Hugging Face's logo

stepfun-ai
/
Step-3.5-Flash-Base

Text Generation
Transformers
Safetensors
step3p5
custom_code
Model card Files
xet
 Community
6
Randomize commited on
Commit
c58ff5a
·
verified ·
1 Parent(s): 0062209

Add files using upload-large-folder tool

Browse files
Files changed (47) hide show
  1. .done +0 -0
  2. config.json +305 -0
  3. model-00001.safetensors +3 -0
  4. model-00002.safetensors +3 -0
  5. model-00003.safetensors +3 -0
  6. model-00004.safetensors +3 -0
  7. model-00005.safetensors +3 -0
  8. model-00006.safetensors +3 -0
  9. model-00007.safetensors +3 -0
  10. model-00008.safetensors +3 -0
  11. model-00009.safetensors +3 -0
  12. model-00010.safetensors +3 -0
  13. model-00011.safetensors +3 -0
  14. model-00012.safetensors +3 -0
  15. model-00013.safetensors +3 -0
  16. model-00014.safetensors +3 -0
  17. model-00015.safetensors +3 -0
  18. model-00016.safetensors +3 -0
  19. model-00017.safetensors +3 -0
  20. model-00018.safetensors +3 -0
  21. model-00019.safetensors +3 -0
  22. model-00020.safetensors +3 -0
  23. model-00021.safetensors +3 -0
  24. model-00022.safetensors +3 -0
  25. model-00023.safetensors +3 -0
  26. model-00024.safetensors +3 -0
  27. model-00025.safetensors +3 -0
  28. model-00026.safetensors +3 -0
  29. model-00027.safetensors +3 -0
  30. model-00028.safetensors +3 -0
  31. model-00029.safetensors +3 -0
  32. model-00030.safetensors +3 -0
  33. model-00031.safetensors +3 -0
  34. model-00032.safetensors +3 -0
  35. model-00033.safetensors +3 -0
  36. model-00034.safetensors +3 -0
  37. model-00035.safetensors +3 -0
  38. model-00036.safetensors +3 -0
  39. model-00037.safetensors +3 -0
  40. model-00038.safetensors +3 -0
  41. model-00039.safetensors +3 -0
  42. model-00040.safetensors +3 -0
  43. model-00041.safetensors +3 -0
  44. model-00042.safetensors +3 -0
  45. model-00043.safetensors +3 -0
  46. model-00044.safetensors +3 -0
  47. model.safetensors.index.json +777 -0
.done ADDED
File without changes
config.json ADDED
@@ -0,0 +1,305 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Step3p5ForCausalLM"
4
+ ],
5
+ "model_type": "step3p5",
6
+ "hidden_size": 4096,
7
+ "intermediate_size": 11264,
8
+ "num_hidden_layers": 45,
9
+ "max_seq_len": 262144,
10
+ "vocab_size": 128815,
11
+ "torch_dtype": "bfloat16",
12
+ "use_qk_norm": false,
13
+ "moe_layers_enum": "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",
14
+ "use_mfa": false,
15
+ "num_attention_heads": 64,
16
+ "num_attention_groups": 8,
17
+ "head_dim": 128,
18
+ "use_moe": true,
19
+ "moe_num_experts": 288,
20
+ "moe_top_k": 8,
21
+ "moe_intermediate_size": 1280,
22
+ "share_expert_dim": 1280,
23
+ "moe_layer_offset": 0,
24
+ "moe_every_n_layer": 1,
25
+ "norm_expert_weight": true,
26
+ "moe_router_activation": "sigmoid",
27
+ "moe_router_scaling_factor": 3.0,
28
+ "att_impl_type": "GQA",
29
+ "rope_theta": [
30
+ 1000000.0,
31
+ 10000.0,
32
+ 10000.0,
33
+ 10000.0,
34
+ 1000000.0,
35
+ 10000.0,
36
+ 10000.0,
37
+ 10000.0,
38
+ 1000000.0,
39
+ 10000.0,
40
+ 10000.0,
41
+ 10000.0,
42
+ 1000000.0,
43
+ 10000.0,
44
+ 10000.0,
45
+ 10000.0,
46
+ 1000000.0,
47
+ 10000.0,
48
+ 10000.0,
49
+ 10000.0,
50
+ 1000000.0,
51
+ 10000.0,
52
+ 10000.0,
53
+ 10000.0,
54
+ 1000000.0,
55
+ 10000.0,
56
+ 10000.0,
57
+ 10000.0,
58
+ 1000000.0,
59
+ 10000.0,
60
+ 10000.0,
61
+ 10000.0,
62
+ 1000000.0,
63
+ 10000.0,
64
+ 10000.0,
65
+ 10000.0,
66
+ 1000000.0,
67
+ 10000.0,
68
+ 10000.0,
69
+ 10000.0,
70
+ 1000000.0,
71
+ 10000.0,
72
+ 10000.0,
73
+ 10000.0,
74
+ 1000000.0,
75
+ 10000.0,
76
+ 10000.0,
77
+ 10000.0
78
+ ],
79
+ "use_head_wise_attn_gate": true,
80
+ "sliding_window": 512,
81
+ "use_moe_router_bias": true,
82
+ "need_fp32_gate": true,
83
+ "sink": false,
84
+ "layer_types": [
85
+ "full_attention",
86
+ "sliding_attention",
87
+ "sliding_attention",
88
+ "sliding_attention",
89
+ "full_attention",
90
+ "sliding_attention",
91
+ "sliding_attention",
92
+ "sliding_attention",
93
+ "full_attention",
94
+ "sliding_attention",
95
+ "sliding_attention",
96
+ "sliding_attention",
97
+ "full_attention",
98
+ "sliding_attention",
99
+ "sliding_attention",
100
+ "sliding_attention",
101
+ "full_attention",
102
+ "sliding_attention",
103
+ "sliding_attention",
104
+ "sliding_attention",
105
+ "full_attention",
106
+ "sliding_attention",
107
+ "sliding_attention",
108
+ "sliding_attention",
109
+ "full_attention",
110
+ "sliding_attention",
111
+ "sliding_attention",
112
+ "sliding_attention",
113
+ "full_attention",
114
+ "sliding_attention",
115
+ "sliding_attention",
116
+ "sliding_attention",
117
+ "full_attention",
118
+ "sliding_attention",
119
+ "sliding_attention",
120
+ "sliding_attention",
121
+ "full_attention",
122
+ "sliding_attention",
123
+ "sliding_attention",
124
+ "sliding_attention",
125
+ "full_attention",
126
+ "sliding_attention",
127
+ "sliding_attention",
128
+ "sliding_attention",
129
+ "full_attention",
130
+ "sliding_attention",
131
+ "sliding_attention",
132
+ "sliding_attention"
133
+ ],
134
+ "use_rope_layers": [],
135
+ "num_nextn_predict_layers": 3,
136
+ "partial_rotary_factors": [
137
+ 0.5,
138
+ 1.0,
139
+ 1.0,
140
+ 1.0,
141
+ 0.5,
142
+ 1.0,
143
+ 1.0,
144
+ 1.0,
145
+ 0.5,
146
+ 1.0,
147
+ 1.0,
148
+ 1.0,
149
+ 0.5,
150
+ 1.0,
151
+ 1.0,
152
+ 1.0,
153
+ 0.5,
154
+ 1.0,
155
+ 1.0,
156
+ 1.0,
157
+ 0.5,
158
+ 1.0,
159
+ 1.0,
160
+ 1.0,
161
+ 0.5,
162
+ 1.0,
163
+ 1.0,
164
+ 1.0,
165
+ 0.5,
166
+ 1.0,
167
+ 1.0,
168
+ 1.0,
169
+ 0.5,
170
+ 1.0,
171
+ 1.0,
172
+ 1.0,
173
+ 0.5,
174
+ 1.0,
175
+ 1.0,
176
+ 1.0,
177
+ 0.5,
178
+ 1.0,
179
+ 1.0,
180
+ 1.0,
181
+ 0.5,
182
+ 1.0,
183
+ 1.0,
184
+ 1.0
185
+ ],
186
+ "eos_token_id": [
187
+ 1,
188
+ 2,
189
+ 128007
190
+ ],
191
+ "bos_token_id": 0,
192
+ "attention_other_setting": {
193
+ "attention_type": "sliding_attention",
194
+ "num_attention_heads": 96,
195
+ "num_attention_groups": 8,
196
+ "head_dim": 128,
197
+ "true_head_dim": 128
198
+ },
199
+ "swiglu_limits": [
200
+ 0.0,
201
+ 0.0,
202
+ 0.0,
203
+ 0.0,
204
+ 0.0,
205
+ 0.0,
206
+ 0.0,
207
+ 0.0,
208
+ 0.0,
209
+ 0.0,
210
+ 0.0,
211
+ 0.0,
212
+ 0.0,
213
+ 0.0,
214
+ 0.0,
215
+ 0.0,
216
+ 0.0,
217
+ 0.0,
218
+ 0.0,
219
+ 0.0,
220
+ 0.0,
221
+ 0.0,
222
+ 0.0,
223
+ 0.0,
224
+ 0.0,
225
+ 0.0,
226
+ 0.0,
227
+ 0.0,
228
+ 0.0,
229
+ 0.0,
230
+ 0.0,
231
+ 0.0,
232
+ 0.0,
233
+ 0.0,
234
+ 0.0,
235
+ 0.0,
236
+ 0.0,
237
+ 0.0,
238
+ 0.0,
239
+ 0.0,
240
+ 0.0,
241
+ 0.0,
242
+ 0.0,
243
+ 7,
244
+ 7,
245
+ 0.0,
246
+ 0.0,
247
+ 0.0
248
+ ],
249
+ "swiglu_limits_shared": [
250
+ 0.0,
251
+ 0.0,
252
+ 0.0,
253
+ 0.0,
254
+ 0.0,
255
+ 0.0,
256
+ 0.0,
257
+ 0.0,
258
+ 0.0,
259
+ 0.0,
260
+ 0.0,
261
+ 0.0,
262
+ 0.0,
263
+ 0.0,
264
+ 0.0,
265
+ 0.0,
266
+ 0.0,
267
+ 0.0,
268
+ 0.0,
269
+ 0.0,
270
+ 0.0,
271
+ 0.0,
272
+ 0.0,
273
+ 0.0,
274
+ 0.0,
275
+ 0.0,
276
+ 0.0,
277
+ 0.0,
278
+ 0.0,
279
+ 0.0,
280
+ 0.0,
281
+ 0.0,
282
+ 0.0,
283
+ 0.0,
284
+ 0.0,
285
+ 0.0,
286
+ 0.0,
287
+ 0.0,
288
+ 0.0,
289
+ 0.0,
290
+ 0.0,
291
+ 0.0,
292
+ 0.0,
293
+ 0.0,
294
+ 16,
295
+ 0.0,
296
+ 0.0,
297
+ 0.0
298
+ ],
299
+ "zero_centered": true,
300
+ "max_position_embeddings": 262144,
301
+ "yarn_only_types": [
302
+ "full_attention"
303
+ ],
304
+ "model_max_lengths": 262144
305
+ }
model-00001.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0db65ebeb53ff19cf5e7471ccab90a34f9fe4d2465b3b2c563eb45b6b6654ec6
3
+ size 9913799640
model-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0247725dfc3b2bbf0aedc6d75965d8fc1068d32ea5339d86b4c79bdb5460d12f
3
+ size 8128653224
model-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b6bfb39654331d2ecdd34511a649a787abf859810195d145ea0f7aeea7b4801
3
+ size 9059696992
model-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a40f603e01b35240fece3d3c48d59a8f9b81921d48ad4a12aa7390db09a5fb63
3
+ size 9059696992
model-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f25c379511d6c8213f901f7d3a2375f9a4b2250093f6053238430a6b61c32e8
3
+ size 9059696992
model-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac66f0852cf739f6c24bf0b0105701a8439c751c69d82ac8e345ff194cf77431
3
+ size 9059696992
model-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe794bd85c19262165a68a897daf791caad4cf9a7976a526c477a87474a144ed
3
+ size 9059696992
model-00008.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1bb3e7e7f23cc82ed84f55af38894c08f26e6d434ef022a9c3f444e14df4255
3
+ size 9059696992
model-00009.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c18ac1cac2ecf230ad28e8b52b1a0a26ce39f110420648b3b1d6b96518dbbf2
3
+ size 9059697000
model-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3075ce1c3807636889ee18f41ec028813d8b573a3af5a7412caf37ab12a8f0dc
3
+ size 9059697000
model-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c52cb2c77716dec1920a3b84db1ea7dd1979005f61c41ab0fa7b4a67080605fa
3
+ size 9059697000
model-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da8503a130e95654d965e8d690456a56d6ca7fb4c32d867d071da37b1f279a1e
3
+ size 9059697000
model-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a15ae0c019068bdb362ebfe9cec555a29d7b91789685d9e90cc285b311293d38
3
+ size 9059697000
model-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ce9f032471a8919195f0c07684718dc2690c2addeb2b13b1a44598b9af69f17
3
+ size 9059697000
model-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e94b5268b6490f5e97775c230b79efee66d18e7611f606e03905f8be40c7b87d
3
+ size 9059697000
model-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53a4f1b1d2cddc83ece355b7220cea9d3f46cbf4bbae7f7b1e5cfe48ba26584f
3
+ size 9059697000
model-00017.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40f0fc9b57978661526fe2dc7b2f57c489294a58041fb696f7c26e1985cee0bf
3
+ size 9059697000
model-00018.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86b13166271f3b31809e1b39d4b8f0e5ce60b5d2bcace0595e8b10bc548ca647
3
+ size 9059697000
model-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:122b9620c119a48518785a505ea24372c486b68210a3ea2404199bd0addd6b1c
3
+ size 9059697000
model-00020.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c431c58dad3d832af9636cef66e41baa798763f651e7821900007f1f86fd6a08
3
+ size 9059697000
model-00021.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc70c069069e7baa01d374e2105d4f9aaba131180aa271d9041d09329abf23b4
3
+ size 9059697000
model-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c57fc5c131d9ec74f8b1045c3b7894de67c6d0381f082bd9275df67a2f7974a0
3
+ size 9059697000
model-00023.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c1070d13f9e82a2a74ac35dbc8c98435121316fe0cfb4f9a49d396d05e529d3
3
+ size 9059697000
model-00024.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07efcaac6ca47da2580267798d3e61ef4401916ecf77cfb5c3e42613d2a30fc7
3
+ size 9059697000
model-00025.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:676e59dbb02a2e47f31d65cf7a4a7b7745fe49f660bb09ad21feba7ef72564dc
3
+ size 9059697000
model-00026.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:895a387b4853ffdf4ef0f0c4e2cd0646a4964f11ca34c017e03c06f1b0945e39
3
+ size 9059697000
model-00027.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5485870557ccfce5e1a593f2c721be02b54b9117f55922c07f4548490a79f7e3
3
+ size 9059697000
model-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29fdfcc3b48ea3217b142613ca269147ae3bbef9bcb495f9564c96664d98a5f8
3
+ size 9059697000
model-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b4c6f2cfbd73521a26a69235df5cb2d7dce9aa509184e1f668b0eb27b77c425
3
+ size 9059697000
model-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab295ec815034897dc95d8e5d5cd536cad24098ec79cca2a4af7e77a8022f9b8
3
+ size 9059697000
model-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ba51bd133eb323a398098425890d950f7261de8d6787fabe2605cbcee184956
3
+ size 9059697000
model-00032.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f1eea2f8143d909dbcd1283c9d3ff45e7c9f759cc9497c2561859f61fd1b13f
3
+ size 9059697000
model-00033.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01c87ecc8c58546f3bc89ffe56dd8859d894baa1d79559abf63516fd2c85f9e7
3
+ size 9059697000
model-00034.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f522d98dbce8afad3c79486a8c6980525a263e4ccd966dcb1f0e22d1fafd7503
3
+ size 9059697000
model-00035.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee86c668e5363cf555f27bf1ca2f51bc2d9fb5dc3d13c5a0724ba83107ef7edb
3
+ size 9059697000
model-00036.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf0760590dc203c975d537e2903991839fe410f3529d394cd0c75ed66820bb3a
3
+ size 9059697000
model-00037.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78746b1f9452ff384dae10df28c3948e4e83b5ac2f6818dc443b7f7efbb2c988
3
+ size 9059697000
model-00038.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca89ded9451340abf472f5bc30bbb5c1272b5e9a2146c6f1575fa637965dcbe9
3
+ size 9059697000
model-00039.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e69764a96240a1a4e16cd903c92ce49201cd7b1104dd8a0a2b81d8b48b9f0f6
3
+ size 9059697000
model-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cbf59e8b6320537b82d2ef96872718b87cd24ab6507f67b26727c6a95762125
3
+ size 9059697000
model-00041.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca140518c40597127df06af646fc731ea5efda38a9f1f42cee31b6f28e983d21
3
+ size 9059697000
model-00042.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:277ebce5aeba2c706a3fc59ac07549b8f204a5040ec68ef0aefaf12a5feefa7a
3
+ size 9059697000
model-00043.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1de3b57c62f21111211a1803617d1176d5056117558d8cfe35bab64ea264498
3
+ size 9059697000
model-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19314c5d060804533d321a1d751c675ff882eebd8ccfe26819d8e41c8803a375
3
+ size 6039798000
model.safetensors.index.json ADDED
@@ -0,0 +1,777 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 395531065600
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00002.safetensors",
7
+ "model.embed_tokens.weight": "model-00001.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001.safetensors",
13
+ "model.layers.0.self_attn.g_proj.weight": "model-00001.safetensors",
14
+ "model.layers.0.self_attn.k_norm.weight": "model-00001.safetensors",
15
+ "model.layers.0.self_attn.k_proj.weight": "model-00001.safetensors",
16
+ "model.layers.0.self_attn.o_proj.weight": "model-00001.safetensors",
17
+ "model.layers.0.self_attn.q_norm.weight": "model-00001.safetensors",
18
+ "model.layers.0.self_attn.q_proj.weight": "model-00001.safetensors",
19
+ "model.layers.0.self_attn.v_proj.weight": "model-00001.safetensors",
20
+ "model.layers.1.input_layernorm.weight": "model-00001.safetensors",
21
+ "model.layers.1.mlp.down_proj.weight": "model-00001.safetensors",
22
+ "model.layers.1.mlp.gate_proj.weight": "model-00001.safetensors",
23
+ "model.layers.1.mlp.up_proj.weight": "model-00001.safetensors",
24
+ "model.layers.1.post_attention_layernorm.weight": "model-00001.safetensors",
25
+ "model.layers.1.self_attn.g_proj.weight": "model-00001.safetensors",
26
+ "model.layers.1.self_attn.k_norm.weight": "model-00001.safetensors",
27
+ "model.layers.1.self_attn.k_proj.weight": "model-00001.safetensors",
28
+ "model.layers.1.self_attn.o_proj.weight": "model-00001.safetensors",
29
+ "model.layers.1.self_attn.q_norm.weight": "model-00001.safetensors",
30
+ "model.layers.1.self_attn.q_proj.weight": "model-00001.safetensors",
31
+ "model.layers.1.self_attn.v_proj.weight": "model-00001.safetensors",
32
+ "model.layers.10.input_layernorm.weight": "model-00001.safetensors",
33
+ "model.layers.10.moe.down_proj.weight": "model-00010.safetensors",
34
+ "model.layers.10.moe.gate.weight": "model-00001.safetensors",
35
+ "model.layers.10.moe.gate_proj.weight": "model-00009.safetensors",
36
+ "model.layers.10.moe.router_bias": "model-00001.safetensors",
37
+ "model.layers.10.moe.up_proj.weight": "model-00010.safetensors",
38
+ "model.layers.10.post_attention_layernorm.weight": "model-00001.safetensors",
39
+ "model.layers.10.self_attn.g_proj.weight": "model-00001.safetensors",
40
+ "model.layers.10.self_attn.k_norm.weight": "model-00001.safetensors",
41
+ "model.layers.10.self_attn.k_proj.weight": "model-00001.safetensors",
42
+ "model.layers.10.self_attn.o_proj.weight": "model-00001.safetensors",
43
+ "model.layers.10.self_attn.q_norm.weight": "model-00001.safetensors",
44
+ "model.layers.10.self_attn.q_proj.weight": "model-00001.safetensors",
45
+ "model.layers.10.self_attn.v_proj.weight": "model-00001.safetensors",
46
+ "model.layers.10.share_expert.down_proj.weight": "model-00001.safetensors",
47
+ "model.layers.10.share_expert.gate_proj.weight": "model-00002.safetensors",
48
+ "model.layers.10.share_expert.up_proj.weight": "model-00002.safetensors",
49
+ "model.layers.11.input_layernorm.weight": "model-00001.safetensors",
50
+ "model.layers.11.moe.down_proj.weight": "model-00011.safetensors",
51
+ "model.layers.11.moe.gate.weight": "model-00001.safetensors",
52
+ "model.layers.11.moe.gate_proj.weight": "model-00010.safetensors",
53
+ "model.layers.11.moe.router_bias": "model-00001.safetensors",
54
+ "model.layers.11.moe.up_proj.weight": "model-00011.safetensors",
55
+ "model.layers.11.post_attention_layernorm.weight": "model-00001.safetensors",
56
+ "model.layers.11.self_attn.g_proj.weight": "model-00001.safetensors",
57
+ "model.layers.11.self_attn.k_norm.weight": "model-00001.safetensors",
58
+ "model.layers.11.self_attn.k_proj.weight": "model-00001.safetensors",
59
+ "model.layers.11.self_attn.o_proj.weight": "model-00001.safetensors",
60
+ "model.layers.11.self_attn.q_norm.weight": "model-00001.safetensors",
61
+ "model.layers.11.self_attn.q_proj.weight": "model-00001.safetensors",
62
+ "model.layers.11.self_attn.v_proj.weight": "model-00001.safetensors",
63
+ "model.layers.11.share_expert.down_proj.weight": "model-00001.safetensors",
64
+ "model.layers.11.share_expert.gate_proj.weight": "model-00002.safetensors",
65
+ "model.layers.11.share_expert.up_proj.weight": "model-00002.safetensors",
66
+ "model.layers.12.input_layernorm.weight": "model-00002.safetensors",
67
+ "model.layers.12.moe.down_proj.weight": "model-00012.safetensors",
68
+ "model.layers.12.moe.gate.weight": "model-00002.safetensors",
69
+ "model.layers.12.moe.gate_proj.weight": "model-00011.safetensors",
70
+ "model.layers.12.moe.router_bias": "model-00002.safetensors",
71
+ "model.layers.12.moe.up_proj.weight": "model-00012.safetensors",
72
+ "model.layers.12.post_attention_layernorm.weight": "model-00002.safetensors",
73
+ "model.layers.12.self_attn.g_proj.weight": "model-00002.safetensors",
74
+ "model.layers.12.self_attn.k_norm.weight": "model-00002.safetensors",
75
+ "model.layers.12.self_attn.k_proj.weight": "model-00002.safetensors",
76
+ "model.layers.12.self_attn.o_proj.weight": "model-00002.safetensors",
77
+ "model.layers.12.self_attn.q_norm.weight": "model-00002.safetensors",
78
+ "model.layers.12.self_attn.q_proj.weight": "model-00002.safetensors",
79
+ "model.layers.12.self_attn.v_proj.weight": "model-00002.safetensors",
80
+ "model.layers.12.share_expert.down_proj.weight": "model-00002.safetensors",
81
+ "model.layers.12.share_expert.gate_proj.weight": "model-00002.safetensors",
82
+ "model.layers.12.share_expert.up_proj.weight": "model-00002.safetensors",
83
+ "model.layers.13.input_layernorm.weight": "model-00002.safetensors",
84
+ "model.layers.13.moe.down_proj.weight": "model-00013.safetensors",
85
+ "model.layers.13.moe.gate.weight": "model-00002.safetensors",
86
+ "model.layers.13.moe.gate_proj.weight": "model-00012.safetensors",
87
+ "model.layers.13.moe.router_bias": "model-00002.safetensors",
88
+ "model.layers.13.moe.up_proj.weight": "model-00013.safetensors",
89
+ "model.layers.13.post_attention_layernorm.weight": "model-00002.safetensors",
90
+ "model.layers.13.self_attn.g_proj.weight": "model-00002.safetensors",
91
+ "model.layers.13.self_attn.k_norm.weight": "model-00002.safetensors",
92
+ "model.layers.13.self_attn.k_proj.weight": "model-00002.safetensors",
93
+ "model.layers.13.self_attn.o_proj.weight": "model-00002.safetensors",
94
+ "model.layers.13.self_attn.q_norm.weight": "model-00002.safetensors",
95
+ "model.layers.13.self_attn.q_proj.weight": "model-00002.safetensors",
96
+ "model.layers.13.self_attn.v_proj.weight": "model-00002.safetensors",
97
+ "model.layers.13.share_expert.down_proj.weight": "model-00002.safetensors",
98
+ "model.layers.13.share_expert.gate_proj.weight": "model-00002.safetensors",
99
+ "model.layers.13.share_expert.up_proj.weight": "model-00002.safetensors",
100
+ "model.layers.14.input_layernorm.weight": "model-00002.safetensors",
101
+ "model.layers.14.moe.down_proj.weight": "model-00014.safetensors",
102
+ "model.layers.14.moe.gate.weight": "model-00002.safetensors",
103
+ "model.layers.14.moe.gate_proj.weight": "model-00013.safetensors",
104
+ "model.layers.14.moe.router_bias": "model-00002.safetensors",
105
+ "model.layers.14.moe.up_proj.weight": "model-00014.safetensors",
106
+ "model.layers.14.post_attention_layernorm.weight": "model-00002.safetensors",
107
+ "model.layers.14.self_attn.g_proj.weight": "model-00002.safetensors",
108
+ "model.layers.14.self_attn.k_norm.weight": "model-00002.safetensors",
109
+ "model.layers.14.self_attn.k_proj.weight": "model-00002.safetensors",
110
+ "model.layers.14.self_attn.o_proj.weight": "model-00002.safetensors",
111
+ "model.layers.14.self_attn.q_norm.weight": "model-00002.safetensors",
112
+ "model.layers.14.self_attn.q_proj.weight": "model-00002.safetensors",
113
+ "model.layers.14.self_attn.v_proj.weight": "model-00002.safetensors",
114
+ "model.layers.14.share_expert.down_proj.weight": "model-00002.safetensors",
115
+ "model.layers.14.share_expert.gate_proj.weight": "model-00002.safetensors",
116
+ "model.layers.14.share_expert.up_proj.weight": "model-00002.safetensors",
117
+ "model.layers.15.input_layernorm.weight": "model-00002.safetensors",
118
+ "model.layers.15.moe.down_proj.weight": "model-00015.safetensors",
119
+ "model.layers.15.moe.gate.weight": "model-00002.safetensors",
120
+ "model.layers.15.moe.gate_proj.weight": "model-00014.safetensors",
121
+ "model.layers.15.moe.router_bias": "model-00002.safetensors",
122
+ "model.layers.15.moe.up_proj.weight": "model-00015.safetensors",
123
+ "model.layers.15.post_attention_layernorm.weight": "model-00002.safetensors",
124
+ "model.layers.15.self_attn.g_proj.weight": "model-00002.safetensors",
125
+ "model.layers.15.self_attn.k_norm.weight": "model-00002.safetensors",
126
+ "model.layers.15.self_attn.k_proj.weight": "model-00002.safetensors",
127
+ "model.layers.15.self_attn.o_proj.weight": "model-00002.safetensors",
128
+ "model.layers.15.self_attn.q_norm.weight": "model-00002.safetensors",
129
+ "model.layers.15.self_attn.q_proj.weight": "model-00002.safetensors",
130
+ "model.layers.15.self_attn.v_proj.weight": "model-00002.safetensors",
131
+ "model.layers.15.share_expert.down_proj.weight": "model-00002.safetensors",
132
+ "model.layers.15.share_expert.gate_proj.weight": "model-00002.safetensors",
133
+ "model.layers.15.share_expert.up_proj.weight": "model-00002.safetensors",
134
+ "model.layers.16.input_layernorm.weight": "model-00001.safetensors",
135
+ "model.layers.16.moe.down_proj.weight": "model-00016.safetensors",
136
+ "model.layers.16.moe.gate.weight": "model-00001.safetensors",
137
+ "model.layers.16.moe.gate_proj.weight": "model-00015.safetensors",
138
+ "model.layers.16.moe.router_bias": "model-00001.safetensors",
139
+ "model.layers.16.moe.up_proj.weight": "model-00016.safetensors",
140
+ "model.layers.16.post_attention_layernorm.weight": "model-00001.safetensors",
141
+ "model.layers.16.self_attn.g_proj.weight": "model-00001.safetensors",
142
+ "model.layers.16.self_attn.k_norm.weight": "model-00001.safetensors",
143
+ "model.layers.16.self_attn.k_proj.weight": "model-00001.safetensors",
144
+ "model.layers.16.self_attn.o_proj.weight": "model-00001.safetensors",
145
+ "model.layers.16.self_attn.q_norm.weight": "model-00001.safetensors",
146
+ "model.layers.16.self_attn.q_proj.weight": "model-00001.safetensors",
147
+ "model.layers.16.self_attn.v_proj.weight": "model-00001.safetensors",
148
+ "model.layers.16.share_expert.down_proj.weight": "model-00001.safetensors",
149
+ "model.layers.16.share_expert.gate_proj.weight": "model-00001.safetensors",
150
+ "model.layers.16.share_expert.up_proj.weight": "model-00001.safetensors",
151
+ "model.layers.17.input_layernorm.weight": "model-00001.safetensors",
152
+ "model.layers.17.moe.down_proj.weight": "model-00017.safetensors",
153
+ "model.layers.17.moe.gate.weight": "model-00001.safetensors",
154
+ "model.layers.17.moe.gate_proj.weight": "model-00016.safetensors",
155
+ "model.layers.17.moe.router_bias": "model-00001.safetensors",
156
+ "model.layers.17.moe.up_proj.weight": "model-00017.safetensors",
157
+ "model.layers.17.post_attention_layernorm.weight": "model-00001.safetensors",
158
+ "model.layers.17.self_attn.g_proj.weight": "model-00001.safetensors",
159
+ "model.layers.17.self_attn.k_norm.weight": "model-00001.safetensors",
160
+ "model.layers.17.self_attn.k_proj.weight": "model-00001.safetensors",
161
+ "model.layers.17.self_attn.o_proj.weight": "model-00001.safetensors",
162
+ "model.layers.17.self_attn.q_norm.weight": "model-00001.safetensors",
163
+ "model.layers.17.self_attn.q_proj.weight": "model-00001.safetensors",
164
+ "model.layers.17.self_attn.v_proj.weight": "model-00001.safetensors",
165
+ "model.layers.17.share_expert.down_proj.weight": "model-00001.safetensors",
166
+ "model.layers.17.share_expert.gate_proj.weight": "model-00001.safetensors",
167
+ "model.layers.17.share_expert.up_proj.weight": "model-00001.safetensors",
168
+ "model.layers.18.input_layernorm.weight": "model-00001.safetensors",
169
+ "model.layers.18.moe.down_proj.weight": "model-00018.safetensors",
170
+ "model.layers.18.moe.gate.weight": "model-00001.safetensors",
171
+ "model.layers.18.moe.gate_proj.weight": "model-00017.safetensors",
172
+ "model.layers.18.moe.router_bias": "model-00001.safetensors",
173
+ "model.layers.18.moe.up_proj.weight": "model-00018.safetensors",
174
+ "model.layers.18.post_attention_layernorm.weight": "model-00001.safetensors",
175
+ "model.layers.18.self_attn.g_proj.weight": "model-00001.safetensors",
176
+ "model.layers.18.self_attn.k_norm.weight": "model-00001.safetensors",
177
+ "model.layers.18.self_attn.k_proj.weight": "model-00001.safetensors",
178
+ "model.layers.18.self_attn.o_proj.weight": "model-00001.safetensors",
179
+ "model.layers.18.self_attn.q_norm.weight": "model-00001.safetensors",
180
+ "model.layers.18.self_attn.q_proj.weight": "model-00001.safetensors",
181
+ "model.layers.18.self_attn.v_proj.weight": "model-00001.safetensors",
182
+ "model.layers.18.share_expert.down_proj.weight": "model-00001.safetensors",
183
+ "model.layers.18.share_expert.gate_proj.weight": "model-00001.safetensors",
184
+ "model.layers.18.share_expert.up_proj.weight": "model-00001.safetensors",
185
+ "model.layers.19.input_layernorm.weight": "model-00001.safetensors",
186
+ "model.layers.19.moe.down_proj.weight": "model-00019.safetensors",
187
+ "model.layers.19.moe.gate.weight": "model-00001.safetensors",
188
+ "model.layers.19.moe.gate_proj.weight": "model-00018.safetensors",
189
+ "model.layers.19.moe.router_bias": "model-00001.safetensors",
190
+ "model.layers.19.moe.up_proj.weight": "model-00019.safetensors",
191
+ "model.layers.19.post_attention_layernorm.weight": "model-00001.safetensors",
192
+ "model.layers.19.self_attn.g_proj.weight": "model-00001.safetensors",
193
+ "model.layers.19.self_attn.k_norm.weight": "model-00001.safetensors",
194
+ "model.layers.19.self_attn.k_proj.weight": "model-00001.safetensors",
195
+ "model.layers.19.self_attn.o_proj.weight": "model-00001.safetensors",
196
+ "model.layers.19.self_attn.q_norm.weight": "model-00001.safetensors",
197
+ "model.layers.19.self_attn.q_proj.weight": "model-00001.safetensors",
198
+ "model.layers.19.self_attn.v_proj.weight": "model-00001.safetensors",
199
+ "model.layers.19.share_expert.down_proj.weight": "model-00001.safetensors",
200
+ "model.layers.19.share_expert.gate_proj.weight": "model-00001.safetensors",
201
+ "model.layers.19.share_expert.up_proj.weight": "model-00001.safetensors",
202
+ "model.layers.2.input_layernorm.weight": "model-00001.safetensors",
203
+ "model.layers.2.mlp.down_proj.weight": "model-00001.safetensors",
204
+ "model.layers.2.mlp.gate_proj.weight": "model-00001.safetensors",
205
+ "model.layers.2.mlp.up_proj.weight": "model-00001.safetensors",
206
+ "model.layers.2.post_attention_layernorm.weight": "model-00001.safetensors",
207
+ "model.layers.2.self_attn.g_proj.weight": "model-00001.safetensors",
208
+ "model.layers.2.self_attn.k_norm.weight": "model-00001.safetensors",
209
+ "model.layers.2.self_attn.k_proj.weight": "model-00001.safetensors",
210
+ "model.layers.2.self_attn.o_proj.weight": "model-00001.safetensors",
211
+ "model.layers.2.self_attn.q_norm.weight": "model-00001.safetensors",
212
+ "model.layers.2.self_attn.q_proj.weight": "model-00001.safetensors",
213
+ "model.layers.2.self_attn.v_proj.weight": "model-00001.safetensors",
214
+ "model.layers.20.input_layernorm.weight": "model-00001.safetensors",
215
+ "model.layers.20.moe.down_proj.weight": "model-00020.safetensors",
216
+ "model.layers.20.moe.gate.weight": "model-00001.safetensors",
217
+ "model.layers.20.moe.gate_proj.weight": "model-00019.safetensors",
218
+ "model.layers.20.moe.router_bias": "model-00001.safetensors",
219
+ "model.layers.20.moe.up_proj.weight": "model-00020.safetensors",
220
+ "model.layers.20.post_attention_layernorm.weight": "model-00001.safetensors",
221
+ "model.layers.20.self_attn.g_proj.weight": "model-00001.safetensors",
222
+ "model.layers.20.self_attn.k_norm.weight": "model-00001.safetensors",
223
+ "model.layers.20.self_attn.k_proj.weight": "model-00001.safetensors",
224
+ "model.layers.20.self_attn.o_proj.weight": "model-00001.safetensors",
225
+ "model.layers.20.self_attn.q_norm.weight": "model-00001.safetensors",
226
+ "model.layers.20.self_attn.q_proj.weight": "model-00001.safetensors",
227
+ "model.layers.20.self_attn.v_proj.weight": "model-00001.safetensors",
228
+ "model.layers.20.share_expert.down_proj.weight": "model-00001.safetensors",
229
+ "model.layers.20.share_expert.gate_proj.weight": "model-00001.safetensors",
230
+ "model.layers.20.share_expert.up_proj.weight": "model-00001.safetensors",
231
+ "model.layers.21.input_layernorm.weight": "model-00001.safetensors",
232
+ "model.layers.21.moe.down_proj.weight": "model-00021.safetensors",
233
+ "model.layers.21.moe.gate.weight": "model-00001.safetensors",
234
+ "model.layers.21.moe.gate_proj.weight": "model-00020.safetensors",
235
+ "model.layers.21.moe.router_bias": "model-00001.safetensors",
236
+ "model.layers.21.moe.up_proj.weight": "model-00021.safetensors",
237
+ "model.layers.21.post_attention_layernorm.weight": "model-00001.safetensors",
238
+ "model.layers.21.self_attn.g_proj.weight": "model-00001.safetensors",
239
+ "model.layers.21.self_attn.k_norm.weight": "model-00001.safetensors",
240
+ "model.layers.21.self_attn.k_proj.weight": "model-00001.safetensors",
241
+ "model.layers.21.self_attn.o_proj.weight": "model-00001.safetensors",
242
+ "model.layers.21.self_attn.q_norm.weight": "model-00001.safetensors",
243
+ "model.layers.21.self_attn.q_proj.weight": "model-00001.safetensors",
244
+ "model.layers.21.self_attn.v_proj.weight": "model-00001.safetensors",
245
+ "model.layers.21.share_expert.down_proj.weight": "model-00001.safetensors",
246
+ "model.layers.21.share_expert.gate_proj.weight": "model-00001.safetensors",
247
+ "model.layers.21.share_expert.up_proj.weight": "model-00001.safetensors",
248
+ "model.layers.22.input_layernorm.weight": "model-00001.safetensors",
249
+ "model.layers.22.moe.down_proj.weight": "model-00022.safetensors",
250
+ "model.layers.22.moe.gate.weight": "model-00001.safetensors",
251
+ "model.layers.22.moe.gate_proj.weight": "model-00021.safetensors",
252
+ "model.layers.22.moe.router_bias": "model-00001.safetensors",
253
+ "model.layers.22.moe.up_proj.weight": "model-00022.safetensors",
254
+ "model.layers.22.post_attention_layernorm.weight": "model-00001.safetensors",
255
+ "model.layers.22.self_attn.g_proj.weight": "model-00001.safetensors",
256
+ "model.layers.22.self_attn.k_norm.weight": "model-00001.safetensors",
257
+ "model.layers.22.self_attn.k_proj.weight": "model-00001.safetensors",
258
+ "model.layers.22.self_attn.o_proj.weight": "model-00001.safetensors",
259
+ "model.layers.22.self_attn.q_norm.weight": "model-00001.safetensors",
260
+ "model.layers.22.self_attn.q_proj.weight": "model-00001.safetensors",
261
+ "model.layers.22.self_attn.v_proj.weight": "model-00001.safetensors",
262
+ "model.layers.22.share_expert.down_proj.weight": "model-00001.safetensors",
263
+ "model.layers.22.share_expert.gate_proj.weight": "model-00001.safetensors",
264
+ "model.layers.22.share_expert.up_proj.weight": "model-00001.safetensors",
265
+ "model.layers.23.input_layernorm.weight": "model-00001.safetensors",
266
+ "model.layers.23.moe.down_proj.weight": "model-00023.safetensors",
267
+ "model.layers.23.moe.gate.weight": "model-00001.safetensors",
268
+ "model.layers.23.moe.gate_proj.weight": "model-00022.safetensors",
269
+ "model.layers.23.moe.router_bias": "model-00001.safetensors",
270
+ "model.layers.23.moe.up_proj.weight": "model-00023.safetensors",
271
+ "model.layers.23.post_attention_layernorm.weight": "model-00001.safetensors",
272
+ "model.layers.23.self_attn.g_proj.weight": "model-00001.safetensors",
273
+ "model.layers.23.self_attn.k_norm.weight": "model-00001.safetensors",
274
+ "model.layers.23.self_attn.k_proj.weight": "model-00001.safetensors",
275
+ "model.layers.23.self_attn.o_proj.weight": "model-00001.safetensors",
276
+ "model.layers.23.self_attn.q_norm.weight": "model-00001.safetensors",
277
+ "model.layers.23.self_attn.q_proj.weight": "model-00001.safetensors",
278
+ "model.layers.23.self_attn.v_proj.weight": "model-00001.safetensors",
279
+ "model.layers.23.share_expert.down_proj.weight": "model-00001.safetensors",
280
+ "model.layers.23.share_expert.gate_proj.weight": "model-00001.safetensors",
281
+ "model.layers.23.share_expert.up_proj.weight": "model-00001.safetensors",
282
+ "model.layers.24.input_layernorm.weight": "model-00001.safetensors",
283
+ "model.layers.24.moe.down_proj.weight": "model-00024.safetensors",
284
+ "model.layers.24.moe.gate.weight": "model-00001.safetensors",
285
+ "model.layers.24.moe.gate_proj.weight": "model-00023.safetensors",
286
+ "model.layers.24.moe.router_bias": "model-00001.safetensors",
287
+ "model.layers.24.moe.up_proj.weight": "model-00024.safetensors",
288
+ "model.layers.24.post_attention_layernorm.weight": "model-00001.safetensors",
289
+ "model.layers.24.self_attn.g_proj.weight": "model-00001.safetensors",
290
+ "model.layers.24.self_attn.k_norm.weight": "model-00001.safetensors",
291
+ "model.layers.24.self_attn.k_proj.weight": "model-00001.safetensors",
292
+ "model.layers.24.self_attn.o_proj.weight": "model-00001.safetensors",
293
+ "model.layers.24.self_attn.q_norm.weight": "model-00001.safetensors",
294
+ "model.layers.24.self_attn.q_proj.weight": "model-00001.safetensors",
295
+ "model.layers.24.self_attn.v_proj.weight": "model-00001.safetensors",
296
+ "model.layers.24.share_expert.down_proj.weight": "model-00001.safetensors",
297
+ "model.layers.24.share_expert.gate_proj.weight": "model-00001.safetensors",
298
+ "model.layers.24.share_expert.up_proj.weight": "model-00001.safetensors",
299
+ "model.layers.25.input_layernorm.weight": "model-00001.safetensors",
300
+ "model.layers.25.moe.down_proj.weight": "model-00025.safetensors",
301
+ "model.layers.25.moe.gate.weight": "model-00001.safetensors",
302
+ "model.layers.25.moe.gate_proj.weight": "model-00024.safetensors",
303
+ "model.layers.25.moe.router_bias": "model-00001.safetensors",
304
+ "model.layers.25.moe.up_proj.weight": "model-00025.safetensors",
305
+ "model.layers.25.post_attention_layernorm.weight": "model-00001.safetensors",
306
+ "model.layers.25.self_attn.g_proj.weight": "model-00001.safetensors",
307
+ "model.layers.25.self_attn.k_norm.weight": "model-00001.safetensors",
308
+ "model.layers.25.self_attn.k_proj.weight": "model-00001.safetensors",
309
+ "model.layers.25.self_attn.o_proj.weight": "model-00001.safetensors",
310
+ "model.layers.25.self_attn.q_norm.weight": "model-00001.safetensors",
311
+ "model.layers.25.self_attn.q_proj.weight": "model-00001.safetensors",
312
+ "model.layers.25.self_attn.v_proj.weight": "model-00001.safetensors",
313
+ "model.layers.25.share_expert.down_proj.weight": "model-00001.safetensors",
314
+ "model.layers.25.share_expert.gate_proj.weight": "model-00001.safetensors",
315
+ "model.layers.25.share_expert.up_proj.weight": "model-00001.safetensors",
316
+ "model.layers.26.input_layernorm.weight": "model-00001.safetensors",
317
+ "model.layers.26.moe.down_proj.weight": "model-00026.safetensors",
318
+ "model.layers.26.moe.gate.weight": "model-00001.safetensors",
319
+ "model.layers.26.moe.gate_proj.weight": "model-00025.safetensors",
320
+ "model.layers.26.moe.router_bias": "model-00001.safetensors",
321
+ "model.layers.26.moe.up_proj.weight": "model-00026.safetensors",
322
+ "model.layers.26.post_attention_layernorm.weight": "model-00001.safetensors",
323
+ "model.layers.26.self_attn.g_proj.weight": "model-00001.safetensors",
324
+ "model.layers.26.self_attn.k_norm.weight": "model-00001.safetensors",
325
+ "model.layers.26.self_attn.k_proj.weight": "model-00001.safetensors",
326
+ "model.layers.26.self_attn.o_proj.weight": "model-00001.safetensors",
327
+ "model.layers.26.self_attn.q_norm.weight": "model-00001.safetensors",
328
+ "model.layers.26.self_attn.q_proj.weight": "model-00001.safetensors",
329
+ "model.layers.26.self_attn.v_proj.weight": "model-00001.safetensors",
330
+ "model.layers.26.share_expert.down_proj.weight": "model-00001.safetensors",
331
+ "model.layers.26.share_expert.gate_proj.weight": "model-00002.safetensors",
332
+ "model.layers.26.share_expert.up_proj.weight": "model-00002.safetensors",
333
+ "model.layers.27.input_layernorm.weight": "model-00001.safetensors",
334
+ "model.layers.27.moe.down_proj.weight": "model-00027.safetensors",
335
+ "model.layers.27.moe.gate.weight": "model-00001.safetensors",
336
+ "model.layers.27.moe.gate_proj.weight": "model-00026.safetensors",
337
+ "model.layers.27.moe.router_bias": "model-00001.safetensors",
338
+ "model.layers.27.moe.up_proj.weight": "model-00027.safetensors",
339
+ "model.layers.27.post_attention_layernorm.weight": "model-00001.safetensors",
340
+ "model.layers.27.self_attn.g_proj.weight": "model-00001.safetensors",
341
+ "model.layers.27.self_attn.k_norm.weight": "model-00001.safetensors",
342
+ "model.layers.27.self_attn.k_proj.weight": "model-00001.safetensors",
343
+ "model.layers.27.self_attn.o_proj.weight": "model-00001.safetensors",
344
+ "model.layers.27.self_attn.q_norm.weight": "model-00001.safetensors",
345
+ "model.layers.27.self_attn.q_proj.weight": "model-00001.safetensors",
346
+ "model.layers.27.self_attn.v_proj.weight": "model-00001.safetensors",
347
+ "model.layers.27.share_expert.down_proj.weight": "model-00001.safetensors",
348
+ "model.layers.27.share_expert.gate_proj.weight": "model-00002.safetensors",
349
+ "model.layers.27.share_expert.up_proj.weight": "model-00002.safetensors",
350
+ "model.layers.28.input_layernorm.weight": "model-00002.safetensors",
351
+ "model.layers.28.moe.down_proj.weight": "model-00028.safetensors",
352
+ "model.layers.28.moe.gate.weight": "model-00002.safetensors",
353
+ "model.layers.28.moe.gate_proj.weight": "model-00027.safetensors",
354
+ "model.layers.28.moe.router_bias": "model-00002.safetensors",
355
+ "model.layers.28.moe.up_proj.weight": "model-00028.safetensors",
356
+ "model.layers.28.post_attention_layernorm.weight": "model-00002.safetensors",
357
+ "model.layers.28.self_attn.g_proj.weight": "model-00002.safetensors",
358
+ "model.layers.28.self_attn.k_norm.weight": "model-00002.safetensors",
359
+ "model.layers.28.self_attn.k_proj.weight": "model-00002.safetensors",
360
+ "model.layers.28.self_attn.o_proj.weight": "model-00002.safetensors",
361
+ "model.layers.28.self_attn.q_norm.weight": "model-00002.safetensors",
362
+ "model.layers.28.self_attn.q_proj.weight": "model-00002.safetensors",
363
+ "model.layers.28.self_attn.v_proj.weight": "model-00002.safetensors",
364
+ "model.layers.28.share_expert.down_proj.weight": "model-00002.safetensors",
365
+ "model.layers.28.share_expert.gate_proj.weight": "model-00002.safetensors",
366
+ "model.layers.28.share_expert.up_proj.weight": "model-00002.safetensors",
367
+ "model.layers.29.input_layernorm.weight": "model-00002.safetensors",
368
+ "model.layers.29.moe.down_proj.weight": "model-00029.safetensors",
369
+ "model.layers.29.moe.gate.weight": "model-00002.safetensors",
370
+ "model.layers.29.moe.gate_proj.weight": "model-00028.safetensors",
371
+ "model.layers.29.moe.router_bias": "model-00002.safetensors",
372
+ "model.layers.29.moe.up_proj.weight": "model-00029.safetensors",
373
+ "model.layers.29.post_attention_layernorm.weight": "model-00002.safetensors",
374
+ "model.layers.29.self_attn.g_proj.weight": "model-00002.safetensors",
375
+ "model.layers.29.self_attn.k_norm.weight": "model-00002.safetensors",
376
+ "model.layers.29.self_attn.k_proj.weight": "model-00002.safetensors",
377
+ "model.layers.29.self_attn.o_proj.weight": "model-00002.safetensors",
378
+ "model.layers.29.self_attn.q_norm.weight": "model-00002.safetensors",
379
+ "model.layers.29.self_attn.q_proj.weight": "model-00002.safetensors",
380
+ "model.layers.29.self_attn.v_proj.weight": "model-00002.safetensors",
381
+ "model.layers.29.share_expert.down_proj.weight": "model-00002.safetensors",
382
+ "model.layers.29.share_expert.gate_proj.weight": "model-00002.safetensors",
383
+ "model.layers.29.share_expert.up_proj.weight": "model-00002.safetensors",
384
+ "model.layers.3.input_layernorm.weight": "model-00001.safetensors",
385
+ "model.layers.3.moe.down_proj.weight": "model-00003.safetensors",
386
+ "model.layers.3.moe.gate.weight": "model-00001.safetensors",
387
+ "model.layers.3.moe.gate_proj.weight": "model-00002.safetensors",
388
+ "model.layers.3.moe.router_bias": "model-00001.safetensors",
389
+ "model.layers.3.moe.up_proj.weight": "model-00003.safetensors",
390
+ "model.layers.3.post_attention_layernorm.weight": "model-00001.safetensors",
391
+ "model.layers.3.self_attn.g_proj.weight": "model-00001.safetensors",
392
+ "model.layers.3.self_attn.k_norm.weight": "model-00001.safetensors",
393
+ "model.layers.3.self_attn.k_proj.weight": "model-00001.safetensors",
394
+ "model.layers.3.self_attn.o_proj.weight": "model-00001.safetensors",
395
+ "model.layers.3.self_attn.q_norm.weight": "model-00001.safetensors",
396
+ "model.layers.3.self_attn.q_proj.weight": "model-00001.safetensors",
397
+ "model.layers.3.self_attn.v_proj.weight": "model-00001.safetensors",
398
+ "model.layers.3.share_expert.down_proj.weight": "model-00001.safetensors",
399
+ "model.layers.3.share_expert.gate_proj.weight": "model-00001.safetensors",
400
+ "model.layers.3.share_expert.up_proj.weight": "model-00001.safetensors",
401
+ "model.layers.30.input_layernorm.weight": "model-00002.safetensors",
402
+ "model.layers.30.moe.down_proj.weight": "model-00030.safetensors",
403
+ "model.layers.30.moe.gate.weight": "model-00002.safetensors",
404
+ "model.layers.30.moe.gate_proj.weight": "model-00029.safetensors",
405
+ "model.layers.30.moe.router_bias": "model-00002.safetensors",
406
+ "model.layers.30.moe.up_proj.weight": "model-00030.safetensors",
407
+ "model.layers.30.post_attention_layernorm.weight": "model-00002.safetensors",
408
+ "model.layers.30.self_attn.g_proj.weight": "model-00002.safetensors",
409
+ "model.layers.30.self_attn.k_norm.weight": "model-00002.safetensors",
410
+ "model.layers.30.self_attn.k_proj.weight": "model-00002.safetensors",
411
+ "model.layers.30.self_attn.o_proj.weight": "model-00002.safetensors",
412
+ "model.layers.30.self_attn.q_norm.weight": "model-00002.safetensors",
413
+ "model.layers.30.self_attn.q_proj.weight": "model-00002.safetensors",
414
+ "model.layers.30.self_attn.v_proj.weight": "model-00002.safetensors",
415
+ "model.layers.30.share_expert.down_proj.weight": "model-00002.safetensors",
416
+ "model.layers.30.share_expert.gate_proj.weight": "model-00002.safetensors",
417
+ "model.layers.30.share_expert.up_proj.weight": "model-00002.safetensors",
418
+ "model.layers.31.input_layernorm.weight": "model-00002.safetensors",
419
+ "model.layers.31.moe.down_proj.weight": "model-00031.safetensors",
420
+ "model.layers.31.moe.gate.weight": "model-00002.safetensors",
421
+ "model.layers.31.moe.gate_proj.weight": "model-00030.safetensors",
422
+ "model.layers.31.moe.router_bias": "model-00002.safetensors",
423
+ "model.layers.31.moe.up_proj.weight": "model-00031.safetensors",
424
+ "model.layers.31.post_attention_layernorm.weight": "model-00002.safetensors",
425
+ "model.layers.31.self_attn.g_proj.weight": "model-00002.safetensors",
426
+ "model.layers.31.self_attn.k_norm.weight": "model-00002.safetensors",
427
+ "model.layers.31.self_attn.k_proj.weight": "model-00002.safetensors",
428
+ "model.layers.31.self_attn.o_proj.weight": "model-00002.safetensors",
429
+ "model.layers.31.self_attn.q_norm.weight": "model-00002.safetensors",
430
+ "model.layers.31.self_attn.q_proj.weight": "model-00002.safetensors",
431
+ "model.layers.31.self_attn.v_proj.weight": "model-00002.safetensors",
432
+ "model.layers.31.share_expert.down_proj.weight": "model-00002.safetensors",
433
+ "model.layers.31.share_expert.gate_proj.weight": "model-00002.safetensors",
434
+ "model.layers.31.share_expert.up_proj.weight": "model-00002.safetensors",
435
+ "model.layers.32.input_layernorm.weight": "model-00001.safetensors",
436
+ "model.layers.32.moe.down_proj.weight": "model-00032.safetensors",
437
+ "model.layers.32.moe.gate.weight": "model-00001.safetensors",
438
+ "model.layers.32.moe.gate_proj.weight": "model-00031.safetensors",
439
+ "model.layers.32.moe.router_bias": "model-00001.safetensors",
440
+ "model.layers.32.moe.up_proj.weight": "model-00032.safetensors",
441
+ "model.layers.32.post_attention_layernorm.weight": "model-00001.safetensors",
442
+ "model.layers.32.self_attn.g_proj.weight": "model-00001.safetensors",
443
+ "model.layers.32.self_attn.k_norm.weight": "model-00001.safetensors",
444
+ "model.layers.32.self_attn.k_proj.weight": "model-00001.safetensors",
445
+ "model.layers.32.self_attn.o_proj.weight": "model-00001.safetensors",
446
+ "model.layers.32.self_attn.q_norm.weight": "model-00001.safetensors",
447
+ "model.layers.32.self_attn.q_proj.weight": "model-00001.safetensors",
448
+ "model.layers.32.self_attn.v_proj.weight": "model-00001.safetensors",
449
+ "model.layers.32.share_expert.down_proj.weight": "model-00001.safetensors",
450
+ "model.layers.32.share_expert.gate_proj.weight": "model-00001.safetensors",
451
+ "model.layers.32.share_expert.up_proj.weight": "model-00001.safetensors",
452
+ "model.layers.33.input_layernorm.weight": "model-00001.safetensors",
453
+ "model.layers.33.moe.down_proj.weight": "model-00033.safetensors",
454
+ "model.layers.33.moe.gate.weight": "model-00001.safetensors",
455
+ "model.layers.33.moe.gate_proj.weight": "model-00032.safetensors",
456
+ "model.layers.33.moe.router_bias": "model-00001.safetensors",
457
+ "model.layers.33.moe.up_proj.weight": "model-00033.safetensors",
458
+ "model.layers.33.post_attention_layernorm.weight": "model-00001.safetensors",
459
+ "model.layers.33.self_attn.g_proj.weight": "model-00001.safetensors",
460
+ "model.layers.33.self_attn.k_norm.weight": "model-00001.safetensors",
461
+ "model.layers.33.self_attn.k_proj.weight": "model-00001.safetensors",
462
+ "model.layers.33.self_attn.o_proj.weight": "model-00001.safetensors",
463
+ "model.layers.33.self_attn.q_norm.weight": "model-00001.safetensors",
464
+ "model.layers.33.self_attn.q_proj.weight": "model-00001.safetensors",
465
+ "model.layers.33.self_attn.v_proj.weight": "model-00001.safetensors",
466
+ "model.layers.33.share_expert.down_proj.weight": "model-00001.safetensors",
467
+ "model.layers.33.share_expert.gate_proj.weight": "model-00001.safetensors",
468
+ "model.layers.33.share_expert.up_proj.weight": "model-00001.safetensors",
469
+ "model.layers.34.input_layernorm.weight": "model-00001.safetensors",
470
+ "model.layers.34.moe.down_proj.weight": "model-00034.safetensors",
471
+ "model.layers.34.moe.gate.weight": "model-00001.safetensors",
472
+ "model.layers.34.moe.gate_proj.weight": "model-00033.safetensors",
473
+ "model.layers.34.moe.router_bias": "model-00001.safetensors",
474
+ "model.layers.34.moe.up_proj.weight": "model-00034.safetensors",
475
+ "model.layers.34.post_attention_layernorm.weight": "model-00001.safetensors",
476
+ "model.layers.34.self_attn.g_proj.weight": "model-00001.safetensors",
477
+ "model.layers.34.self_attn.k_norm.weight": "model-00001.safetensors",
478
+ "model.layers.34.self_attn.k_proj.weight": "model-00001.safetensors",
479
+ "model.layers.34.self_attn.o_proj.weight": "model-00001.safetensors",
480
+ "model.layers.34.self_attn.q_norm.weight": "model-00001.safetensors",
481
+ "model.layers.34.self_attn.q_proj.weight": "model-00001.safetensors",
482
+ "model.layers.34.self_attn.v_proj.weight": "model-00001.safetensors",
483
+ "model.layers.34.share_expert.down_proj.weight": "model-00001.safetensors",
484
+ "model.layers.34.share_expert.gate_proj.weight": "model-00001.safetensors",
485
+ "model.layers.34.share_expert.up_proj.weight": "model-00001.safetensors",
486
+ "model.layers.35.input_layernorm.weight": "model-00001.safetensors",
487
+ "model.layers.35.moe.down_proj.weight": "model-00035.safetensors",
488
+ "model.layers.35.moe.gate.weight": "model-00001.safetensors",
489
+ "model.layers.35.moe.gate_proj.weight": "model-00034.safetensors",
490
+ "model.layers.35.moe.router_bias": "model-00001.safetensors",
491
+ "model.layers.35.moe.up_proj.weight": "model-00035.safetensors",
492
+ "model.layers.35.post_attention_layernorm.weight": "model-00001.safetensors",
493
+ "model.layers.35.self_attn.g_proj.weight": "model-00001.safetensors",
494
+ "model.layers.35.self_attn.k_norm.weight": "model-00001.safetensors",
495
+ "model.layers.35.self_attn.k_proj.weight": "model-00001.safetensors",
496
+ "model.layers.35.self_attn.o_proj.weight": "model-00001.safetensors",
497
+ "model.layers.35.self_attn.q_norm.weight": "model-00001.safetensors",
498
+ "model.layers.35.self_attn.q_proj.weight": "model-00001.safetensors",
499
+ "model.layers.35.self_attn.v_proj.weight": "model-00001.safetensors",
500
+ "model.layers.35.share_expert.down_proj.weight": "model-00001.safetensors",
501
+ "model.layers.35.share_expert.gate_proj.weight": "model-00001.safetensors",
502
+ "model.layers.35.share_expert.up_proj.weight": "model-00001.safetensors",
503
+ "model.layers.36.input_layernorm.weight": "model-00001.safetensors",
504
+ "model.layers.36.moe.down_proj.weight": "model-00036.safetensors",
505
+ "model.layers.36.moe.gate.weight": "model-00001.safetensors",
506
+ "model.layers.36.moe.gate_proj.weight": "model-00035.safetensors",
507
+ "model.layers.36.moe.router_bias": "model-00001.safetensors",
508
+ "model.layers.36.moe.up_proj.weight": "model-00036.safetensors",
509
+ "model.layers.36.post_attention_layernorm.weight": "model-00001.safetensors",
510
+ "model.layers.36.self_attn.g_proj.weight": "model-00001.safetensors",
511
+ "model.layers.36.self_attn.k_norm.weight": "model-00001.safetensors",
512
+ "model.layers.36.self_attn.k_proj.weight": "model-00001.safetensors",
513
+ "model.layers.36.self_attn.o_proj.weight": "model-00001.safetensors",
514
+ "model.layers.36.self_attn.q_norm.weight": "model-00001.safetensors",
515
+ "model.layers.36.self_attn.q_proj.weight": "model-00001.safetensors",
516
+ "model.layers.36.self_attn.v_proj.weight": "model-00001.safetensors",
517
+ "model.layers.36.share_expert.down_proj.weight": "model-00001.safetensors",
518
+ "model.layers.36.share_expert.gate_proj.weight": "model-00001.safetensors",
519
+ "model.layers.36.share_expert.up_proj.weight": "model-00001.safetensors",
520
+ "model.layers.37.input_layernorm.weight": "model-00001.safetensors",
521
+ "model.layers.37.moe.down_proj.weight": "model-00037.safetensors",
522
+ "model.layers.37.moe.gate.weight": "model-00001.safetensors",
523
+ "model.layers.37.moe.gate_proj.weight": "model-00036.safetensors",
524
+ "model.layers.37.moe.router_bias": "model-00001.safetensors",
525
+ "model.layers.37.moe.up_proj.weight": "model-00037.safetensors",
526
+ "model.layers.37.post_attention_layernorm.weight": "model-00001.safetensors",
527
+ "model.layers.37.self_attn.g_proj.weight": "model-00001.safetensors",
528
+ "model.layers.37.self_attn.k_norm.weight": "model-00001.safetensors",
529
+ "model.layers.37.self_attn.k_proj.weight": "model-00001.safetensors",
530
+ "model.layers.37.self_attn.o_proj.weight": "model-00001.safetensors",
531
+ "model.layers.37.self_attn.q_norm.weight": "model-00001.safetensors",
532
+ "model.layers.37.self_attn.q_proj.weight": "model-00001.safetensors",
533
+ "model.layers.37.self_attn.v_proj.weight": "model-00001.safetensors",
534
+ "model.layers.37.share_expert.down_proj.weight": "model-00001.safetensors",
535
+ "model.layers.37.share_expert.gate_proj.weight": "model-00001.safetensors",
536
+ "model.layers.37.share_expert.up_proj.weight": "model-00001.safetensors",
537
+ "model.layers.38.input_layernorm.weight": "model-00001.safetensors",
538
+ "model.layers.38.moe.down_proj.weight": "model-00038.safetensors",
539
+ "model.layers.38.moe.gate.weight": "model-00001.safetensors",
540
+ "model.layers.38.moe.gate_proj.weight": "model-00037.safetensors",
541
+ "model.layers.38.moe.router_bias": "model-00001.safetensors",
542
+ "model.layers.38.moe.up_proj.weight": "model-00038.safetensors",
543
+ "model.layers.38.post_attention_layernorm.weight": "model-00001.safetensors",
544
+ "model.layers.38.self_attn.g_proj.weight": "model-00001.safetensors",
545
+ "model.layers.38.self_attn.k_norm.weight": "model-00001.safetensors",
546
+ "model.layers.38.self_attn.k_proj.weight": "model-00001.safetensors",
547
+ "model.layers.38.self_attn.o_proj.weight": "model-00001.safetensors",
548
+ "model.layers.38.self_attn.q_norm.weight": "model-00001.safetensors",
549
+ "model.layers.38.self_attn.q_proj.weight": "model-00001.safetensors",
550
+ "model.layers.38.self_attn.v_proj.weight": "model-00001.safetensors",
551
+ "model.layers.38.share_expert.down_proj.weight": "model-00001.safetensors",
552
+ "model.layers.38.share_expert.gate_proj.weight": "model-00001.safetensors",
553
+ "model.layers.38.share_expert.up_proj.weight": "model-00001.safetensors",
554
+ "model.layers.39.input_layernorm.weight": "model-00001.safetensors",
555
+ "model.layers.39.moe.down_proj.weight": "model-00039.safetensors",
556
+ "model.layers.39.moe.gate.weight": "model-00001.safetensors",
557
+ "model.layers.39.moe.gate_proj.weight": "model-00038.safetensors",
558
+ "model.layers.39.moe.router_bias": "model-00001.safetensors",
559
+ "model.layers.39.moe.up_proj.weight": "model-00039.safetensors",
560
+ "model.layers.39.post_attention_layernorm.weight": "model-00001.safetensors",
561
+ "model.layers.39.self_attn.g_proj.weight": "model-00001.safetensors",
562
+ "model.layers.39.self_attn.k_norm.weight": "model-00001.safetensors",
563
+ "model.layers.39.self_attn.k_proj.weight": "model-00001.safetensors",
564
+ "model.layers.39.self_attn.o_proj.weight": "model-00001.safetensors",
565
+ "model.layers.39.self_attn.q_norm.weight": "model-00001.safetensors",
566
+ "model.layers.39.self_attn.q_proj.weight": "model-00001.safetensors",
567
+ "model.layers.39.self_attn.v_proj.weight": "model-00001.safetensors",
568
+ "model.layers.39.share_expert.down_proj.weight": "model-00001.safetensors",
569
+ "model.layers.39.share_expert.gate_proj.weight": "model-00001.safetensors",
570
+ "model.layers.39.share_expert.up_proj.weight": "model-00001.safetensors",
571
+ "model.layers.4.input_layernorm.weight": "model-00001.safetensors",
572
+ "model.layers.4.moe.down_proj.weight": "model-00004.safetensors",
573
+ "model.layers.4.moe.gate.weight": "model-00001.safetensors",
574
+ "model.layers.4.moe.gate_proj.weight": "model-00003.safetensors",
575
+ "model.layers.4.moe.router_bias": "model-00001.safetensors",
576
+ "model.layers.4.moe.up_proj.weight": "model-00004.safetensors",
577
+ "model.layers.4.post_attention_layernorm.weight": "model-00001.safetensors",
578
+ "model.layers.4.self_attn.g_proj.weight": "model-00001.safetensors",
579
+ "model.layers.4.self_attn.k_norm.weight": "model-00001.safetensors",
580
+ "model.layers.4.self_attn.k_proj.weight": "model-00001.safetensors",
581
+ "model.layers.4.self_attn.o_proj.weight": "model-00001.safetensors",
582
+ "model.layers.4.self_attn.q_norm.weight": "model-00001.safetensors",
583
+ "model.layers.4.self_attn.q_proj.weight": "model-00001.safetensors",
584
+ "model.layers.4.self_attn.v_proj.weight": "model-00001.safetensors",
585
+ "model.layers.4.share_expert.down_proj.weight": "model-00001.safetensors",
586
+ "model.layers.4.share_expert.gate_proj.weight": "model-00001.safetensors",
587
+ "model.layers.4.share_expert.up_proj.weight": "model-00001.safetensors",
588
+ "model.layers.40.input_layernorm.weight": "model-00001.safetensors",
589
+ "model.layers.40.moe.down_proj.weight": "model-00040.safetensors",
590
+ "model.layers.40.moe.gate.weight": "model-00001.safetensors",
591
+ "model.layers.40.moe.gate_proj.weight": "model-00039.safetensors",
592
+ "model.layers.40.moe.router_bias": "model-00001.safetensors",
593
+ "model.layers.40.moe.up_proj.weight": "model-00040.safetensors",
594
+ "model.layers.40.post_attention_layernorm.weight": "model-00001.safetensors",
595
+ "model.layers.40.self_attn.g_proj.weight": "model-00001.safetensors",
596
+ "model.layers.40.self_attn.k_norm.weight": "model-00001.safetensors",
597
+ "model.layers.40.self_attn.k_proj.weight": "model-00001.safetensors",
598
+ "model.layers.40.self_attn.o_proj.weight": "model-00001.safetensors",
599
+ "model.layers.40.self_attn.q_norm.weight": "model-00001.safetensors",
600
+ "model.layers.40.self_attn.q_proj.weight": "model-00001.safetensors",
601
+ "model.layers.40.self_attn.v_proj.weight": "model-00001.safetensors",
602
+ "model.layers.40.share_expert.down_proj.weight": "model-00001.safetensors",
603
+ "model.layers.40.share_expert.gate_proj.weight": "model-00001.safetensors",
604
+ "model.layers.40.share_expert.up_proj.weight": "model-00001.safetensors",
605
+ "model.layers.41.input_layernorm.weight": "model-00001.safetensors",
606
+ "model.layers.41.moe.down_proj.weight": "model-00041.safetensors",
607
+ "model.layers.41.moe.gate.weight": "model-00001.safetensors",
608
+ "model.layers.41.moe.gate_proj.weight": "model-00040.safetensors",
609
+ "model.layers.41.moe.router_bias": "model-00001.safetensors",
610
+ "model.layers.41.moe.up_proj.weight": "model-00041.safetensors",
611
+ "model.layers.41.post_attention_layernorm.weight": "model-00001.safetensors",
612
+ "model.layers.41.self_attn.g_proj.weight": "model-00001.safetensors",
613
+ "model.layers.41.self_attn.k_norm.weight": "model-00001.safetensors",
614
+ "model.layers.41.self_attn.k_proj.weight": "model-00001.safetensors",
615
+ "model.layers.41.self_attn.o_proj.weight": "model-00001.safetensors",
616
+ "model.layers.41.self_attn.q_norm.weight": "model-00001.safetensors",
617
+ "model.layers.41.self_attn.q_proj.weight": "model-00001.safetensors",
618
+ "model.layers.41.self_attn.v_proj.weight": "model-00001.safetensors",
619
+ "model.layers.41.share_expert.down_proj.weight": "model-00001.safetensors",
620
+ "model.layers.41.share_expert.gate_proj.weight": "model-00001.safetensors",
621
+ "model.layers.41.share_expert.up_proj.weight": "model-00001.safetensors",
622
+ "model.layers.42.input_layernorm.weight": "model-00001.safetensors",
623
+ "model.layers.42.moe.down_proj.weight": "model-00042.safetensors",
624
+ "model.layers.42.moe.gate.weight": "model-00001.safetensors",
625
+ "model.layers.42.moe.gate_proj.weight": "model-00041.safetensors",
626
+ "model.layers.42.moe.router_bias": "model-00001.safetensors",
627
+ "model.layers.42.moe.up_proj.weight": "model-00042.safetensors",
628
+ "model.layers.42.post_attention_layernorm.weight": "model-00001.safetensors",
629
+ "model.layers.42.self_attn.g_proj.weight": "model-00002.safetensors",
630
+ "model.layers.42.self_attn.k_norm.weight": "model-00001.safetensors",
631
+ "model.layers.42.self_attn.k_proj.weight": "model-00002.safetensors",
632
+ "model.layers.42.self_attn.o_proj.weight": "model-00001.safetensors",
633
+ "model.layers.42.self_attn.q_norm.weight": "model-00001.safetensors",
634
+ "model.layers.42.self_attn.q_proj.weight": "model-00002.safetensors",
635
+ "model.layers.42.self_attn.v_proj.weight": "model-00002.safetensors",
636
+ "model.layers.42.share_expert.down_proj.weight": "model-00001.safetensors",
637
+ "model.layers.42.share_expert.gate_proj.weight": "model-00002.safetensors",
638
+ "model.layers.42.share_expert.up_proj.weight": "model-00002.safetensors",
639
+ "model.layers.43.input_layernorm.weight": "model-00001.safetensors",
640
+ "model.layers.43.moe.down_proj.weight": "model-00043.safetensors",
641
+ "model.layers.43.moe.gate.weight": "model-00001.safetensors",
642
+ "model.layers.43.moe.gate_proj.weight": "model-00042.safetensors",
643
+ "model.layers.43.moe.router_bias": "model-00001.safetensors",
644
+ "model.layers.43.moe.up_proj.weight": "model-00043.safetensors",
645
+ "model.layers.43.post_attention_layernorm.weight": "model-00001.safetensors",
646
+ "model.layers.43.self_attn.g_proj.weight": "model-00002.safetensors",
647
+ "model.layers.43.self_attn.k_norm.weight": "model-00001.safetensors",
648
+ "model.layers.43.self_attn.k_proj.weight": "model-00002.safetensors",
649
+ "model.layers.43.self_attn.o_proj.weight": "model-00001.safetensors",
650
+ "model.layers.43.self_attn.q_norm.weight": "model-00001.safetensors",
651
+ "model.layers.43.self_attn.q_proj.weight": "model-00002.safetensors",
652
+ "model.layers.43.self_attn.v_proj.weight": "model-00002.safetensors",
653
+ "model.layers.43.share_expert.down_proj.weight": "model-00001.safetensors",
654
+ "model.layers.43.share_expert.gate_proj.weight": "model-00002.safetensors",
655
+ "model.layers.43.share_expert.up_proj.weight": "model-00002.safetensors",
656
+ "model.layers.44.input_layernorm.weight": "model-00002.safetensors",
657
+ "model.layers.44.moe.down_proj.weight": "model-00044.safetensors",
658
+ "model.layers.44.moe.gate.weight": "model-00002.safetensors",
659
+ "model.layers.44.moe.gate_proj.weight": "model-00043.safetensors",
660
+ "model.layers.44.moe.router_bias": "model-00002.safetensors",
661
+ "model.layers.44.moe.up_proj.weight": "model-00044.safetensors",
662
+ "model.layers.44.post_attention_layernorm.weight": "model-00002.safetensors",
663
+ "model.layers.44.self_attn.g_proj.weight": "model-00002.safetensors",
664
+ "model.layers.44.self_attn.k_norm.weight": "model-00002.safetensors",
665
+ "model.layers.44.self_attn.k_proj.weight": "model-00002.safetensors",
666
+ "model.layers.44.self_attn.o_proj.weight": "model-00002.safetensors",
667
+ "model.layers.44.self_attn.q_norm.weight": "model-00002.safetensors",
668
+ "model.layers.44.self_attn.q_proj.weight": "model-00002.safetensors",
669
+ "model.layers.44.self_attn.v_proj.weight": "model-00002.safetensors",
670
+ "model.layers.44.share_expert.down_proj.weight": "model-00002.safetensors",
671
+ "model.layers.44.share_expert.gate_proj.weight": "model-00002.safetensors",
672
+ "model.layers.44.share_expert.up_proj.weight": "model-00002.safetensors",
673
+ "model.layers.45.eh_proj.weight": "model-00002.safetensors",
674
+ "model.layers.45.enorm.weight": "model-00002.safetensors",
675
+ "model.layers.45.hnorm.weight": "model-00002.safetensors",
676
+ "model.layers.45.input_layernorm.weight": "model-00002.safetensors",
677
+ "model.layers.45.mlp.down_proj.weight": "model-00002.safetensors",
678
+ "model.layers.45.mlp.gate_proj.weight": "model-00002.safetensors",
679
+ "model.layers.45.mlp.up_proj.weight": "model-00002.safetensors",
680
+ "model.layers.45.post_attention_layernorm.weight": "model-00002.safetensors",
681
+ "model.layers.45.self_attn.g_proj.weight": "model-00002.safetensors",
682
+ "model.layers.45.self_attn.k_norm.weight": "model-00002.safetensors",
683
+ "model.layers.45.self_attn.k_proj.weight": "model-00002.safetensors",
684
+ "model.layers.45.self_attn.o_proj.weight": "model-00002.safetensors",
685
+ "model.layers.45.self_attn.q_norm.weight": "model-00002.safetensors",
686
+ "model.layers.45.self_attn.q_proj.weight": "model-00002.safetensors",
687
+ "model.layers.45.self_attn.v_proj.weight": "model-00002.safetensors",
688
+ "model.layers.45.transformer.shared_head.norm.weight": "model-00002.safetensors",
689
+ "model.layers.45.transformer.shared_head.output.weight": "model-00002.safetensors",
690
+ "model.layers.5.input_layernorm.weight": "model-00001.safetensors",
691
+ "model.layers.5.moe.down_proj.weight": "model-00005.safetensors",
692
+ "model.layers.5.moe.gate.weight": "model-00001.safetensors",
693
+ "model.layers.5.moe.gate_proj.weight": "model-00004.safetensors",
694
+ "model.layers.5.moe.router_bias": "model-00001.safetensors",
695
+ "model.layers.5.moe.up_proj.weight": "model-00005.safetensors",
696
+ "model.layers.5.post_attention_layernorm.weight": "model-00001.safetensors",
697
+ "model.layers.5.self_attn.g_proj.weight": "model-00001.safetensors",
698
+ "model.layers.5.self_attn.k_norm.weight": "model-00001.safetensors",
699
+ "model.layers.5.self_attn.k_proj.weight": "model-00001.safetensors",
700
+ "model.layers.5.self_attn.o_proj.weight": "model-00001.safetensors",
701
+ "model.layers.5.self_attn.q_norm.weight": "model-00001.safetensors",
702
+ "model.layers.5.self_attn.q_proj.weight": "model-00001.safetensors",
703
+ "model.layers.5.self_attn.v_proj.weight": "model-00001.safetensors",
704
+ "model.layers.5.share_expert.down_proj.weight": "model-00001.safetensors",
705
+ "model.layers.5.share_expert.gate_proj.weight": "model-00001.safetensors",
706
+ "model.layers.5.share_expert.up_proj.weight": "model-00001.safetensors",
707
+ "model.layers.6.input_layernorm.weight": "model-00001.safetensors",
708
+ "model.layers.6.moe.down_proj.weight": "model-00006.safetensors",
709
+ "model.layers.6.moe.gate.weight": "model-00001.safetensors",
710
+ "model.layers.6.moe.gate_proj.weight": "model-00005.safetensors",
711
+ "model.layers.6.moe.router_bias": "model-00001.safetensors",
712
+ "model.layers.6.moe.up_proj.weight": "model-00006.safetensors",
713
+ "model.layers.6.post_attention_layernorm.weight": "model-00001.safetensors",
714
+ "model.layers.6.self_attn.g_proj.weight": "model-00001.safetensors",
715
+ "model.layers.6.self_attn.k_norm.weight": "model-00001.safetensors",
716
+ "model.layers.6.self_attn.k_proj.weight": "model-00001.safetensors",
717
+ "model.layers.6.self_attn.o_proj.weight": "model-00001.safetensors",
718
+ "model.layers.6.self_attn.q_norm.weight": "model-00001.safetensors",
719
+ "model.layers.6.self_attn.q_proj.weight": "model-00001.safetensors",
720
+ "model.layers.6.self_attn.v_proj.weight": "model-00001.safetensors",
721
+ "model.layers.6.share_expert.down_proj.weight": "model-00001.safetensors",
722
+ "model.layers.6.share_expert.gate_proj.weight": "model-00001.safetensors",
723
+ "model.layers.6.share_expert.up_proj.weight": "model-00001.safetensors",
724
+ "model.layers.7.input_layernorm.weight": "model-00001.safetensors",
725
+ "model.layers.7.moe.down_proj.weight": "model-00007.safetensors",
726
+ "model.layers.7.moe.gate.weight": "model-00001.safetensors",
727
+ "model.layers.7.moe.gate_proj.weight": "model-00006.safetensors",
728
+ "model.layers.7.moe.router_bias": "model-00001.safetensors",
729
+ "model.layers.7.moe.up_proj.weight": "model-00007.safetensors",
730
+ "model.layers.7.post_attention_layernorm.weight": "model-00001.safetensors",
731
+ "model.layers.7.self_attn.g_proj.weight": "model-00001.safetensors",
732
+ "model.layers.7.self_attn.k_norm.weight": "model-00001.safetensors",
733
+ "model.layers.7.self_attn.k_proj.weight": "model-00001.safetensors",
734
+ "model.layers.7.self_attn.o_proj.weight": "model-00001.safetensors",
735
+ "model.layers.7.self_attn.q_norm.weight": "model-00001.safetensors",
736
+ "model.layers.7.self_attn.q_proj.weight": "model-00001.safetensors",
737
+ "model.layers.7.self_attn.v_proj.weight": "model-00001.safetensors",
738
+ "model.layers.7.share_expert.down_proj.weight": "model-00001.safetensors",
739
+ "model.layers.7.share_expert.gate_proj.weight": "model-00001.safetensors",
740
+ "model.layers.7.share_expert.up_proj.weight": "model-00001.safetensors",
741
+ "model.layers.8.input_layernorm.weight": "model-00001.safetensors",
742
+ "model.layers.8.moe.down_proj.weight": "model-00008.safetensors",
743
+ "model.layers.8.moe.gate.weight": "model-00001.safetensors",
744
+ "model.layers.8.moe.gate_proj.weight": "model-00007.safetensors",
745
+ "model.layers.8.moe.router_bias": "model-00001.safetensors",
746
+ "model.layers.8.moe.up_proj.weight": "model-00008.safetensors",
747
+ "model.layers.8.post_attention_layernorm.weight": "model-00001.safetensors",
748
+ "model.layers.8.self_attn.g_proj.weight": "model-00001.safetensors",
749
+ "model.layers.8.self_attn.k_norm.weight": "model-00001.safetensors",
750
+ "model.layers.8.self_attn.k_proj.weight": "model-00001.safetensors",
751
+ "model.layers.8.self_attn.o_proj.weight": "model-00001.safetensors",
752
+ "model.layers.8.self_attn.q_norm.weight": "model-00001.safetensors",
753
+ "model.layers.8.self_attn.q_proj.weight": "model-00001.safetensors",
754
+ "model.layers.8.self_attn.v_proj.weight": "model-00001.safetensors",
755
+ "model.layers.8.share_expert.down_proj.weight": "model-00001.safetensors",
756
+ "model.layers.8.share_expert.gate_proj.weight": "model-00001.safetensors",
757
+ "model.layers.8.share_expert.up_proj.weight": "model-00001.safetensors",
758
+ "model.layers.9.input_layernorm.weight": "model-00001.safetensors",
759
+ "model.layers.9.moe.down_proj.weight": "model-00009.safetensors",
760
+ "model.layers.9.moe.gate.weight": "model-00001.safetensors",
761
+ "model.layers.9.moe.gate_proj.weight": "model-00008.safetensors",
762
+ "model.layers.9.moe.router_bias": "model-00001.safetensors",
763
+ "model.layers.9.moe.up_proj.weight": "model-00009.safetensors",
764
+ "model.layers.9.post_attention_layernorm.weight": "model-00001.safetensors",
765
+ "model.layers.9.self_attn.g_proj.weight": "model-00001.safetensors",
766
+ "model.layers.9.self_attn.k_norm.weight": "model-00001.safetensors",
767
+ "model.layers.9.self_attn.k_proj.weight": "model-00001.safetensors",
768
+ "model.layers.9.self_attn.o_proj.weight": "model-00001.safetensors",
769
+ "model.layers.9.self_attn.q_norm.weight": "model-00001.safetensors",
770
+ "model.layers.9.self_attn.q_proj.weight": "model-00001.safetensors",
771
+ "model.layers.9.self_attn.v_proj.weight": "model-00001.safetensors",
772
+ "model.layers.9.share_expert.down_proj.weight": "model-00001.safetensors",
773
+ "model.layers.9.share_expert.gate_proj.weight": "model-00001.safetensors",
774
+ "model.layers.9.share_expert.up_proj.weight": "model-00001.safetensors",
775
+ "model.norm.weight": "model-00002.safetensors"
776
+ }
777
+ }