.weight": "model-00001-of-000001.safetensors",
2601 "model.layers.11.mlp.experts.27.up_proj.weight": "model-00001-of-000001.safetensors",
2602 "model.layers.11.mlp.experts.27.down_proj.weight": "model-00001-of-000001.safetensors",
2603 "model.layers.11.mlp.experts.28.gate_proj.weight": "model-00001-of-000001.safetensors",
2604 "model.layers.11.mlp.experts.28.up_proj.weight": "model-00001-of-000001.safetensors",
2605 "model.layers.11.mlp.experts.28.down_proj.weight": "model-00001-of-000001.safetensors",
2606 "model.layers.11.mlp.experts.29.gate_proj.weight": "model-00001-of-000001.safetensors",
2607 "model.layers.11.mlp.experts.29.up_proj.weight": "model-00001-of-000001.safetensors",
2608 "model.layers.11.mlp.experts.29.down_proj.weight": "model-00001-of-000001.safetensors",
2609 "model.layers.11.mlp.experts.30.gate_proj.weight": "model-00001-of-000001.safetensors",
2610 "model.layers.11.mlp.experts.30.up_proj.weight": "model-00001-of-000001.safetensors",
2611 "model.layers.11.mlp.experts.30.down_proj.weight": "model-00001-of-000001.safetensors",
2612 "model.layers.11.mlp.experts.31.gate_proj.weight": "model-00001-of-000001.safetensors",
2613 "model.layers.11.mlp.experts.31.up_proj.weight": "model-00001-of-000001.safetensors",
2614 "model.layers.11.mlp.experts.31.down_proj.weight": "model-00001-of-000001.safetensors",
2615 "model.layers.11.mlp.experts.32.gate_proj.weight": "model-00001-of-000001.safetensors",
2616 "model.layers.11.mlp.experts.32.up_proj.weight": "model-00001-of-000001.safetensors",
2617 "model.layers.11.mlp.experts.32.down_proj.weight": "model-00001-of-000001.safetensors",
2618 "model.layers.11.mlp.experts.33.gate_proj.weight": "model-00001-of-000001.safetensors",
2619 "model.layers.11.mlp.experts.33.up_proj.weight": "model-00001-of-000001.safetensors",
2620 "model.layers.11.mlp.experts.33.down_proj.weight": "model-00001-of-000001.safetensors",
2621 "model.layers.11.mlp.experts.34.gate_proj.weight": "model-00001-of-000001.safetensors",
2622 "model.layers.11.mlp.experts.34.up_proj.weight": "model-00001-of-000001.safetensors",
2623 "model.layers.11.mlp.experts.34.down_proj.weight": "model-00001-of-000001.safetensors",
2624 "model.layers.11.mlp.experts.35.gate_proj.weight": "model-00001-of-000001.safetensors",
2625 "model.layers.11.mlp.experts.35.up_proj.weight": "model-00001-of-000001.safetensors",
2626 "model.layers.11.mlp.experts.35.down_proj.weight": "model-00001-of-000001.safetensors",
2627 "model.layers.11.mlp.experts.36.gate_proj.weight": "model-00001-of-000001.safetensors",
2628 "model.layers.11.mlp.experts.36.up_proj.weight": "model-00001-of-000001.safetensors",
2629 "model.layers.11.mlp.experts.36.down_proj.weight": "model-00001-of-000001.safetensors",
2630 "model.layers.11.mlp.experts.37.gate_proj.weight": "model-00001-of-000001.safetensors",
2631 "model.layers.11.mlp.experts.37.up_proj.weight": "model-00001-of-000001.safetensors",
2632 "model.layers.11.mlp.experts.37.down_proj.weight": "model-00001-of-000001.safetensors",
2633 "model.layers.11.mlp.experts.38.gate_proj.weight": "model-00001-of-000001.safetensors",
2634 "model.layers.11.mlp.experts.38.up_proj.weight": "model-00001-of-000001.safetensors",
2635 "model.layers.11.mlp.experts.38.down_proj.weight": "model-00001-of-000001.safetensors",
2636 "model.layers.11.mlp.experts.39.gate_proj.weight": "model-00001-of-000001.safetensors",
2637 "model.layers.11.mlp.experts.39.up_proj.weight": "model-00001-of-000001.safetensors",
2638 "model.layers.11.mlp.experts.39.down_proj.weight": "model-00001-of-000001.safetensors",
2639 "model.layers.11.mlp.experts.40.gate_proj.weight": "model-00001-of-000001.safetensors",
2640 "model.layers.11.mlp.experts.40.up_proj.weight": "model-00001-of-000001.safetensors",
2641 "model.layers.11.mlp.experts.40.down_proj.weight": "model-00001-of-000001.safetensors",
2642 "model.layers.11.mlp.experts.41.gate_proj.weight": "model-00001-of-000001.safetensors",
2643 "model.layers.11.mlp.experts.41.up_proj.weight": "model-00001-of-000001.safetensors",
2644 "model.layers.11.mlp.experts.41.down_proj.weight": "model-00001-of-000001.safetensors",
2645 "model.layers.11.mlp.experts.42.gate_proj.weight": "model-00001-of-000001.safetensors",
2646 "model.layers.11.mlp.experts.42.up_proj.weight": "model-00001-of-000001.safetensors",
2647 "model.layers.11.mlp.experts.42.down_proj.weight": "model-00001-of-000001.safetensors",
2648 "model.layers.11.mlp.experts.43.gate_proj.weight": "model-00001-of-000001.safetensors",
2649 "model.layers.11.mlp.experts.43.up_proj.weight": "model-00001-of-000001.safetensors",
2650 "model.layers.11.mlp.experts.43.down_proj.weight": "model-00001-of-000001.safetensors",
2651 "model.layers.11.mlp.experts.44.gate_proj.weight": "model-00001-of-000001.safetensors",
2652 "model.layers.11.mlp.experts.44.up_proj.weight": "model-00001-of-000001.safetensors",
2653 "model.layers.11.mlp.experts.44.down_proj.weight": "model-00001-of-000001.safetensors",
2654 "model.layers.11.mlp.experts.45.gate_proj.weight": "model-00001-of-000001.safetensors",
2655 "model.layers.11.mlp.experts.45.up_proj.weight": "model-00001-of-000001.safetensors",
2656 "model.layers.11.mlp.experts.45.down_proj.weight": "model-00001-of-000001.safetensors",
2657 "model.layers.11.mlp.experts.46.gate_proj.weight": "model-00001-of-000001.safetensors",
2658 "model.layers.11.mlp.experts.46.up_proj.weight": "model-00001-of-000001.safetensors",
2659 "model.layers.11.mlp.experts.46.down_proj.weight": "model-00001-of-000001.safetensors",
2660 "model.layers.11.mlp.experts.47.gate_proj.weight": "model-00001-of-000001.safetensors",
2661 "model.layers.11.mlp.experts.47.up_proj.weight": "model-00001-of-000001.safetensors",
2662 "model.layers.11.mlp.experts.47.down_proj.weight": "model-00001-of-000001.safetensors",
2663 "model.layers.11.mlp.experts.48.gate_proj.weight": "model-00001-of-000001.safetensors",
2664 "model.layers.11.mlp.experts.48.up_proj.weight": "model-00001-of-000001.safetensors",
2665 "model.layers.11.mlp.experts.48.down_proj.weight": "model-00001-of-000001.safetensors",
2666 "model.layers.11.mlp.experts.49.gate_proj.weight": "model-00001-of-000001.safetensors",
2667 "model.layers.11.mlp.experts.49.up_proj.weight": "model-00001-of-000001.safetensors",
2668 "model.layers.11.mlp.experts.49.down_proj.weight": "model-00001-of-000001.safetensors",
2669 "model.layers.11.mlp.experts.50.gate_proj.weight": "model-00001-of-000001.safetensors",
2670 "model.layers.11.mlp.experts.50.up_proj.weight": "model-00001-of-000001.safetensors",
2671 "model.layers.11.mlp.experts.50.down_proj.weight": "model-00001-of-000001.safetensors",
2672 "model.layers.11.mlp.experts.51.gate_proj.weight": "model-00001-of-000001.safetensors",
2673 "model.layers.11.mlp.experts.51.up_proj.weight": "model-00001-of-000001.safetensors",
2674 "model.layers.11.mlp.experts.51.down_proj.weight": "model-00001-of-000001.safetensors",
2675 "model.layers.11.mlp.experts.52.gate_proj.weight": "model-00001-of-000001.safetensors",
2676 "model.layers.11.mlp.experts.52.up_proj.weight": "model-00001-of-000001.safetensors",
2677 "model.layers.11.mlp.experts.52.down_proj.weight": "model-00001-of-000001.safetensors",
2678 "model.layers.11.mlp.experts.53.gate_proj.weight": "model-00001-of-000001.safetensors",
2679 "model.layers.11.mlp.experts.53.up_proj.weight": "model-00001-of-000001.safetensors",
2680 "model.layers.11.mlp.experts.53.down_proj.weight": "model-00001-of-000001.safetensors",
2681 "model.layers.11.mlp.experts.54.gate_proj.weight": "model-00001-of-000001.safetensors",
2682 "model.layers.11.mlp.experts.54.up_proj.weight": "model-00001-of-000001.safetensors",
2683 "model.layers.11.mlp.experts.54.down_proj.weight": "model-00001-of-000001.safetensors",
2684 "model.layers.11.mlp.experts.55.gate_proj.weight": "model-00001-of-000001.safetensors",
2685 "model.layers.11.mlp.experts.55.up_proj.weight": "model-00001-of-000001.safetensors",
2686 "model.layers.11.mlp.experts.55.down_proj.weight": "model-00001-of-000001.safetensors",
2687 "model.layers.11.mlp.experts.56.gate_proj.weight": "model-00001-of-000001.safetensors",
2688 "model.layers.11.mlp.experts.56.up_proj.weight": "model-00001-of-000001.safetensors",
2689 "model.layers.11.mlp.experts.56.down_proj.weight": "model-00001-of-000001.safetensors",
2690 "model.layers.11.mlp.experts.57.gate_proj.weight": "model-00001-of-000001.safetensors",
2691 "model.layers.11.mlp.experts.57.up_proj.weight": "model-00001-of-000001.safetensors",
2692 "model.layers.11.mlp.experts.57.down_proj.weight": "model-00001-of-000001.safetensors",
2693 "model.layers.11.mlp.experts.58.gate_proj.weight": "model-00001-of-000001.safetensors",
2694 "model.layers.11.mlp.experts.58.up_proj.weight": "model-00001-of-000001.safetensors",
2695 "model.layers.11.mlp.experts.58.down_proj.weight": "model-00001-of-000001.safetensors",
2696 "model.layers.11.mlp.experts.59.gate_proj.weight": "model-00001-of-000001.safetensors",
2697 "model.layers.11.mlp.experts.59.up_proj.weight": "model-00001-of-000001.safetensors",
2698 "model.layers.11.mlp.experts.59.down_proj.weight": "model-00001-of-000001.safetensors",
2699 "model.layers.11.mlp.experts.60.gate_proj.weight": "model-00001-of-000001.safetensors",
2700 "model.layers.11.mlp.experts.60.up_proj.weight": "model-00001-of-000001.safetensors",
2701 "model.layers.11.mlp.experts.60.down_proj.weight": "model-00001-of-000001.safetensors",
2702 "model.layers.11.mlp.experts.61.gate_proj.weight": "model-00001-of-000001.safetensors",
2703 "model.layers.11.mlp.experts.61.up_proj.weight": "model-00001-of-000001.safetensors",
2704 "model.layers.11.mlp.experts.61.down_proj.weight": "model-00001-of-000001.safetensors",
2705 "model.layers.11.mlp.experts.62.gate_proj.weight": "model-00001-of-000001.safetensors",
2706 "model.layers.11.mlp.experts.62.up_proj.weight": "model-00001-of-000001.safetensors",
2707 "model.layers.11.mlp.experts.62.down_proj.weight": "model-00001-of-000001.safetensors",
2708 "model.layers.11.mlp.experts.63.gate_proj.weight": "model-00001-of-000001.safetensors",
2709 "model.layers.11.mlp.experts.63.up_proj.weight": "model-00001-of-000001.safetensors",
2710 "model.layers.11.mlp.experts.63.down_proj.weight": "model-00001-of-000001.safetensors",
2711 "model.layers.11.input_layernorm.weight": "model-00001-of-000001.safetensors",
2712 "model.layers.11.post_attention_layernorm.weight": "model-00001-of-000001.safetensors"
2713 }
2714 }