Hugging Face's logo

stabilityai
/
japanese-stablelm-base-alpha-7b

Text Generation
Transformers
PyTorch
Japanese
japanese-stablelm
causal-lm
custom_code
Model card Files Community
9
japanese-stablelm-base-alpha-7b
File size: 24,091 Bytes 
c79d6e6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
 
{
  "metadata": {
    "total_size": 28052590592
  },
  "weight_map": {
    "embed_out.weight": "pytorch_model-00003-of-00003.bin",
    "transformer.embed_in.weight": "pytorch_model-00001-of-00003.bin",
    "transformer.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
    "transformer.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.0.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.0.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.0.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.0.attention.rotary_emb.scale": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.0.mlp.out_proj.weight": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.0.mlp.packed_input_proj.weight": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.1.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.1.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.1.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.1.attention.rotary_emb.scale": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.1.mlp.out_proj.weight": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.1.mlp.packed_input_proj.weight": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.10.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.10.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.10.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.10.attention.rotary_emb.scale": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.10.mlp.out_proj.weight": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.10.mlp.packed_input_proj.weight": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.10.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.11.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.11.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.11.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.11.attention.rotary_emb.scale": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.11.mlp.out_proj.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.11.mlp.packed_input_proj.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.11.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.12.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.12.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.12.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.12.attention.rotary_emb.scale": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.12.mlp.out_proj.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.12.mlp.packed_input_proj.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.12.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.13.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.13.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.13.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.13.attention.rotary_emb.scale": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.13.mlp.out_proj.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.13.mlp.packed_input_proj.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.13.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.14.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.14.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.14.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.14.attention.rotary_emb.scale": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.14.mlp.out_proj.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.14.mlp.packed_input_proj.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.14.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.15.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.15.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.15.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.15.attention.rotary_emb.scale": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.15.mlp.out_proj.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.15.mlp.packed_input_proj.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.15.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.16.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.16.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.16.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.16.attention.rotary_emb.scale": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.16.mlp.out_proj.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.16.mlp.packed_input_proj.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.16.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.17.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.17.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.17.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.17.attention.rotary_emb.scale": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.17.mlp.out_proj.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.17.mlp.packed_input_proj.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.17.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.18.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.18.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.18.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.18.attention.rotary_emb.scale": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.18.mlp.out_proj.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.18.mlp.packed_input_proj.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.18.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.19.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.19.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.19.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.19.attention.rotary_emb.scale": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.19.mlp.out_proj.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.19.mlp.packed_input_proj.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.19.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.2.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.2.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.2.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.2.attention.rotary_emb.scale": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.2.mlp.out_proj.weight": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.2.mlp.packed_input_proj.weight": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.20.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.20.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.20.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.20.attention.rotary_emb.scale": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.20.mlp.out_proj.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.20.mlp.packed_input_proj.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.20.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.21.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.21.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.21.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.21.attention.rotary_emb.scale": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.21.mlp.out_proj.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.21.mlp.packed_input_proj.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.21.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.22.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.22.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.22.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.22.attention.rotary_emb.scale": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.22.mlp.out_proj.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.22.mlp.packed_input_proj.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.22.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.23.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.23.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.23.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.23.attention.rotary_emb.scale": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.23.mlp.out_proj.weight": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.23.mlp.packed_input_proj.weight": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.23.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
    "transformer.layers.24.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.24.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.24.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.24.attention.rotary_emb.scale": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.24.mlp.out_proj.weight": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.24.mlp.packed_input_proj.weight": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.24.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.25.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.25.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.25.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.25.attention.rotary_emb.scale": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.25.mlp.out_proj.weight": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.25.mlp.packed_input_proj.weight": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.25.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.26.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.26.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.26.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.26.attention.rotary_emb.scale": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.26.mlp.out_proj.weight": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.26.mlp.packed_input_proj.weight": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.26.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.27.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.27.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.27.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.27.attention.rotary_emb.scale": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.27.mlp.out_proj.weight": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.27.mlp.packed_input_proj.weight": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.27.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.28.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.28.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.28.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.28.attention.rotary_emb.scale": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.28.mlp.out_proj.weight": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.28.mlp.packed_input_proj.weight": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.28.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.29.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.29.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.29.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.29.attention.rotary_emb.scale": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.29.mlp.out_proj.weight": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.29.mlp.packed_input_proj.weight": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.29.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.3.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.3.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.3.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.3.attention.rotary_emb.scale": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.3.mlp.out_proj.weight": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.3.mlp.packed_input_proj.weight": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.30.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.30.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.30.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.30.attention.rotary_emb.scale": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.30.mlp.out_proj.weight": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.30.mlp.packed_input_proj.weight": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.30.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.31.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.31.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.31.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.31.attention.rotary_emb.scale": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.31.mlp.out_proj.weight": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.31.mlp.packed_input_proj.weight": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.31.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
    "transformer.layers.4.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.4.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.4.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.4.attention.rotary_emb.scale": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.4.mlp.out_proj.weight": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.4.mlp.packed_input_proj.weight": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.5.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.5.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.5.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.5.attention.rotary_emb.scale": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.5.mlp.out_proj.weight": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.5.mlp.packed_input_proj.weight": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.5.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.6.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.6.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.6.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.6.attention.rotary_emb.scale": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.6.mlp.out_proj.weight": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.6.mlp.packed_input_proj.weight": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.6.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.7.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.7.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.7.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.7.attention.rotary_emb.scale": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.7.mlp.out_proj.weight": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.7.mlp.packed_input_proj.weight": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.7.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.8.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.8.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.8.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.8.attention.rotary_emb.scale": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.8.mlp.out_proj.weight": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.8.mlp.packed_input_proj.weight": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.8.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.9.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.9.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.9.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.9.attention.rotary_emb.scale": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.9.mlp.out_proj.weight": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.9.mlp.packed_input_proj.weight": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.9.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
    "transformer.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin"
  }
}