model.safetensors.index.json
57.0 KB · 715 lines · json Raw
1 {
2 "metadata": {
3 "total_size": 65524246528
4 },
5 "weight_map": {
6 "lm_head.weight": "model-00017-of-00017.safetensors",
7 "model.embed_tokens.weight": "model-00001-of-00017.safetensors",
8 "model.layers.0.input_layernorm.weight": "model-00001-of-00017.safetensors",
9 "model.layers.0.mlp.down_proj.weight": "model-00001-of-00017.safetensors",
10 "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00017.safetensors",
11 "model.layers.0.mlp.up_proj.weight": "model-00001-of-00017.safetensors",
12 "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00017.safetensors",
13 "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00017.safetensors",
14 "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00017.safetensors",
15 "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00017.safetensors",
16 "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00017.safetensors",
17 "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00017.safetensors",
18 "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00017.safetensors",
19 "model.layers.1.input_layernorm.weight": "model-00001-of-00017.safetensors",
20 "model.layers.1.mlp.down_proj.weight": "model-00001-of-00017.safetensors",
21 "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00017.safetensors",
22 "model.layers.1.mlp.up_proj.weight": "model-00001-of-00017.safetensors",
23 "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00017.safetensors",
24 "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00017.safetensors",
25 "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00017.safetensors",
26 "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00017.safetensors",
27 "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00017.safetensors",
28 "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00017.safetensors",
29 "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00017.safetensors",
30 "model.layers.10.input_layernorm.weight": "model-00004-of-00017.safetensors",
31 "model.layers.10.mlp.down_proj.weight": "model-00004-of-00017.safetensors",
32 "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00017.safetensors",
33 "model.layers.10.mlp.up_proj.weight": "model-00004-of-00017.safetensors",
34 "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00017.safetensors",
35 "model.layers.10.self_attn.k_norm.weight": "model-00003-of-00017.safetensors",
36 "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00017.safetensors",
37 "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00017.safetensors",
38 "model.layers.10.self_attn.q_norm.weight": "model-00003-of-00017.safetensors",
39 "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00017.safetensors",
40 "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00017.safetensors",
41 "model.layers.11.input_layernorm.weight": "model-00004-of-00017.safetensors",
42 "model.layers.11.mlp.down_proj.weight": "model-00004-of-00017.safetensors",
43 "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00017.safetensors",
44 "model.layers.11.mlp.up_proj.weight": "model-00004-of-00017.safetensors",
45 "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00017.safetensors",
46 "model.layers.11.self_attn.k_norm.weight": "model-00004-of-00017.safetensors",
47 "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00017.safetensors",
48 "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00017.safetensors",
49 "model.layers.11.self_attn.q_norm.weight": "model-00004-of-00017.safetensors",
50 "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00017.safetensors",
51 "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00017.safetensors",
52 "model.layers.12.input_layernorm.weight": "model-00004-of-00017.safetensors",
53 "model.layers.12.mlp.down_proj.weight": "model-00004-of-00017.safetensors",
54 "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00017.safetensors",
55 "model.layers.12.mlp.up_proj.weight": "model-00004-of-00017.safetensors",
56 "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00017.safetensors",
57 "model.layers.12.self_attn.k_norm.weight": "model-00004-of-00017.safetensors",
58 "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00017.safetensors",
59 "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00017.safetensors",
60 "model.layers.12.self_attn.q_norm.weight": "model-00004-of-00017.safetensors",
61 "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00017.safetensors",
62 "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00017.safetensors",
63 "model.layers.13.input_layernorm.weight": "model-00004-of-00017.safetensors",
64 "model.layers.13.mlp.down_proj.weight": "model-00004-of-00017.safetensors",
65 "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00017.safetensors",
66 "model.layers.13.mlp.up_proj.weight": "model-00004-of-00017.safetensors",
67 "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00017.safetensors",
68 "model.layers.13.self_attn.k_norm.weight": "model-00004-of-00017.safetensors",
69 "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00017.safetensors",
70 "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00017.safetensors",
71 "model.layers.13.self_attn.q_norm.weight": "model-00004-of-00017.safetensors",
72 "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00017.safetensors",
73 "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00017.safetensors",
74 "model.layers.14.input_layernorm.weight": "model-00005-of-00017.safetensors",
75 "model.layers.14.mlp.down_proj.weight": "model-00005-of-00017.safetensors",
76 "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00017.safetensors",
77 "model.layers.14.mlp.up_proj.weight": "model-00005-of-00017.safetensors",
78 "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00017.safetensors",
79 "model.layers.14.self_attn.k_norm.weight": "model-00004-of-00017.safetensors",
80 "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00017.safetensors",
81 "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00017.safetensors",
82 "model.layers.14.self_attn.q_norm.weight": "model-00004-of-00017.safetensors",
83 "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00017.safetensors",
84 "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00017.safetensors",
85 "model.layers.15.input_layernorm.weight": "model-00005-of-00017.safetensors",
86 "model.layers.15.mlp.down_proj.weight": "model-00005-of-00017.safetensors",
87 "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00017.safetensors",
88 "model.layers.15.mlp.up_proj.weight": "model-00005-of-00017.safetensors",
89 "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00017.safetensors",
90 "model.layers.15.self_attn.k_norm.weight": "model-00005-of-00017.safetensors",
91 "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00017.safetensors",
92 "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00017.safetensors",
93 "model.layers.15.self_attn.q_norm.weight": "model-00005-of-00017.safetensors",
94 "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00017.safetensors",
95 "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00017.safetensors",
96 "model.layers.16.input_layernorm.weight": "model-00005-of-00017.safetensors",
97 "model.layers.16.mlp.down_proj.weight": "model-00005-of-00017.safetensors",
98 "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00017.safetensors",
99 "model.layers.16.mlp.up_proj.weight": "model-00005-of-00017.safetensors",
100 "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00017.safetensors",
101 "model.layers.16.self_attn.k_norm.weight": "model-00005-of-00017.safetensors",
102 "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00017.safetensors",
103 "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00017.safetensors",
104 "model.layers.16.self_attn.q_norm.weight": "model-00005-of-00017.safetensors",
105 "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00017.safetensors",
106 "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00017.safetensors",
107 "model.layers.17.input_layernorm.weight": "model-00005-of-00017.safetensors",
108 "model.layers.17.mlp.down_proj.weight": "model-00005-of-00017.safetensors",
109 "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00017.safetensors",
110 "model.layers.17.mlp.up_proj.weight": "model-00005-of-00017.safetensors",
111 "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00017.safetensors",
112 "model.layers.17.self_attn.k_norm.weight": "model-00005-of-00017.safetensors",
113 "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00017.safetensors",
114 "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00017.safetensors",
115 "model.layers.17.self_attn.q_norm.weight": "model-00005-of-00017.safetensors",
116 "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00017.safetensors",
117 "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00017.safetensors",
118 "model.layers.18.input_layernorm.weight": "model-00006-of-00017.safetensors",
119 "model.layers.18.mlp.down_proj.weight": "model-00006-of-00017.safetensors",
120 "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00017.safetensors",
121 "model.layers.18.mlp.up_proj.weight": "model-00006-of-00017.safetensors",
122 "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00017.safetensors",
123 "model.layers.18.self_attn.k_norm.weight": "model-00005-of-00017.safetensors",
124 "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00017.safetensors",
125 "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00017.safetensors",
126 "model.layers.18.self_attn.q_norm.weight": "model-00005-of-00017.safetensors",
127 "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00017.safetensors",
128 "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00017.safetensors",
129 "model.layers.19.input_layernorm.weight": "model-00006-of-00017.safetensors",
130 "model.layers.19.mlp.down_proj.weight": "model-00006-of-00017.safetensors",
131 "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00017.safetensors",
132 "model.layers.19.mlp.up_proj.weight": "model-00006-of-00017.safetensors",
133 "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00017.safetensors",
134 "model.layers.19.self_attn.k_norm.weight": "model-00006-of-00017.safetensors",
135 "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00017.safetensors",
136 "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00017.safetensors",
137 "model.layers.19.self_attn.q_norm.weight": "model-00006-of-00017.safetensors",
138 "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00017.safetensors",
139 "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00017.safetensors",
140 "model.layers.2.input_layernorm.weight": "model-00002-of-00017.safetensors",
141 "model.layers.2.mlp.down_proj.weight": "model-00002-of-00017.safetensors",
142 "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00017.safetensors",
143 "model.layers.2.mlp.up_proj.weight": "model-00002-of-00017.safetensors",
144 "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
145 "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00017.safetensors",
146 "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00017.safetensors",
147 "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00017.safetensors",
148 "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00017.safetensors",
149 "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00017.safetensors",
150 "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00017.safetensors",
151 "model.layers.20.input_layernorm.weight": "model-00006-of-00017.safetensors",
152 "model.layers.20.mlp.down_proj.weight": "model-00006-of-00017.safetensors",
153 "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00017.safetensors",
154 "model.layers.20.mlp.up_proj.weight": "model-00006-of-00017.safetensors",
155 "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00017.safetensors",
156 "model.layers.20.self_attn.k_norm.weight": "model-00006-of-00017.safetensors",
157 "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00017.safetensors",
158 "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00017.safetensors",
159 "model.layers.20.self_attn.q_norm.weight": "model-00006-of-00017.safetensors",
160 "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00017.safetensors",
161 "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00017.safetensors",
162 "model.layers.21.input_layernorm.weight": "model-00006-of-00017.safetensors",
163 "model.layers.21.mlp.down_proj.weight": "model-00006-of-00017.safetensors",
164 "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00017.safetensors",
165 "model.layers.21.mlp.up_proj.weight": "model-00006-of-00017.safetensors",
166 "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00017.safetensors",
167 "model.layers.21.self_attn.k_norm.weight": "model-00006-of-00017.safetensors",
168 "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00017.safetensors",
169 "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00017.safetensors",
170 "model.layers.21.self_attn.q_norm.weight": "model-00006-of-00017.safetensors",
171 "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00017.safetensors",
172 "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00017.safetensors",
173 "model.layers.22.input_layernorm.weight": "model-00007-of-00017.safetensors",
174 "model.layers.22.mlp.down_proj.weight": "model-00007-of-00017.safetensors",
175 "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00017.safetensors",
176 "model.layers.22.mlp.up_proj.weight": "model-00007-of-00017.safetensors",
177 "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00017.safetensors",
178 "model.layers.22.self_attn.k_norm.weight": "model-00006-of-00017.safetensors",
179 "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00017.safetensors",
180 "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00017.safetensors",
181 "model.layers.22.self_attn.q_norm.weight": "model-00006-of-00017.safetensors",
182 "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00017.safetensors",
183 "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00017.safetensors",
184 "model.layers.23.input_layernorm.weight": "model-00007-of-00017.safetensors",
185 "model.layers.23.mlp.down_proj.weight": "model-00007-of-00017.safetensors",
186 "model.layers.23.mlp.gate_proj.weight": "model-00007-of-00017.safetensors",
187 "model.layers.23.mlp.up_proj.weight": "model-00007-of-00017.safetensors",
188 "model.layers.23.post_attention_layernorm.weight": "model-00007-of-00017.safetensors",
189 "model.layers.23.self_attn.k_norm.weight": "model-00007-of-00017.safetensors",
190 "model.layers.23.self_attn.k_proj.weight": "model-00007-of-00017.safetensors",
191 "model.layers.23.self_attn.o_proj.weight": "model-00007-of-00017.safetensors",
192 "model.layers.23.self_attn.q_norm.weight": "model-00007-of-00017.safetensors",
193 "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00017.safetensors",
194 "model.layers.23.self_attn.v_proj.weight": "model-00007-of-00017.safetensors",
195 "model.layers.24.input_layernorm.weight": "model-00007-of-00017.safetensors",
196 "model.layers.24.mlp.down_proj.weight": "model-00007-of-00017.safetensors",
197 "model.layers.24.mlp.gate_proj.weight": "model-00007-of-00017.safetensors",
198 "model.layers.24.mlp.up_proj.weight": "model-00007-of-00017.safetensors",
199 "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00017.safetensors",
200 "model.layers.24.self_attn.k_norm.weight": "model-00007-of-00017.safetensors",
201 "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00017.safetensors",
202 "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00017.safetensors",
203 "model.layers.24.self_attn.q_norm.weight": "model-00007-of-00017.safetensors",
204 "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00017.safetensors",
205 "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00017.safetensors",
206 "model.layers.25.input_layernorm.weight": "model-00007-of-00017.safetensors",
207 "model.layers.25.mlp.down_proj.weight": "model-00007-of-00017.safetensors",
208 "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00017.safetensors",
209 "model.layers.25.mlp.up_proj.weight": "model-00007-of-00017.safetensors",
210 "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00017.safetensors",
211 "model.layers.25.self_attn.k_norm.weight": "model-00007-of-00017.safetensors",
212 "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00017.safetensors",
213 "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00017.safetensors",
214 "model.layers.25.self_attn.q_norm.weight": "model-00007-of-00017.safetensors",
215 "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00017.safetensors",
216 "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00017.safetensors",
217 "model.layers.26.input_layernorm.weight": "model-00008-of-00017.safetensors",
218 "model.layers.26.mlp.down_proj.weight": "model-00008-of-00017.safetensors",
219 "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00017.safetensors",
220 "model.layers.26.mlp.up_proj.weight": "model-00008-of-00017.safetensors",
221 "model.layers.26.post_attention_layernorm.weight": "model-00008-of-00017.safetensors",
222 "model.layers.26.self_attn.k_norm.weight": "model-00007-of-00017.safetensors",
223 "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00017.safetensors",
224 "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00017.safetensors",
225 "model.layers.26.self_attn.q_norm.weight": "model-00007-of-00017.safetensors",
226 "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00017.safetensors",
227 "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00017.safetensors",
228 "model.layers.27.input_layernorm.weight": "model-00008-of-00017.safetensors",
229 "model.layers.27.mlp.down_proj.weight": "model-00008-of-00017.safetensors",
230 "model.layers.27.mlp.gate_proj.weight": "model-00008-of-00017.safetensors",
231 "model.layers.27.mlp.up_proj.weight": "model-00008-of-00017.safetensors",
232 "model.layers.27.post_attention_layernorm.weight": "model-00008-of-00017.safetensors",
233 "model.layers.27.self_attn.k_norm.weight": "model-00008-of-00017.safetensors",
234 "model.layers.27.self_attn.k_proj.weight": "model-00008-of-00017.safetensors",
235 "model.layers.27.self_attn.o_proj.weight": "model-00008-of-00017.safetensors",
236 "model.layers.27.self_attn.q_norm.weight": "model-00008-of-00017.safetensors",
237 "model.layers.27.self_attn.q_proj.weight": "model-00008-of-00017.safetensors",
238 "model.layers.27.self_attn.v_proj.weight": "model-00008-of-00017.safetensors",
239 "model.layers.28.input_layernorm.weight": "model-00008-of-00017.safetensors",
240 "model.layers.28.mlp.down_proj.weight": "model-00008-of-00017.safetensors",
241 "model.layers.28.mlp.gate_proj.weight": "model-00008-of-00017.safetensors",
242 "model.layers.28.mlp.up_proj.weight": "model-00008-of-00017.safetensors",
243 "model.layers.28.post_attention_layernorm.weight": "model-00008-of-00017.safetensors",
244 "model.layers.28.self_attn.k_norm.weight": "model-00008-of-00017.safetensors",
245 "model.layers.28.self_attn.k_proj.weight": "model-00008-of-00017.safetensors",
246 "model.layers.28.self_attn.o_proj.weight": "model-00008-of-00017.safetensors",
247 "model.layers.28.self_attn.q_norm.weight": "model-00008-of-00017.safetensors",
248 "model.layers.28.self_attn.q_proj.weight": "model-00008-of-00017.safetensors",
249 "model.layers.28.self_attn.v_proj.weight": "model-00008-of-00017.safetensors",
250 "model.layers.29.input_layernorm.weight": "model-00008-of-00017.safetensors",
251 "model.layers.29.mlp.down_proj.weight": "model-00008-of-00017.safetensors",
252 "model.layers.29.mlp.gate_proj.weight": "model-00008-of-00017.safetensors",
253 "model.layers.29.mlp.up_proj.weight": "model-00008-of-00017.safetensors",
254 "model.layers.29.post_attention_layernorm.weight": "model-00008-of-00017.safetensors",
255 "model.layers.29.self_attn.k_norm.weight": "model-00008-of-00017.safetensors",
256 "model.layers.29.self_attn.k_proj.weight": "model-00008-of-00017.safetensors",
257 "model.layers.29.self_attn.o_proj.weight": "model-00008-of-00017.safetensors",
258 "model.layers.29.self_attn.q_norm.weight": "model-00008-of-00017.safetensors",
259 "model.layers.29.self_attn.q_proj.weight": "model-00008-of-00017.safetensors",
260 "model.layers.29.self_attn.v_proj.weight": "model-00008-of-00017.safetensors",
261 "model.layers.3.input_layernorm.weight": "model-00002-of-00017.safetensors",
262 "model.layers.3.mlp.down_proj.weight": "model-00002-of-00017.safetensors",
263 "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00017.safetensors",
264 "model.layers.3.mlp.up_proj.weight": "model-00002-of-00017.safetensors",
265 "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
266 "model.layers.3.self_attn.k_norm.weight": "model-00002-of-00017.safetensors",
267 "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
268 "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
269 "model.layers.3.self_attn.q_norm.weight": "model-00002-of-00017.safetensors",
270 "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
271 "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
272 "model.layers.30.input_layernorm.weight": "model-00009-of-00017.safetensors",
273 "model.layers.30.mlp.down_proj.weight": "model-00009-of-00017.safetensors",
274 "model.layers.30.mlp.gate_proj.weight": "model-00008-of-00017.safetensors",
275 "model.layers.30.mlp.up_proj.weight": "model-00009-of-00017.safetensors",
276 "model.layers.30.post_attention_layernorm.weight": "model-00009-of-00017.safetensors",
277 "model.layers.30.self_attn.k_norm.weight": "model-00008-of-00017.safetensors",
278 "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00017.safetensors",
279 "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00017.safetensors",
280 "model.layers.30.self_attn.q_norm.weight": "model-00008-of-00017.safetensors",
281 "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00017.safetensors",
282 "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00017.safetensors",
283 "model.layers.31.input_layernorm.weight": "model-00009-of-00017.safetensors",
284 "model.layers.31.mlp.down_proj.weight": "model-00009-of-00017.safetensors",
285 "model.layers.31.mlp.gate_proj.weight": "model-00009-of-00017.safetensors",
286 "model.layers.31.mlp.up_proj.weight": "model-00009-of-00017.safetensors",
287 "model.layers.31.post_attention_layernorm.weight": "model-00009-of-00017.safetensors",
288 "model.layers.31.self_attn.k_norm.weight": "model-00009-of-00017.safetensors",
289 "model.layers.31.self_attn.k_proj.weight": "model-00009-of-00017.safetensors",
290 "model.layers.31.self_attn.o_proj.weight": "model-00009-of-00017.safetensors",
291 "model.layers.31.self_attn.q_norm.weight": "model-00009-of-00017.safetensors",
292 "model.layers.31.self_attn.q_proj.weight": "model-00009-of-00017.safetensors",
293 "model.layers.31.self_attn.v_proj.weight": "model-00009-of-00017.safetensors",
294 "model.layers.32.input_layernorm.weight": "model-00009-of-00017.safetensors",
295 "model.layers.32.mlp.down_proj.weight": "model-00009-of-00017.safetensors",
296 "model.layers.32.mlp.gate_proj.weight": "model-00009-of-00017.safetensors",
297 "model.layers.32.mlp.up_proj.weight": "model-00009-of-00017.safetensors",
298 "model.layers.32.post_attention_layernorm.weight": "model-00009-of-00017.safetensors",
299 "model.layers.32.self_attn.k_norm.weight": "model-00009-of-00017.safetensors",
300 "model.layers.32.self_attn.k_proj.weight": "model-00009-of-00017.safetensors",
301 "model.layers.32.self_attn.o_proj.weight": "model-00009-of-00017.safetensors",
302 "model.layers.32.self_attn.q_norm.weight": "model-00009-of-00017.safetensors",
303 "model.layers.32.self_attn.q_proj.weight": "model-00009-of-00017.safetensors",
304 "model.layers.32.self_attn.v_proj.weight": "model-00009-of-00017.safetensors",
305 "model.layers.33.input_layernorm.weight": "model-00009-of-00017.safetensors",
306 "model.layers.33.mlp.down_proj.weight": "model-00009-of-00017.safetensors",
307 "model.layers.33.mlp.gate_proj.weight": "model-00009-of-00017.safetensors",
308 "model.layers.33.mlp.up_proj.weight": "model-00009-of-00017.safetensors",
309 "model.layers.33.post_attention_layernorm.weight": "model-00009-of-00017.safetensors",
310 "model.layers.33.self_attn.k_norm.weight": "model-00009-of-00017.safetensors",
311 "model.layers.33.self_attn.k_proj.weight": "model-00009-of-00017.safetensors",
312 "model.layers.33.self_attn.o_proj.weight": "model-00009-of-00017.safetensors",
313 "model.layers.33.self_attn.q_norm.weight": "model-00009-of-00017.safetensors",
314 "model.layers.33.self_attn.q_proj.weight": "model-00009-of-00017.safetensors",
315 "model.layers.33.self_attn.v_proj.weight": "model-00009-of-00017.safetensors",
316 "model.layers.34.input_layernorm.weight": "model-00010-of-00017.safetensors",
317 "model.layers.34.mlp.down_proj.weight": "model-00010-of-00017.safetensors",
318 "model.layers.34.mlp.gate_proj.weight": "model-00009-of-00017.safetensors",
319 "model.layers.34.mlp.up_proj.weight": "model-00010-of-00017.safetensors",
320 "model.layers.34.post_attention_layernorm.weight": "model-00010-of-00017.safetensors",
321 "model.layers.34.self_attn.k_norm.weight": "model-00009-of-00017.safetensors",
322 "model.layers.34.self_attn.k_proj.weight": "model-00009-of-00017.safetensors",
323 "model.layers.34.self_attn.o_proj.weight": "model-00009-of-00017.safetensors",
324 "model.layers.34.self_attn.q_norm.weight": "model-00009-of-00017.safetensors",
325 "model.layers.34.self_attn.q_proj.weight": "model-00009-of-00017.safetensors",
326 "model.layers.34.self_attn.v_proj.weight": "model-00009-of-00017.safetensors",
327 "model.layers.35.input_layernorm.weight": "model-00010-of-00017.safetensors",
328 "model.layers.35.mlp.down_proj.weight": "model-00010-of-00017.safetensors",
329 "model.layers.35.mlp.gate_proj.weight": "model-00010-of-00017.safetensors",
330 "model.layers.35.mlp.up_proj.weight": "model-00010-of-00017.safetensors",
331 "model.layers.35.post_attention_layernorm.weight": "model-00010-of-00017.safetensors",
332 "model.layers.35.self_attn.k_norm.weight": "model-00010-of-00017.safetensors",
333 "model.layers.35.self_attn.k_proj.weight": "model-00010-of-00017.safetensors",
334 "model.layers.35.self_attn.o_proj.weight": "model-00010-of-00017.safetensors",
335 "model.layers.35.self_attn.q_norm.weight": "model-00010-of-00017.safetensors",
336 "model.layers.35.self_attn.q_proj.weight": "model-00010-of-00017.safetensors",
337 "model.layers.35.self_attn.v_proj.weight": "model-00010-of-00017.safetensors",
338 "model.layers.36.input_layernorm.weight": "model-00010-of-00017.safetensors",
339 "model.layers.36.mlp.down_proj.weight": "model-00010-of-00017.safetensors",
340 "model.layers.36.mlp.gate_proj.weight": "model-00010-of-00017.safetensors",
341 "model.layers.36.mlp.up_proj.weight": "model-00010-of-00017.safetensors",
342 "model.layers.36.post_attention_layernorm.weight": "model-00010-of-00017.safetensors",
343 "model.layers.36.self_attn.k_norm.weight": "model-00010-of-00017.safetensors",
344 "model.layers.36.self_attn.k_proj.weight": "model-00010-of-00017.safetensors",
345 "model.layers.36.self_attn.o_proj.weight": "model-00010-of-00017.safetensors",
346 "model.layers.36.self_attn.q_norm.weight": "model-00010-of-00017.safetensors",
347 "model.layers.36.self_attn.q_proj.weight": "model-00010-of-00017.safetensors",
348 "model.layers.36.self_attn.v_proj.weight": "model-00010-of-00017.safetensors",
349 "model.layers.37.input_layernorm.weight": "model-00010-of-00017.safetensors",
350 "model.layers.37.mlp.down_proj.weight": "model-00010-of-00017.safetensors",
351 "model.layers.37.mlp.gate_proj.weight": "model-00010-of-00017.safetensors",
352 "model.layers.37.mlp.up_proj.weight": "model-00010-of-00017.safetensors",
353 "model.layers.37.post_attention_layernorm.weight": "model-00010-of-00017.safetensors",
354 "model.layers.37.self_attn.k_norm.weight": "model-00010-of-00017.safetensors",
355 "model.layers.37.self_attn.k_proj.weight": "model-00010-of-00017.safetensors",
356 "model.layers.37.self_attn.o_proj.weight": "model-00010-of-00017.safetensors",
357 "model.layers.37.self_attn.q_norm.weight": "model-00010-of-00017.safetensors",
358 "model.layers.37.self_attn.q_proj.weight": "model-00010-of-00017.safetensors",
359 "model.layers.37.self_attn.v_proj.weight": "model-00010-of-00017.safetensors",
360 "model.layers.38.input_layernorm.weight": "model-00011-of-00017.safetensors",
361 "model.layers.38.mlp.down_proj.weight": "model-00011-of-00017.safetensors",
362 "model.layers.38.mlp.gate_proj.weight": "model-00010-of-00017.safetensors",
363 "model.layers.38.mlp.up_proj.weight": "model-00011-of-00017.safetensors",
364 "model.layers.38.post_attention_layernorm.weight": "model-00011-of-00017.safetensors",
365 "model.layers.38.self_attn.k_norm.weight": "model-00010-of-00017.safetensors",
366 "model.layers.38.self_attn.k_proj.weight": "model-00010-of-00017.safetensors",
367 "model.layers.38.self_attn.o_proj.weight": "model-00010-of-00017.safetensors",
368 "model.layers.38.self_attn.q_norm.weight": "model-00010-of-00017.safetensors",
369 "model.layers.38.self_attn.q_proj.weight": "model-00010-of-00017.safetensors",
370 "model.layers.38.self_attn.v_proj.weight": "model-00010-of-00017.safetensors",
371 "model.layers.39.input_layernorm.weight": "model-00011-of-00017.safetensors",
372 "model.layers.39.mlp.down_proj.weight": "model-00011-of-00017.safetensors",
373 "model.layers.39.mlp.gate_proj.weight": "model-00011-of-00017.safetensors",
374 "model.layers.39.mlp.up_proj.weight": "model-00011-of-00017.safetensors",
375 "model.layers.39.post_attention_layernorm.weight": "model-00011-of-00017.safetensors",
376 "model.layers.39.self_attn.k_norm.weight": "model-00011-of-00017.safetensors",
377 "model.layers.39.self_attn.k_proj.weight": "model-00011-of-00017.safetensors",
378 "model.layers.39.self_attn.o_proj.weight": "model-00011-of-00017.safetensors",
379 "model.layers.39.self_attn.q_norm.weight": "model-00011-of-00017.safetensors",
380 "model.layers.39.self_attn.q_proj.weight": "model-00011-of-00017.safetensors",
381 "model.layers.39.self_attn.v_proj.weight": "model-00011-of-00017.safetensors",
382 "model.layers.4.input_layernorm.weight": "model-00002-of-00017.safetensors",
383 "model.layers.4.mlp.down_proj.weight": "model-00002-of-00017.safetensors",
384 "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00017.safetensors",
385 "model.layers.4.mlp.up_proj.weight": "model-00002-of-00017.safetensors",
386 "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
387 "model.layers.4.self_attn.k_norm.weight": "model-00002-of-00017.safetensors",
388 "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
389 "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
390 "model.layers.4.self_attn.q_norm.weight": "model-00002-of-00017.safetensors",
391 "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
392 "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
393 "model.layers.40.input_layernorm.weight": "model-00011-of-00017.safetensors",
394 "model.layers.40.mlp.down_proj.weight": "model-00011-of-00017.safetensors",
395 "model.layers.40.mlp.gate_proj.weight": "model-00011-of-00017.safetensors",
396 "model.layers.40.mlp.up_proj.weight": "model-00011-of-00017.safetensors",
397 "model.layers.40.post_attention_layernorm.weight": "model-00011-of-00017.safetensors",
398 "model.layers.40.self_attn.k_norm.weight": "model-00011-of-00017.safetensors",
399 "model.layers.40.self_attn.k_proj.weight": "model-00011-of-00017.safetensors",
400 "model.layers.40.self_attn.o_proj.weight": "model-00011-of-00017.safetensors",
401 "model.layers.40.self_attn.q_norm.weight": "model-00011-of-00017.safetensors",
402 "model.layers.40.self_attn.q_proj.weight": "model-00011-of-00017.safetensors",
403 "model.layers.40.self_attn.v_proj.weight": "model-00011-of-00017.safetensors",
404 "model.layers.41.input_layernorm.weight": "model-00011-of-00017.safetensors",
405 "model.layers.41.mlp.down_proj.weight": "model-00011-of-00017.safetensors",
406 "model.layers.41.mlp.gate_proj.weight": "model-00011-of-00017.safetensors",
407 "model.layers.41.mlp.up_proj.weight": "model-00011-of-00017.safetensors",
408 "model.layers.41.post_attention_layernorm.weight": "model-00011-of-00017.safetensors",
409 "model.layers.41.self_attn.k_norm.weight": "model-00011-of-00017.safetensors",
410 "model.layers.41.self_attn.k_proj.weight": "model-00011-of-00017.safetensors",
411 "model.layers.41.self_attn.o_proj.weight": "model-00011-of-00017.safetensors",
412 "model.layers.41.self_attn.q_norm.weight": "model-00011-of-00017.safetensors",
413 "model.layers.41.self_attn.q_proj.weight": "model-00011-of-00017.safetensors",
414 "model.layers.41.self_attn.v_proj.weight": "model-00011-of-00017.safetensors",
415 "model.layers.42.input_layernorm.weight": "model-00012-of-00017.safetensors",
416 "model.layers.42.mlp.down_proj.weight": "model-00012-of-00017.safetensors",
417 "model.layers.42.mlp.gate_proj.weight": "model-00011-of-00017.safetensors",
418 "model.layers.42.mlp.up_proj.weight": "model-00012-of-00017.safetensors",
419 "model.layers.42.post_attention_layernorm.weight": "model-00012-of-00017.safetensors",
420 "model.layers.42.self_attn.k_norm.weight": "model-00011-of-00017.safetensors",
421 "model.layers.42.self_attn.k_proj.weight": "model-00011-of-00017.safetensors",
422 "model.layers.42.self_attn.o_proj.weight": "model-00011-of-00017.safetensors",
423 "model.layers.42.self_attn.q_norm.weight": "model-00011-of-00017.safetensors",
424 "model.layers.42.self_attn.q_proj.weight": "model-00011-of-00017.safetensors",
425 "model.layers.42.self_attn.v_proj.weight": "model-00011-of-00017.safetensors",
426 "model.layers.43.input_layernorm.weight": "model-00012-of-00017.safetensors",
427 "model.layers.43.mlp.down_proj.weight": "model-00012-of-00017.safetensors",
428 "model.layers.43.mlp.gate_proj.weight": "model-00012-of-00017.safetensors",
429 "model.layers.43.mlp.up_proj.weight": "model-00012-of-00017.safetensors",
430 "model.layers.43.post_attention_layernorm.weight": "model-00012-of-00017.safetensors",
431 "model.layers.43.self_attn.k_norm.weight": "model-00012-of-00017.safetensors",
432 "model.layers.43.self_attn.k_proj.weight": "model-00012-of-00017.safetensors",
433 "model.layers.43.self_attn.o_proj.weight": "model-00012-of-00017.safetensors",
434 "model.layers.43.self_attn.q_norm.weight": "model-00012-of-00017.safetensors",
435 "model.layers.43.self_attn.q_proj.weight": "model-00012-of-00017.safetensors",
436 "model.layers.43.self_attn.v_proj.weight": "model-00012-of-00017.safetensors",
437 "model.layers.44.input_layernorm.weight": "model-00012-of-00017.safetensors",
438 "model.layers.44.mlp.down_proj.weight": "model-00012-of-00017.safetensors",
439 "model.layers.44.mlp.gate_proj.weight": "model-00012-of-00017.safetensors",
440 "model.layers.44.mlp.up_proj.weight": "model-00012-of-00017.safetensors",
441 "model.layers.44.post_attention_layernorm.weight": "model-00012-of-00017.safetensors",
442 "model.layers.44.self_attn.k_norm.weight": "model-00012-of-00017.safetensors",
443 "model.layers.44.self_attn.k_proj.weight": "model-00012-of-00017.safetensors",
444 "model.layers.44.self_attn.o_proj.weight": "model-00012-of-00017.safetensors",
445 "model.layers.44.self_attn.q_norm.weight": "model-00012-of-00017.safetensors",
446 "model.layers.44.self_attn.q_proj.weight": "model-00012-of-00017.safetensors",
447 "model.layers.44.self_attn.v_proj.weight": "model-00012-of-00017.safetensors",
448 "model.layers.45.input_layernorm.weight": "model-00012-of-00017.safetensors",
449 "model.layers.45.mlp.down_proj.weight": "model-00012-of-00017.safetensors",
450 "model.layers.45.mlp.gate_proj.weight": "model-00012-of-00017.safetensors",
451 "model.layers.45.mlp.up_proj.weight": "model-00012-of-00017.safetensors",
452 "model.layers.45.post_attention_layernorm.weight": "model-00012-of-00017.safetensors",
453 "model.layers.45.self_attn.k_norm.weight": "model-00012-of-00017.safetensors",
454 "model.layers.45.self_attn.k_proj.weight": "model-00012-of-00017.safetensors",
455 "model.layers.45.self_attn.o_proj.weight": "model-00012-of-00017.safetensors",
456 "model.layers.45.self_attn.q_norm.weight": "model-00012-of-00017.safetensors",
457 "model.layers.45.self_attn.q_proj.weight": "model-00012-of-00017.safetensors",
458 "model.layers.45.self_attn.v_proj.weight": "model-00012-of-00017.safetensors",
459 "model.layers.46.input_layernorm.weight": "model-00013-of-00017.safetensors",
460 "model.layers.46.mlp.down_proj.weight": "model-00013-of-00017.safetensors",
461 "model.layers.46.mlp.gate_proj.weight": "model-00012-of-00017.safetensors",
462 "model.layers.46.mlp.up_proj.weight": "model-00013-of-00017.safetensors",
463 "model.layers.46.post_attention_layernorm.weight": "model-00013-of-00017.safetensors",
464 "model.layers.46.self_attn.k_norm.weight": "model-00012-of-00017.safetensors",
465 "model.layers.46.self_attn.k_proj.weight": "model-00012-of-00017.safetensors",
466 "model.layers.46.self_attn.o_proj.weight": "model-00012-of-00017.safetensors",
467 "model.layers.46.self_attn.q_norm.weight": "model-00012-of-00017.safetensors",
468 "model.layers.46.self_attn.q_proj.weight": "model-00012-of-00017.safetensors",
469 "model.layers.46.self_attn.v_proj.weight": "model-00012-of-00017.safetensors",
470 "model.layers.47.input_layernorm.weight": "model-00013-of-00017.safetensors",
471 "model.layers.47.mlp.down_proj.weight": "model-00013-of-00017.safetensors",
472 "model.layers.47.mlp.gate_proj.weight": "model-00013-of-00017.safetensors",
473 "model.layers.47.mlp.up_proj.weight": "model-00013-of-00017.safetensors",
474 "model.layers.47.post_attention_layernorm.weight": "model-00013-of-00017.safetensors",
475 "model.layers.47.self_attn.k_norm.weight": "model-00013-of-00017.safetensors",
476 "model.layers.47.self_attn.k_proj.weight": "model-00013-of-00017.safetensors",
477 "model.layers.47.self_attn.o_proj.weight": "model-00013-of-00017.safetensors",
478 "model.layers.47.self_attn.q_norm.weight": "model-00013-of-00017.safetensors",
479 "model.layers.47.self_attn.q_proj.weight": "model-00013-of-00017.safetensors",
480 "model.layers.47.self_attn.v_proj.weight": "model-00013-of-00017.safetensors",
481 "model.layers.48.input_layernorm.weight": "model-00013-of-00017.safetensors",
482 "model.layers.48.mlp.down_proj.weight": "model-00013-of-00017.safetensors",
483 "model.layers.48.mlp.gate_proj.weight": "model-00013-of-00017.safetensors",
484 "model.layers.48.mlp.up_proj.weight": "model-00013-of-00017.safetensors",
485 "model.layers.48.post_attention_layernorm.weight": "model-00013-of-00017.safetensors",
486 "model.layers.48.self_attn.k_norm.weight": "model-00013-of-00017.safetensors",
487 "model.layers.48.self_attn.k_proj.weight": "model-00013-of-00017.safetensors",
488 "model.layers.48.self_attn.o_proj.weight": "model-00013-of-00017.safetensors",
489 "model.layers.48.self_attn.q_norm.weight": "model-00013-of-00017.safetensors",
490 "model.layers.48.self_attn.q_proj.weight": "model-00013-of-00017.safetensors",
491 "model.layers.48.self_attn.v_proj.weight": "model-00013-of-00017.safetensors",
492 "model.layers.49.input_layernorm.weight": "model-00013-of-00017.safetensors",
493 "model.layers.49.mlp.down_proj.weight": "model-00013-of-00017.safetensors",
494 "model.layers.49.mlp.gate_proj.weight": "model-00013-of-00017.safetensors",
495 "model.layers.49.mlp.up_proj.weight": "model-00013-of-00017.safetensors",
496 "model.layers.49.post_attention_layernorm.weight": "model-00013-of-00017.safetensors",
497 "model.layers.49.self_attn.k_norm.weight": "model-00013-of-00017.safetensors",
498 "model.layers.49.self_attn.k_proj.weight": "model-00013-of-00017.safetensors",
499 "model.layers.49.self_attn.o_proj.weight": "model-00013-of-00017.safetensors",
500 "model.layers.49.self_attn.q_norm.weight": "model-00013-of-00017.safetensors",
501 "model.layers.49.self_attn.q_proj.weight": "model-00013-of-00017.safetensors",
502 "model.layers.49.self_attn.v_proj.weight": "model-00013-of-00017.safetensors",
503 "model.layers.5.input_layernorm.weight": "model-00002-of-00017.safetensors",
504 "model.layers.5.mlp.down_proj.weight": "model-00002-of-00017.safetensors",
505 "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00017.safetensors",
506 "model.layers.5.mlp.up_proj.weight": "model-00002-of-00017.safetensors",
507 "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
508 "model.layers.5.self_attn.k_norm.weight": "model-00002-of-00017.safetensors",
509 "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
510 "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
511 "model.layers.5.self_attn.q_norm.weight": "model-00002-of-00017.safetensors",
512 "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
513 "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
514 "model.layers.50.input_layernorm.weight": "model-00014-of-00017.safetensors",
515 "model.layers.50.mlp.down_proj.weight": "model-00014-of-00017.safetensors",
516 "model.layers.50.mlp.gate_proj.weight": "model-00013-of-00017.safetensors",
517 "model.layers.50.mlp.up_proj.weight": "model-00014-of-00017.safetensors",
518 "model.layers.50.post_attention_layernorm.weight": "model-00014-of-00017.safetensors",
519 "model.layers.50.self_attn.k_norm.weight": "model-00013-of-00017.safetensors",
520 "model.layers.50.self_attn.k_proj.weight": "model-00013-of-00017.safetensors",
521 "model.layers.50.self_attn.o_proj.weight": "model-00013-of-00017.safetensors",
522 "model.layers.50.self_attn.q_norm.weight": "model-00013-of-00017.safetensors",
523 "model.layers.50.self_attn.q_proj.weight": "model-00013-of-00017.safetensors",
524 "model.layers.50.self_attn.v_proj.weight": "model-00013-of-00017.safetensors",
525 "model.layers.51.input_layernorm.weight": "model-00014-of-00017.safetensors",
526 "model.layers.51.mlp.down_proj.weight": "model-00014-of-00017.safetensors",
527 "model.layers.51.mlp.gate_proj.weight": "model-00014-of-00017.safetensors",
528 "model.layers.51.mlp.up_proj.weight": "model-00014-of-00017.safetensors",
529 "model.layers.51.post_attention_layernorm.weight": "model-00014-of-00017.safetensors",
530 "model.layers.51.self_attn.k_norm.weight": "model-00014-of-00017.safetensors",
531 "model.layers.51.self_attn.k_proj.weight": "model-00014-of-00017.safetensors",
532 "model.layers.51.self_attn.o_proj.weight": "model-00014-of-00017.safetensors",
533 "model.layers.51.self_attn.q_norm.weight": "model-00014-of-00017.safetensors",
534 "model.layers.51.self_attn.q_proj.weight": "model-00014-of-00017.safetensors",
535 "model.layers.51.self_attn.v_proj.weight": "model-00014-of-00017.safetensors",
536 "model.layers.52.input_layernorm.weight": "model-00014-of-00017.safetensors",
537 "model.layers.52.mlp.down_proj.weight": "model-00014-of-00017.safetensors",
538 "model.layers.52.mlp.gate_proj.weight": "model-00014-of-00017.safetensors",
539 "model.layers.52.mlp.up_proj.weight": "model-00014-of-00017.safetensors",
540 "model.layers.52.post_attention_layernorm.weight": "model-00014-of-00017.safetensors",
541 "model.layers.52.self_attn.k_norm.weight": "model-00014-of-00017.safetensors",
542 "model.layers.52.self_attn.k_proj.weight": "model-00014-of-00017.safetensors",
543 "model.layers.52.self_attn.o_proj.weight": "model-00014-of-00017.safetensors",
544 "model.layers.52.self_attn.q_norm.weight": "model-00014-of-00017.safetensors",
545 "model.layers.52.self_attn.q_proj.weight": "model-00014-of-00017.safetensors",
546 "model.layers.52.self_attn.v_proj.weight": "model-00014-of-00017.safetensors",
547 "model.layers.53.input_layernorm.weight": "model-00014-of-00017.safetensors",
548 "model.layers.53.mlp.down_proj.weight": "model-00014-of-00017.safetensors",
549 "model.layers.53.mlp.gate_proj.weight": "model-00014-of-00017.safetensors",
550 "model.layers.53.mlp.up_proj.weight": "model-00014-of-00017.safetensors",
551 "model.layers.53.post_attention_layernorm.weight": "model-00014-of-00017.safetensors",
552 "model.layers.53.self_attn.k_norm.weight": "model-00014-of-00017.safetensors",
553 "model.layers.53.self_attn.k_proj.weight": "model-00014-of-00017.safetensors",
554 "model.layers.53.self_attn.o_proj.weight": "model-00014-of-00017.safetensors",
555 "model.layers.53.self_attn.q_norm.weight": "model-00014-of-00017.safetensors",
556 "model.layers.53.self_attn.q_proj.weight": "model-00014-of-00017.safetensors",
557 "model.layers.53.self_attn.v_proj.weight": "model-00014-of-00017.safetensors",
558 "model.layers.54.input_layernorm.weight": "model-00015-of-00017.safetensors",
559 "model.layers.54.mlp.down_proj.weight": "model-00015-of-00017.safetensors",
560 "model.layers.54.mlp.gate_proj.weight": "model-00014-of-00017.safetensors",
561 "model.layers.54.mlp.up_proj.weight": "model-00015-of-00017.safetensors",
562 "model.layers.54.post_attention_layernorm.weight": "model-00015-of-00017.safetensors",
563 "model.layers.54.self_attn.k_norm.weight": "model-00014-of-00017.safetensors",
564 "model.layers.54.self_attn.k_proj.weight": "model-00014-of-00017.safetensors",
565 "model.layers.54.self_attn.o_proj.weight": "model-00014-of-00017.safetensors",
566 "model.layers.54.self_attn.q_norm.weight": "model-00014-of-00017.safetensors",
567 "model.layers.54.self_attn.q_proj.weight": "model-00014-of-00017.safetensors",
568 "model.layers.54.self_attn.v_proj.weight": "model-00014-of-00017.safetensors",
569 "model.layers.55.input_layernorm.weight": "model-00015-of-00017.safetensors",
570 "model.layers.55.mlp.down_proj.weight": "model-00015-of-00017.safetensors",
571 "model.layers.55.mlp.gate_proj.weight": "model-00015-of-00017.safetensors",
572 "model.layers.55.mlp.up_proj.weight": "model-00015-of-00017.safetensors",
573 "model.layers.55.post_attention_layernorm.weight": "model-00015-of-00017.safetensors",
574 "model.layers.55.self_attn.k_norm.weight": "model-00015-of-00017.safetensors",
575 "model.layers.55.self_attn.k_proj.weight": "model-00015-of-00017.safetensors",
576 "model.layers.55.self_attn.o_proj.weight": "model-00015-of-00017.safetensors",
577 "model.layers.55.self_attn.q_norm.weight": "model-00015-of-00017.safetensors",
578 "model.layers.55.self_attn.q_proj.weight": "model-00015-of-00017.safetensors",
579 "model.layers.55.self_attn.v_proj.weight": "model-00015-of-00017.safetensors",
580 "model.layers.56.input_layernorm.weight": "model-00015-of-00017.safetensors",
581 "model.layers.56.mlp.down_proj.weight": "model-00015-of-00017.safetensors",
582 "model.layers.56.mlp.gate_proj.weight": "model-00015-of-00017.safetensors",
583 "model.layers.56.mlp.up_proj.weight": "model-00015-of-00017.safetensors",
584 "model.layers.56.post_attention_layernorm.weight": "model-00015-of-00017.safetensors",
585 "model.layers.56.self_attn.k_norm.weight": "model-00015-of-00017.safetensors",
586 "model.layers.56.self_attn.k_proj.weight": "model-00015-of-00017.safetensors",
587 "model.layers.56.self_attn.o_proj.weight": "model-00015-of-00017.safetensors",
588 "model.layers.56.self_attn.q_norm.weight": "model-00015-of-00017.safetensors",
589 "model.layers.56.self_attn.q_proj.weight": "model-00015-of-00017.safetensors",
590 "model.layers.56.self_attn.v_proj.weight": "model-00015-of-00017.safetensors",
591 "model.layers.57.input_layernorm.weight": "model-00015-of-00017.safetensors",
592 "model.layers.57.mlp.down_proj.weight": "model-00015-of-00017.safetensors",
593 "model.layers.57.mlp.gate_proj.weight": "model-00015-of-00017.safetensors",
594 "model.layers.57.mlp.up_proj.weight": "model-00015-of-00017.safetensors",
595 "model.layers.57.post_attention_layernorm.weight": "model-00015-of-00017.safetensors",
596 "model.layers.57.self_attn.k_norm.weight": "model-00015-of-00017.safetensors",
597 "model.layers.57.self_attn.k_proj.weight": "model-00015-of-00017.safetensors",
598 "model.layers.57.self_attn.o_proj.weight": "model-00015-of-00017.safetensors",
599 "model.layers.57.self_attn.q_norm.weight": "model-00015-of-00017.safetensors",
600 "model.layers.57.self_attn.q_proj.weight": "model-00015-of-00017.safetensors",
601 "model.layers.57.self_attn.v_proj.weight": "model-00015-of-00017.safetensors",
602 "model.layers.58.input_layernorm.weight": "model-00016-of-00017.safetensors",
603 "model.layers.58.mlp.down_proj.weight": "model-00016-of-00017.safetensors",
604 "model.layers.58.mlp.gate_proj.weight": "model-00015-of-00017.safetensors",
605 "model.layers.58.mlp.up_proj.weight": "model-00016-of-00017.safetensors",
606 "model.layers.58.post_attention_layernorm.weight": "model-00016-of-00017.safetensors",
607 "model.layers.58.self_attn.k_norm.weight": "model-00015-of-00017.safetensors",
608 "model.layers.58.self_attn.k_proj.weight": "model-00015-of-00017.safetensors",
609 "model.layers.58.self_attn.o_proj.weight": "model-00015-of-00017.safetensors",
610 "model.layers.58.self_attn.q_norm.weight": "model-00015-of-00017.safetensors",
611 "model.layers.58.self_attn.q_proj.weight": "model-00015-of-00017.safetensors",
612 "model.layers.58.self_attn.v_proj.weight": "model-00015-of-00017.safetensors",
613 "model.layers.59.input_layernorm.weight": "model-00016-of-00017.safetensors",
614 "model.layers.59.mlp.down_proj.weight": "model-00016-of-00017.safetensors",
615 "model.layers.59.mlp.gate_proj.weight": "model-00016-of-00017.safetensors",
616 "model.layers.59.mlp.up_proj.weight": "model-00016-of-00017.safetensors",
617 "model.layers.59.post_attention_layernorm.weight": "model-00016-of-00017.safetensors",
618 "model.layers.59.self_attn.k_norm.weight": "model-00016-of-00017.safetensors",
619 "model.layers.59.self_attn.k_proj.weight": "model-00016-of-00017.safetensors",
620 "model.layers.59.self_attn.o_proj.weight": "model-00016-of-00017.safetensors",
621 "model.layers.59.self_attn.q_norm.weight": "model-00016-of-00017.safetensors",
622 "model.layers.59.self_attn.q_proj.weight": "model-00016-of-00017.safetensors",
623 "model.layers.59.self_attn.v_proj.weight": "model-00016-of-00017.safetensors",
624 "model.layers.6.input_layernorm.weight": "model-00003-of-00017.safetensors",
625 "model.layers.6.mlp.down_proj.weight": "model-00003-of-00017.safetensors",
626 "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00017.safetensors",
627 "model.layers.6.mlp.up_proj.weight": "model-00003-of-00017.safetensors",
628 "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00017.safetensors",
629 "model.layers.6.self_attn.k_norm.weight": "model-00002-of-00017.safetensors",
630 "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
631 "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
632 "model.layers.6.self_attn.q_norm.weight": "model-00002-of-00017.safetensors",
633 "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
634 "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
635 "model.layers.60.input_layernorm.weight": "model-00016-of-00017.safetensors",
636 "model.layers.60.mlp.down_proj.weight": "model-00016-of-00017.safetensors",
637 "model.layers.60.mlp.gate_proj.weight": "model-00016-of-00017.safetensors",
638 "model.layers.60.mlp.up_proj.weight": "model-00016-of-00017.safetensors",
639 "model.layers.60.post_attention_layernorm.weight": "model-00016-of-00017.safetensors",
640 "model.layers.60.self_attn.k_norm.weight": "model-00016-of-00017.safetensors",
641 "model.layers.60.self_attn.k_proj.weight": "model-00016-of-00017.safetensors",
642 "model.layers.60.self_attn.o_proj.weight": "model-00016-of-00017.safetensors",
643 "model.layers.60.self_attn.q_norm.weight": "model-00016-of-00017.safetensors",
644 "model.layers.60.self_attn.q_proj.weight": "model-00016-of-00017.safetensors",
645 "model.layers.60.self_attn.v_proj.weight": "model-00016-of-00017.safetensors",
646 "model.layers.61.input_layernorm.weight": "model-00016-of-00017.safetensors",
647 "model.layers.61.mlp.down_proj.weight": "model-00016-of-00017.safetensors",
648 "model.layers.61.mlp.gate_proj.weight": "model-00016-of-00017.safetensors",
649 "model.layers.61.mlp.up_proj.weight": "model-00016-of-00017.safetensors",
650 "model.layers.61.post_attention_layernorm.weight": "model-00016-of-00017.safetensors",
651 "model.layers.61.self_attn.k_norm.weight": "model-00016-of-00017.safetensors",
652 "model.layers.61.self_attn.k_proj.weight": "model-00016-of-00017.safetensors",
653 "model.layers.61.self_attn.o_proj.weight": "model-00016-of-00017.safetensors",
654 "model.layers.61.self_attn.q_norm.weight": "model-00016-of-00017.safetensors",
655 "model.layers.61.self_attn.q_proj.weight": "model-00016-of-00017.safetensors",
656 "model.layers.61.self_attn.v_proj.weight": "model-00016-of-00017.safetensors",
657 "model.layers.62.input_layernorm.weight": "model-00017-of-00017.safetensors",
658 "model.layers.62.mlp.down_proj.weight": "model-00017-of-00017.safetensors",
659 "model.layers.62.mlp.gate_proj.weight": "model-00016-of-00017.safetensors",
660 "model.layers.62.mlp.up_proj.weight": "model-00017-of-00017.safetensors",
661 "model.layers.62.post_attention_layernorm.weight": "model-00017-of-00017.safetensors",
662 "model.layers.62.self_attn.k_norm.weight": "model-00016-of-00017.safetensors",
663 "model.layers.62.self_attn.k_proj.weight": "model-00016-of-00017.safetensors",
664 "model.layers.62.self_attn.o_proj.weight": "model-00016-of-00017.safetensors",
665 "model.layers.62.self_attn.q_norm.weight": "model-00016-of-00017.safetensors",
666 "model.layers.62.self_attn.q_proj.weight": "model-00016-of-00017.safetensors",
667 "model.layers.62.self_attn.v_proj.weight": "model-00016-of-00017.safetensors",
668 "model.layers.63.input_layernorm.weight": "model-00017-of-00017.safetensors",
669 "model.layers.63.mlp.down_proj.weight": "model-00017-of-00017.safetensors",
670 "model.layers.63.mlp.gate_proj.weight": "model-00017-of-00017.safetensors",
671 "model.layers.63.mlp.up_proj.weight": "model-00017-of-00017.safetensors",
672 "model.layers.63.post_attention_layernorm.weight": "model-00017-of-00017.safetensors",
673 "model.layers.63.self_attn.k_norm.weight": "model-00017-of-00017.safetensors",
674 "model.layers.63.self_attn.k_proj.weight": "model-00017-of-00017.safetensors",
675 "model.layers.63.self_attn.o_proj.weight": "model-00017-of-00017.safetensors",
676 "model.layers.63.self_attn.q_norm.weight": "model-00017-of-00017.safetensors",
677 "model.layers.63.self_attn.q_proj.weight": "model-00017-of-00017.safetensors",
678 "model.layers.63.self_attn.v_proj.weight": "model-00017-of-00017.safetensors",
679 "model.layers.7.input_layernorm.weight": "model-00003-of-00017.safetensors",
680 "model.layers.7.mlp.down_proj.weight": "model-00003-of-00017.safetensors",
681 "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00017.safetensors",
682 "model.layers.7.mlp.up_proj.weight": "model-00003-of-00017.safetensors",
683 "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00017.safetensors",
684 "model.layers.7.self_attn.k_norm.weight": "model-00003-of-00017.safetensors",
685 "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00017.safetensors",
686 "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00017.safetensors",
687 "model.layers.7.self_attn.q_norm.weight": "model-00003-of-00017.safetensors",
688 "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00017.safetensors",
689 "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00017.safetensors",
690 "model.layers.8.input_layernorm.weight": "model-00003-of-00017.safetensors",
691 "model.layers.8.mlp.down_proj.weight": "model-00003-of-00017.safetensors",
692 "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00017.safetensors",
693 "model.layers.8.mlp.up_proj.weight": "model-00003-of-00017.safetensors",
694 "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00017.safetensors",
695 "model.layers.8.self_attn.k_norm.weight": "model-00003-of-00017.safetensors",
696 "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00017.safetensors",
697 "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00017.safetensors",
698 "model.layers.8.self_attn.q_norm.weight": "model-00003-of-00017.safetensors",
699 "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00017.safetensors",
700 "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00017.safetensors",
701 "model.layers.9.input_layernorm.weight": "model-00003-of-00017.safetensors",
702 "model.layers.9.mlp.down_proj.weight": "model-00003-of-00017.safetensors",
703 "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00017.safetensors",
704 "model.layers.9.mlp.up_proj.weight": "model-00003-of-00017.safetensors",
705 "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00017.safetensors",
706 "model.layers.9.self_attn.k_norm.weight": "model-00003-of-00017.safetensors",
707 "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00017.safetensors",
708 "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00017.safetensors",
709 "model.layers.9.self_attn.q_norm.weight": "model-00003-of-00017.safetensors",
710 "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00017.safetensors",
711 "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00017.safetensors",
712 "model.norm.weight": "model-00017-of-00017.safetensors"
713 }
714 }
715