model.safetensors.index.json
39.5 KB · 472 lines · json Raw
1 {
2 "metadata": {
3 "total_parameters": 8489841664,
4 "total_size": 16979683328
5 },
6 "weight_map": {
7 "emb_ext.0.weight": "model-00004-of-00004.safetensors",
8 "emb_ext.1.weight": "model-00004-of-00004.safetensors",
9 "emb_ext.10.weight": "model-00004-of-00004.safetensors",
10 "emb_ext.11.weight": "model-00004-of-00004.safetensors",
11 "emb_ext.12.weight": "model-00004-of-00004.safetensors",
12 "emb_ext.13.weight": "model-00004-of-00004.safetensors",
13 "emb_ext.14.weight": "model-00004-of-00004.safetensors",
14 "emb_ext.15.weight": "model-00004-of-00004.safetensors",
15 "emb_ext.16.weight": "model-00004-of-00004.safetensors",
16 "emb_ext.17.weight": "model-00004-of-00004.safetensors",
17 "emb_ext.18.weight": "model-00004-of-00004.safetensors",
18 "emb_ext.19.weight": "model-00004-of-00004.safetensors",
19 "emb_ext.2.weight": "model-00004-of-00004.safetensors",
20 "emb_ext.20.weight": "model-00004-of-00004.safetensors",
21 "emb_ext.21.weight": "model-00004-of-00004.safetensors",
22 "emb_ext.22.weight": "model-00004-of-00004.safetensors",
23 "emb_ext.23.weight": "model-00004-of-00004.safetensors",
24 "emb_ext.24.weight": "model-00004-of-00004.safetensors",
25 "emb_ext.25.weight": "model-00004-of-00004.safetensors",
26 "emb_ext.26.weight": "model-00004-of-00004.safetensors",
27 "emb_ext.27.weight": "model-00004-of-00004.safetensors",
28 "emb_ext.28.weight": "model-00004-of-00004.safetensors",
29 "emb_ext.29.weight": "model-00004-of-00004.safetensors",
30 "emb_ext.3.weight": "model-00004-of-00004.safetensors",
31 "emb_ext.30.weight": "model-00004-of-00004.safetensors",
32 "emb_ext.31.weight": "model-00004-of-00004.safetensors",
33 "emb_ext.4.weight": "model-00004-of-00004.safetensors",
34 "emb_ext.5.weight": "model-00004-of-00004.safetensors",
35 "emb_ext.6.weight": "model-00004-of-00004.safetensors",
36 "emb_ext.7.weight": "model-00004-of-00004.safetensors",
37 "emb_ext.8.weight": "model-00004-of-00004.safetensors",
38 "emb_ext.9.weight": "model-00004-of-00004.safetensors",
39 "language_model.embed_tokens.weight": "model-00001-of-00004.safetensors",
40 "language_model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
41 "language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
42 "language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
43 "language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
44 "language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
45 "language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
46 "language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
47 "language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
48 "language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
49 "language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
50 "language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
51 "language_model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
52 "language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
53 "language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
54 "language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
55 "language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
56 "language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
57 "language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
58 "language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
59 "language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
60 "language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
61 "language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
62 "language_model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
63 "language_model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
64 "language_model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
65 "language_model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
66 "language_model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
67 "language_model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
68 "language_model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
69 "language_model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
70 "language_model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
71 "language_model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
72 "language_model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
73 "language_model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
74 "language_model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
75 "language_model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
76 "language_model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
77 "language_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
78 "language_model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
79 "language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
80 "language_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
81 "language_model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
82 "language_model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
83 "language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
84 "language_model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
85 "language_model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
86 "language_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
87 "language_model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
88 "language_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
89 "language_model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
90 "language_model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
91 "language_model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
92 "language_model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
93 "language_model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
94 "language_model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
95 "language_model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
96 "language_model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
97 "language_model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
98 "language_model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
99 "language_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
100 "language_model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
101 "language_model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
102 "language_model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
103 "language_model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
104 "language_model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
105 "language_model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
106 "language_model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
107 "language_model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
108 "language_model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
109 "language_model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
110 "language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
111 "language_model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
112 "language_model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
113 "language_model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
114 "language_model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
115 "language_model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
116 "language_model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
117 "language_model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
118 "language_model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
119 "language_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
120 "language_model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
121 "language_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
122 "language_model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
123 "language_model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
124 "language_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
125 "language_model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
126 "language_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
127 "language_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
128 "language_model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
129 "language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
130 "language_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
131 "language_model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
132 "language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
133 "language_model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
134 "language_model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
135 "language_model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
136 "language_model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
137 "language_model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
138 "language_model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
139 "language_model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
140 "language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
141 "language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
142 "language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
143 "language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
144 "language_model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
145 "language_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
146 "language_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
147 "language_model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
148 "language_model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
149 "language_model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
150 "language_model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
151 "language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
152 "language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
153 "language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
154 "language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
155 "language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
156 "language_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
157 "language_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
158 "language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
159 "language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
160 "language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
161 "language_model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
162 "language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
163 "language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
164 "language_model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
165 "language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
166 "language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
167 "language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
168 "language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
169 "language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
170 "language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
171 "language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
172 "language_model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
173 "language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
174 "language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
175 "language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
176 "language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
177 "language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
178 "language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
179 "language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
180 "language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
181 "language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
182 "language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
183 "language_model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
184 "language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
185 "language_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
186 "language_model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
187 "language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
188 "language_model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
189 "language_model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
190 "language_model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
191 "language_model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
192 "language_model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
193 "language_model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
194 "language_model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
195 "language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
196 "language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
197 "language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
198 "language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
199 "language_model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
200 "language_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
201 "language_model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
202 "language_model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
203 "language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
204 "language_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
205 "language_model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
206 "language_model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
207 "language_model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
208 "language_model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
209 "language_model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
210 "language_model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
211 "language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
212 "language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
213 "language_model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
214 "language_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
215 "language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
216 "language_model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
217 "language_model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
218 "language_model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
219 "language_model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
220 "language_model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
221 "language_model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
222 "language_model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
223 "language_model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
224 "language_model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
225 "language_model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
226 "language_model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
227 "language_model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
228 "language_model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
229 "language_model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
230 "language_model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
231 "language_model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
232 "language_model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
233 "language_model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
234 "language_model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
235 "language_model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
236 "language_model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
237 "language_model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
238 "language_model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
239 "language_model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
240 "language_model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
241 "language_model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
242 "language_model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
243 "language_model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
244 "language_model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
245 "language_model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
246 "language_model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
247 "language_model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
248 "language_model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
249 "language_model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
250 "language_model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
251 "language_model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
252 "language_model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
253 "language_model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
254 "language_model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
255 "language_model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
256 "language_model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
257 "language_model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
258 "language_model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
259 "language_model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
260 "language_model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
261 "language_model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
262 "language_model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
263 "language_model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
264 "language_model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
265 "language_model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
266 "language_model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
267 "language_model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
268 "language_model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
269 "language_model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
270 "language_model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
271 "language_model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
272 "language_model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
273 "language_model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
274 "language_model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
275 "language_model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
276 "language_model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
277 "language_model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
278 "language_model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
279 "language_model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
280 "language_model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
281 "language_model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
282 "language_model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
283 "language_model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
284 "language_model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
285 "language_model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
286 "language_model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
287 "language_model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
288 "language_model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
289 "language_model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
290 "language_model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
291 "language_model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
292 "language_model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
293 "language_model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
294 "language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
295 "language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
296 "language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
297 "language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
298 "language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
299 "language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
300 "language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
301 "language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
302 "language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
303 "language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
304 "language_model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
305 "language_model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
306 "language_model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
307 "language_model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
308 "language_model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
309 "language_model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
310 "language_model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
311 "language_model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
312 "language_model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
313 "language_model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
314 "language_model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
315 "language_model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
316 "language_model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
317 "language_model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
318 "language_model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
319 "language_model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
320 "language_model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
321 "language_model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
322 "language_model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
323 "language_model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
324 "language_model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
325 "language_model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
326 "language_model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
327 "language_model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
328 "language_model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
329 "language_model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
330 "language_model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
331 "language_model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
332 "language_model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
333 "language_model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
334 "language_model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
335 "language_model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
336 "language_model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
337 "language_model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
338 "language_model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
339 "language_model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
340 "language_model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
341 "language_model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
342 "language_model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
343 "language_model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
344 "language_model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
345 "language_model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
346 "language_model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
347 "language_model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
348 "language_model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
349 "language_model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
350 "language_model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
351 "language_model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
352 "language_model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
353 "language_model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
354 "language_model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
355 "language_model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
356 "language_model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
357 "language_model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
358 "language_model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
359 "language_model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
360 "language_model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
361 "language_model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
362 "language_model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
363 "language_model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
364 "language_model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
365 "language_model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
366 "language_model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
367 "language_model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
368 "language_model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
369 "language_model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
370 "language_model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
371 "language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
372 "language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
373 "language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
374 "language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
375 "language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
376 "language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
377 "language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
378 "language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
379 "language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
380 "language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
381 "language_model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
382 "language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
383 "language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
384 "language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
385 "language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
386 "language_model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
387 "language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
388 "language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
389 "language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
390 "language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
391 "language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
392 "language_model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
393 "language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
394 "language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
395 "language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
396 "language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
397 "language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
398 "language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
399 "language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
400 "language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
401 "language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
402 "language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
403 "language_model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
404 "language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
405 "language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
406 "language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
407 "language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
408 "language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
409 "language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
410 "language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
411 "language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
412 "language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
413 "language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
414 "language_model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
415 "language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
416 "language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
417 "language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
418 "language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
419 "language_model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
420 "language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
421 "language_model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
422 "language_model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
423 "language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
424 "language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
425 "language_model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
426 "language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
427 "language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
428 "language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
429 "language_model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
430 "language_model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
431 "language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
432 "language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
433 "language_model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
434 "language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
435 "language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
436 "language_model.norm.weight": "model-00004-of-00004.safetensors",
437 "lm_heads.0.weight": "model-00004-of-00004.safetensors",
438 "lm_heads.1.weight": "model-00004-of-00004.safetensors",
439 "lm_heads.10.weight": "model-00004-of-00004.safetensors",
440 "lm_heads.11.weight": "model-00004-of-00004.safetensors",
441 "lm_heads.12.weight": "model-00004-of-00004.safetensors",
442 "lm_heads.13.weight": "model-00004-of-00004.safetensors",
443 "lm_heads.14.weight": "model-00004-of-00004.safetensors",
444 "lm_heads.15.weight": "model-00004-of-00004.safetensors",
445 "lm_heads.16.weight": "model-00004-of-00004.safetensors",
446 "lm_heads.17.weight": "model-00004-of-00004.safetensors",
447 "lm_heads.18.weight": "model-00004-of-00004.safetensors",
448 "lm_heads.19.weight": "model-00004-of-00004.safetensors",
449 "lm_heads.2.weight": "model-00004-of-00004.safetensors",
450 "lm_heads.20.weight": "model-00004-of-00004.safetensors",
451 "lm_heads.21.weight": "model-00004-of-00004.safetensors",
452 "lm_heads.22.weight": "model-00004-of-00004.safetensors",
453 "lm_heads.23.weight": "model-00004-of-00004.safetensors",
454 "lm_heads.24.weight": "model-00004-of-00004.safetensors",
455 "lm_heads.25.weight": "model-00004-of-00004.safetensors",
456 "lm_heads.26.weight": "model-00004-of-00004.safetensors",
457 "lm_heads.27.weight": "model-00004-of-00004.safetensors",
458 "lm_heads.28.weight": "model-00004-of-00004.safetensors",
459 "lm_heads.29.weight": "model-00004-of-00004.safetensors",
460 "lm_heads.3.weight": "model-00004-of-00004.safetensors",
461 "lm_heads.30.weight": "model-00004-of-00004.safetensors",
462 "lm_heads.31.weight": "model-00004-of-00004.safetensors",
463 "lm_heads.32.weight": "model-00004-of-00004.safetensors",
464 "lm_heads.4.weight": "model-00004-of-00004.safetensors",
465 "lm_heads.5.weight": "model-00004-of-00004.safetensors",
466 "lm_heads.6.weight": "model-00004-of-00004.safetensors",
467 "lm_heads.7.weight": "model-00004-of-00004.safetensors",
468 "lm_heads.8.weight": "model-00004-of-00004.safetensors",
469 "lm_heads.9.weight": "model-00004-of-00004.safetensors"
470 }
471 }
472