Hugging Face's logo

cognitivecomputations
/
dolphin-2.9.2-qwen2-72b

Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
axolotl
conversational
Eval Results
text-generation-inference
Inference Endpoints
Model card Files Community
8
Crystalcareai commited on
Commit
1f10a29
•
1 Parent(s): adebe73

Upload folder using huggingface_hub

Browse files
Files changed (41) hide show
  1. README.md +454 -0
  2. added_tokens.json +5 -0
  3. config.json +27 -0
  4. generation_config.json +7 -0
  5. merges.txt +0 -0
  6. model-00001-of-00031.safetensors +3 -0
  7. model-00002-of-00031.safetensors +3 -0
  8. model-00003-of-00031.safetensors +3 -0
  9. model-00004-of-00031.safetensors +3 -0
  10. model-00005-of-00031.safetensors +3 -0
  11. model-00006-of-00031.safetensors +3 -0
  12. model-00007-of-00031.safetensors +3 -0
  13. model-00008-of-00031.safetensors +3 -0
  14. model-00009-of-00031.safetensors +3 -0
  15. model-00010-of-00031.safetensors +3 -0
  16. model-00011-of-00031.safetensors +3 -0
  17. model-00012-of-00031.safetensors +3 -0
  18. model-00013-of-00031.safetensors +3 -0
  19. model-00014-of-00031.safetensors +3 -0
  20. model-00015-of-00031.safetensors +3 -0
  21. model-00016-of-00031.safetensors +3 -0
  22. model-00017-of-00031.safetensors +3 -0
  23. model-00018-of-00031.safetensors +3 -0
  24. model-00019-of-00031.safetensors +3 -0
  25. model-00020-of-00031.safetensors +3 -0
  26. model-00021-of-00031.safetensors +3 -0
  27. model-00022-of-00031.safetensors +3 -0
  28. model-00023-of-00031.safetensors +3 -0
  29. model-00024-of-00031.safetensors +3 -0
  30. model-00025-of-00031.safetensors +3 -0
  31. model-00026-of-00031.safetensors +3 -0
  32. model-00027-of-00031.safetensors +3 -0
  33. model-00028-of-00031.safetensors +3 -0
  34. model-00029-of-00031.safetensors +3 -0
  35. model-00030-of-00031.safetensors +3 -0
  36. model-00031-of-00031.safetensors +3 -0
  37. model.safetensors.index.json +970 -0
  38. special_tokens_map.json +20 -0
  39. tokenizer.json +0 -0
  40. tokenizer_config.json +43 -0
  41. vocab.json +0 -0
README.md ADDED
@@ -0,0 +1,454 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ base_model: Qwen/Qwen2-72B
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: qwen2-72b
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
15
+ <details><summary>See axolotl config</summary>
16
+
17
+ axolotl version: `0.4.0`
18
+ ```yaml
19
+ base_model: Qwen/Qwen2-72B
20
+ model_type: AutoModelForCausalLM
21
+ tokenizer_type: AutoTokenizer
22
+
23
+ trust_remote_code: true
24
+
25
+ # load_in_8bit: true
26
+ # load_in_4bit: false
27
+ # strict: false
28
+
29
+ datasets:
30
+ - path: /workspace/datasets/dolphin-2.9.2/dolphin201-sharegpt2.jsonl
31
+ type: sharegpt
32
+ conversation: chatml
33
+ - path: /workspace/datasets/dolphin-2.9.2/dolphin-coder-codegen-sharegpt2.jsonl
34
+ type: sharegpt
35
+ conversation: chatml
36
+ - path: /workspace/datasets/dolphin-2.9.2/dolphin-coder-translate-sharegpt2.jsonl
37
+ type: sharegpt
38
+ conversation: chatml
39
+ - path: /workspace/datasets/dolphin-2.9.2/m-a-p_Code-Feedback-sharegpt-unfiltered.jsonl
40
+ type: sharegpt
41
+ conversation: chatml
42
+ - path: /workspace/datasets/dolphin-2.9.2/m-a-p_CodeFeedback-Filtered-Instruction-sharegpt-unfiltered.jsonl
43
+ type: sharegpt
44
+ conversation: chatml
45
+ - path: /workspace/datasets/dolphin-2.9.2/not_samantha_norefusals.jsonl
46
+ type: sharegpt
47
+ conversation: chatml
48
+ - path: /workspace/datasets/dolphin-2.9.2/openhermes200k_unfiltered.jsonl
49
+ type: sharegpt
50
+ conversation: chatml
51
+ - path: /workspace/datasets/dolphin-2.9.2/Orca-Math-resort-unfiltered.jsonl
52
+ type: sharegpt
53
+ conversation: chatml
54
+ - path: /workspace/datasets/dolphin-2.9.2/SystemChat_sharegpt.jsonl
55
+ type: sharegpt
56
+ conversation: chatml
57
+ - path: /workspace/datasets/dolphin-2.9.2/toolbench_instruct_j1s1_3k_unfiltered.jsonl
58
+ type: sharegpt
59
+ conversation: chatml
60
+ - path: /workspace/datasets/dolphin-2.9.2/toolbench_negative_unfiltered.jsonl
61
+ type: sharegpt
62
+ conversation: chatml
63
+ - path: /workspace/datasets/dolphin-2.9.2/toolbench_react_10p_unfiltered.jsonl
64
+ type: sharegpt
65
+ conversation: chatml
66
+ - path: /workspace/datasets/dolphin-2.9.2/toolbench_tflan_cot_30p_unfiltered.jsonl
67
+ type: sharegpt
68
+ conversation: chatml
69
+ - path: /workspace/datasets/dolphin-2.9.2/agent_instruct_react_unfiltered.jsonl
70
+ type: sharegpt
71
+ conversation: chatml
72
+
73
+ unfrozen_parameters:
74
+ - ^lm_head.weight$
75
+ - ^model.embed_tokens.weight$
76
+ # mlp.down_proj layers
77
+ - model.layers.62.mlp.down_proj
78
+ - model.layers.63.mlp.down_proj
79
+ - model.layers.66.mlp.down_proj
80
+ - model.layers.65.mlp.down_proj
81
+ - model.layers.64.mlp.down_proj
82
+ - model.layers.67.mlp.down_proj
83
+ - model.layers.68.mlp.down_proj
84
+ - model.layers.60.mlp.down_proj
85
+ - model.layers.31.mlp.down_proj
86
+ - model.layers.69.mlp.down_proj
87
+ - model.layers.61.mlp.down_proj
88
+ - model.layers.59.mlp.down_proj
89
+ - model.layers.70.mlp.down_proj
90
+ - model.layers.30.mlp.down_proj
91
+ - model.layers.76.mlp.down_proj
92
+ - model.layers.72.mlp.down_proj
93
+ - model.layers.77.mlp.down_proj
94
+ - model.layers.71.mlp.down_proj
95
+ - model.layers.29.mlp.down_proj
96
+ - model.layers.58.mlp.down_proj
97
+ - model.layers.75.mlp.down_proj
98
+ - model.layers.32.mlp.down_proj
99
+ - model.layers.56.mlp.down_proj
100
+ - model.layers.28.mlp.down_proj
101
+ - model.layers.26.mlp.down_proj
102
+ - model.layers.33.mlp.down_proj
103
+ - model.layers.34.mlp.down_proj
104
+ - model.layers.57.mlp.down_proj
105
+ - model.layers.27.mlp.down_proj
106
+ - model.layers.25.mlp.down_proj
107
+ - model.layers.35.mlp.down_proj
108
+ - model.layers.73.mlp.down_proj
109
+ - model.layers.24.mlp.down_proj
110
+ - model.layers.78.mlp.down_proj
111
+ - model.layers.74.mlp.down_proj
112
+ - model.layers.54.mlp.down_proj
113
+ # mlp.gate_proj layers
114
+ - model.layers.78.mlp.gate_proj
115
+ - model.layers.77.mlp.gate_proj
116
+ - model.layers.76.mlp.gate_proj
117
+ - model.layers.79.mlp.gate_proj
118
+ - model.layers.75.mlp.gate_proj
119
+ - model.layers.74.mlp.gate_proj
120
+ - model.layers.73.mlp.gate_proj
121
+ - model.layers.70.mlp.gate_proj
122
+ - model.layers.72.mlp.gate_proj
123
+ - model.layers.71.mlp.gate_proj
124
+ - model.layers.69.mlp.gate_proj
125
+ - model.layers.54.mlp.gate_proj
126
+ - model.layers.68.mlp.gate_proj
127
+ - model.layers.57.mlp.gate_proj
128
+ - model.layers.63.mlp.gate_proj
129
+ - model.layers.49.mlp.gate_proj
130
+ - model.layers.55.mlp.gate_proj
131
+ - model.layers.53.mlp.gate_proj
132
+ - model.layers.44.mlp.gate_proj
133
+ - model.layers.46.mlp.gate_proj
134
+ - model.layers.67.mlp.gate_proj
135
+ - model.layers.58.mlp.gate_proj
136
+ - model.layers.56.mlp.gate_proj
137
+ - model.layers.45.mlp.gate_proj
138
+ - model.layers.50.mlp.gate_proj
139
+ - model.layers.62.mlp.gate_proj
140
+ - model.layers.64.mlp.gate_proj
141
+ - model.layers.48.mlp.gate_proj
142
+ - model.layers.66.mlp.gate_proj
143
+ - model.layers.52.mlp.gate_proj
144
+ - model.layers.40.mlp.gate_proj
145
+ - model.layers.47.mlp.gate_proj
146
+ - model.layers.43.mlp.gate_proj
147
+ - model.layers.65.mlp.gate_proj
148
+ - model.layers.61.mlp.gate_proj
149
+ - model.layers.59.mlp.gate_proj
150
+ # mlp.up_proj layers
151
+ - model.layers.69.mlp.up_proj
152
+ - model.layers.70.mlp.up_proj
153
+ - model.layers.71.mlp.up_proj
154
+ - model.layers.68.mlp.up_proj
155
+ - model.layers.67.mlp.up_proj
156
+ - model.layers.66.mlp.up_proj
157
+ - model.layers.46.mlp.up_proj
158
+ - model.layers.63.mlp.up_proj
159
+ - model.layers.72.mlp.up_proj
160
+ - model.layers.64.mlp.up_proj
161
+ - model.layers.62.mlp.up_proj
162
+ - model.layers.45.mlp.up_proj
163
+ - model.layers.65.mlp.up_proj
164
+ - model.layers.73.mlp.up_proj
165
+ - model.layers.47.mlp.up_proj
166
+ - model.layers.44.mlp.up_proj
167
+ - model.layers.49.mlp.up_proj
168
+ - model.layers.48.mlp.up_proj
169
+ - model.layers.53.mlp.up_proj
170
+ - model.layers.74.mlp.up_proj
171
+ - model.layers.75.mlp.up_proj
172
+ - model.layers.57.mlp.up_proj
173
+ - model.layers.76.mlp.up_proj
174
+ - model.layers.43.mlp.up_proj
175
+ - model.layers.42.mlp.up_proj
176
+ - model.layers.61.mlp.up_proj
177
+ - model.layers.40.mlp.up_proj
178
+ - model.layers.56.mlp.up_proj
179
+ - model.layers.60.mlp.up_proj
180
+ - model.layers.31.mlp.up_proj
181
+ - model.layers.54.mlp.up_proj
182
+ - model.layers.55.mlp.up_proj
183
+ - model.layers.32.mlp.up_proj
184
+ - model.layers.41.mlp.up_proj
185
+ - model.layers.33.mlp.up_proj
186
+ - model.layers.58.mlp.up_proj
187
+ # self_attn.k_proj layers
188
+ - model.layers.79.self_attn.k_proj
189
+ - model.layers.36.self_attn.k_proj
190
+ - model.layers.35.self_attn.k_proj
191
+ - model.layers.74.self_attn.k_proj
192
+ - model.layers.34.self_attn.k_proj
193
+ - model.layers.78.self_attn.k_proj
194
+ - model.layers.77.self_attn.k_proj
195
+ - model.layers.37.self_attn.k_proj
196
+ - model.layers.39.self_attn.k_proj
197
+ - model.layers.41.self_attn.k_proj
198
+ - model.layers.38.self_attn.k_proj
199
+ - model.layers.33.self_attn.k_proj
200
+ - model.layers.69.self_attn.k_proj
201
+ - model.layers.42.self_attn.k_proj
202
+ - model.layers.32.self_attn.k_proj
203
+ - model.layers.25.self_attn.k_proj
204
+ - model.layers.70.self_attn.k_proj
205
+ - model.layers.22.self_attn.k_proj
206
+ - model.layers.63.self_attn.k_proj
207
+ - model.layers.29.self_attn.k_proj
208
+ - model.layers.68.self_attn.k_proj
209
+ - model.layers.24.self_attn.k_proj
210
+ - model.layers.30.self_attn.k_proj
211
+ - model.layers.66.self_attn.k_proj
212
+ - model.layers.31.self_attn.k_proj
213
+ - model.layers.23.self_attn.k_proj
214
+ - model.layers.65.self_attn.k_proj
215
+ - model.layers.57.self_attn.k_proj
216
+ - model.layers.28.self_attn.k_proj
217
+ - model.layers.64.self_attn.k_proj
218
+ - model.layers.44.self_attn.k_proj
219
+ - model.layers.27.self_attn.k_proj
220
+ - model.layers.75.self_attn.k_proj
221
+ - model.layers.40.self_attn.k_proj
222
+ - model.layers.26.self_attn.k_proj
223
+ - model.layers.61.self_attn.k_proj
224
+ # self_attn.o_proj layers
225
+ - model.layers.14.self_attn.o_proj
226
+ - model.layers.39.self_attn.o_proj
227
+ - model.layers.19.self_attn.o_proj
228
+ - model.layers.16.self_attn.o_proj
229
+ - model.layers.17.self_attn.o_proj
230
+ - model.layers.15.self_attn.o_proj
231
+ - model.layers.69.self_attn.o_proj
232
+ - model.layers.12.self_attn.o_proj
233
+ - model.layers.42.self_attn.o_proj
234
+ - model.layers.23.self_attn.o_proj
235
+ - model.layers.22.self_attn.o_proj
236
+ - model.layers.29.self_attn.o_proj
237
+ - model.layers.13.self_attn.o_proj
238
+ - model.layers.46.self_attn.o_proj
239
+ - model.layers.52.self_attn.o_proj
240
+ - model.layers.26.self_attn.o_proj
241
+ - model.layers.38.self_attn.o_proj
242
+ - model.layers.41.self_attn.o_proj
243
+ - model.layers.18.self_attn.o_proj
244
+ - model.layers.49.self_attn.o_proj
245
+ - model.layers.11.self_attn.o_proj
246
+ - model.layers.28.self_attn.o_proj
247
+ - model.layers.25.self_attn.o_proj
248
+ - model.layers.47.self_attn.o_proj
249
+ - model.layers.53.self_attn.o_proj
250
+ - model.layers.27.self_attn.o_proj
251
+ - model.layers.37.self_attn.o_proj
252
+ - model.layers.20.self_attn.o_proj
253
+ - model.layers.43.self_attn.o_proj
254
+ - model.layers.44.self_attn.o_proj
255
+ - model.layers.45.self_attn.o_proj
256
+ - model.layers.30.self_attn.o_proj
257
+ - model.layers.24.self_attn.o_proj
258
+ - model.layers.21.self_attn.o_proj
259
+ - model.layers.10.self_attn.o_proj
260
+ - model.layers.3.self_attn.o_proj
261
+ # self_attn.q_proj layers
262
+ - model.layers.1.self_attn.q_proj
263
+ - model.layers.2.self_attn.q_proj
264
+ - model.layers.3.self_attn.q_proj
265
+ - model.layers.5.self_attn.q_proj
266
+ - model.layers.4.self_attn.q_proj
267
+ - model.layers.0.self_attn.q_proj
268
+ - model.layers.6.self_attn.q_proj
269
+ - model.layers.8.self_attn.q_proj
270
+ - model.layers.7.self_attn.q_proj
271
+ - model.layers.9.self_attn.q_proj
272
+ - model.layers.10.self_attn.q_proj
273
+ - model.layers.12.self_attn.q_proj
274
+ - model.layers.19.self_attn.q_proj
275
+ - model.layers.18.self_attn.q_proj
276
+ - model.layers.25.self_attn.q_proj
277
+ - model.layers.11.self_attn.q_proj
278
+ - model.layers.15.self_attn.q_proj
279
+ - model.layers.61.self_attn.q_proj
280
+ - model.layers.17.self_attn.q_proj
281
+ - model.layers.55.self_attn.q_proj
282
+ - model.layers.54.self_attn.q_proj
283
+ - model.layers.16.self_attn.q_proj
284
+ - model.layers.68.self_attn.q_proj
285
+ - model.layers.49.self_attn.q_proj
286
+ - model.layers.48.self_attn.q_proj
287
+ - model.layers.52.self_attn.q_proj
288
+ - model.layers.13.self_attn.q_proj
289
+ - model.layers.42.self_attn.q_proj
290
+ - model.layers.57.self_attn.q_proj
291
+ - model.layers.60.self_attn.q_proj
292
+ - model.layers.53.self_attn.q_proj
293
+ - model.layers.64.self_attn.q_proj
294
+ - model.layers.66.self_attn.q_proj
295
+ - model.layers.62.self_attn.q_proj
296
+ - model.layers.59.self_attn.q_proj
297
+ - model.layers.50.self_attn.q_proj
298
+ # self_attn.v_proj layers
299
+ - model.layers.15.self_attn.v_proj
300
+ - model.layers.16.self_attn.v_proj
301
+ - model.layers.23.self_attn.v_proj
302
+ - model.layers.24.self_attn.v_proj
303
+ - model.layers.25.self_attn.v_proj
304
+ - model.layers.26.self_attn.v_proj
305
+ - model.layers.27.self_attn.v_proj
306
+ - model.layers.28.self_attn.v_proj
307
+ - model.layers.29.self_attn.v_proj
308
+ - model.layers.30.self_attn.v_proj
309
+ - model.layers.31.self_attn.v_proj
310
+ - model.layers.32.self_attn.v_proj
311
+ - model.layers.33.self_attn.v_proj
312
+ - model.layers.34.self_attn.v_proj
313
+ - model.layers.35.self_attn.v_proj
314
+ - model.layers.36.self_attn.v_proj
315
+ - model.layers.37.self_attn.v_proj
316
+ - model.layers.38.self_attn.v_proj
317
+ - model.layers.39.self_attn.v_proj
318
+ - model.layers.41.self_attn.v_proj
319
+ - model.layers.42.self_attn.v_proj
320
+ - model.layers.48.self_attn.v_proj
321
+ - model.layers.53.self_attn.v_proj
322
+ - model.layers.57.self_attn.v_proj
323
+ - model.layers.58.self_attn.v_proj
324
+ - model.layers.59.self_attn.v_proj
325
+ - model.layers.61.self_attn.v_proj
326
+ - model.layers.63.self_attn.v_proj
327
+ - model.layers.64.self_attn.v_proj
328
+ - model.layers.65.self_attn.v_proj
329
+ - model.layers.66.self_attn.v_proj
330
+ - model.layers.69.self_attn.v_proj
331
+ - model.layers.74.self_attn.v_proj
332
+ - model.layers.75.self_attn.v_proj
333
+ - model.layers.76.self_attn.v_proj
334
+ - model.layers.72.self_attn.v_proj
335
+
336
+
337
+ chat_template: chatml
338
+ dataset_prepared_path: qwen2-72b-data
339
+ val_set_size: 0.01
340
+ output_dir: qwen2-72b
341
+
342
+ sequence_len: 8192 # supports up to 8192
343
+ sample_packing: true
344
+ pad_to_sequence_len: true
345
+
346
+ # adapter: lora
347
+ # lora_model_dir:
348
+ # lora_r: 32
349
+ # lora_alpha: 16
350
+ # lora_dropout: 0.05
351
+ # lora_target_linear: true
352
+ # lora_fan_in_fan_out:
353
+
354
+ wandb_project: qwen2-72b
355
+ wandb_entity:
356
+ wandb_watch:
357
+ wandb_name:
358
+ wandb_log_model:
359
+
360
+ gradient_accumulation_steps: 8
361
+ micro_batch_size: 1
362
+ num_epochs: 3
363
+ optimizer: paged_adamw_8bit
364
+ lr_scheduler: cosine
365
+ learning_rate: 1e-5
366
+
367
+ train_on_inputs: false
368
+ group_by_length: false
369
+ bf16: auto
370
+ fp16:
371
+ tf32: false
372
+
373
+ gradient_checkpointing: true
374
+ early_stopping_patience:
375
+ resume_from_checkpoint:
376
+ local_rank:
377
+ logging_steps: 1
378
+ xformers_attention:
379
+ flash_attention: true
380
+
381
+ warmup_steps: 10
382
+ evals_per_epoch: 2
383
+ eval_table_size:
384
+ eval_max_new_tokens: 128
385
+ saves_per_epoch: 4
386
+ save_total_limit: 2
387
+ debug:
388
+ deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16_cpuoffload_params.json
389
+ weight_decay: 0.05
390
+ fsdp:
391
+ fsdp_config:
392
+ special_tokens:
393
+ pad_token: "<|endoftext|>"
394
+ eos_token: "<|im_end|>"
395
+
396
+ ```
397
+
398
+ </details><br>
399
+
400
+ # qwen2-72b
401
+
402
+ This model is a fine-tuned version of [Qwen/Qwen2-72B](https://huggingface.co/Qwen/Qwen2-72B) on the None dataset.
403
+ It achieves the following results on the evaluation set:
404
+ - Loss: 0.4737
405
+
406
+ ## Model description
407
+
408
+ More information needed
409
+
410
+ ## Intended uses & limitations
411
+
412
+ More information needed
413
+
414
+ ## Training and evaluation data
415
+
416
+ More information needed
417
+
418
+ ## Training procedure
419
+
420
+ ### Training hyperparameters
421
+
422
+ The following hyperparameters were used during training:
423
+ - learning_rate: 1e-05
424
+ - train_batch_size: 1
425
+ - eval_batch_size: 1
426
+ - seed: 42
427
+ - distributed_type: multi-GPU
428
+ - num_devices: 8
429
+ - gradient_accumulation_steps: 8
430
+ - total_train_batch_size: 64
431
+ - total_eval_batch_size: 8
432
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
433
+ - lr_scheduler_type: cosine
434
+ - lr_scheduler_warmup_steps: 10
435
+ - num_epochs: 3
436
+
437
+ ### Training results
438
+
439
+ | Training Loss | Epoch | Step | Validation Loss |
440
+ |:-------------:|:------:|:----:|:---------------:|
441
+ | 0.5458 | 0.0007 | 1 | 0.5673 |
442
+ | 0.4634 | 0.5003 | 741 | 0.4655 |
443
+ | 0.4466 | 1.0007 | 1482 | 0.4550 |
444
+ | 0.3817 | 1.4835 | 2223 | 0.4587 |
445
+ | 0.386 | 1.9838 | 2964 | 0.4540 |
446
+ | 0.3258 | 2.4664 | 3705 | 0.4737 |
447
+
448
+
449
+ ### Framework versions
450
+
451
+ - Transformers 4.40.2
452
+ - Pytorch 2.2.2+cu121
453
+ - Datasets 2.19.1
454
+ - Tokenizers 0.19.1
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 151643,
3
+ "<|im_end|>": 151645,
4
+ "<|im_start|>": 151644
5
+ }
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Qwen/Qwen2-72B",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "eos_token_id": 151645,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 8192,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 29568,
12
+ "max_position_embeddings": 131072,
13
+ "max_window_layers": 28,
14
+ "model_type": "qwen2",
15
+ "num_attention_heads": 64,
16
+ "num_hidden_layers": 80,
17
+ "num_key_value_heads": 8,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_theta": 1000000.0,
20
+ "sliding_window": 4096,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.40.2",
24
+ "use_cache": false,
25
+ "use_sliding_window": false,
26
+ "vocab_size": 152064
27
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": 151643,
5
+ "max_new_tokens": 2048,
6
+ "transformers_version": "4.40.2"
7
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f5599273a1ca997a5ac89337cfe727fe397a47c2c7feefb6fdf6dddfa56edd9
3
+ size 4548798728
model-00002-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf616e6c6a9e376ea312d36e59a67a1216110208508e196e0ab501498581a04c
3
+ size 4964101384
model-00003-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdc25d88b75b9224726e6aa3fe3b3cf09ada663b5ea754e729efb7a2ac30bb6a
3
+ size 4781637328
model-00004-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdce5eebec8c24f047695cb54d61f452faa189c1b89aedc094263d3563b7d0bd
3
+ size 4781670320
model-00005-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:205a60a92d774ca322edabe0875f29e5c67be400d03d9e422bb2c534ed2dddb9
3
+ size 4781670360
model-00006-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:510773b8ccb00e789f2d44d33b40071f86e62edc5343771c17a73c34b4a818f2
3
+ size 4964101416
model-00007-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09cce022015f1b8d554299895d7a035311aed57c9a23bac27d77f137a7668f00
3
+ size 4781637360
model-00008-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f6e2cc9564b6e218e38ef60c5ab2b126e78f7f18829ca9de19b0da15d19d3df
3
+ size 4781670360
model-00009-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2a022c28691e9660ef7a8e84a6b79656de40e36c42d57f2b9175e2779207820
3
+ size 4781670360
model-00010-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da71f1c58f5cc5e3c4aede73ee1ac856f1a1c7bcd41e33115eb2134fd6993880
3
+ size 4964101416
model-00011-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7ff1ff75146dbd0c77d3c4bdb69a2d8aef4ea50472f67e0d76c5ba922f83af9
3
+ size 4781637360
model-00012-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9258582e8aaca8c5a221d373d586b521dbe9cecbaf45094c1ea0f37dd15db480
3
+ size 4781670360
model-00013-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2da11496b4d061f4cba2dc14809d59a9e7274f71dd83ff52520052d47ebb8ad6
3
+ size 4781670360
model-00014-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:152e771b6cc34bcdfec54ca566f5fcf3fd623f4f2a0937411d58a305d8c3e7ee
3
+ size 4964101416
model-00015-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa38170cfcf5d2592ac0c8136cdded4ea143e6f01e5f0e610ee600fdaf359283
3
+ size 4781637360
model-00016-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd1b659a970e069611bbdb76a472d5bdc3c3da503d8445f1328270318577fe0e
3
+ size 4781670360
model-00017-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f71c2c77cd8a6fc1de47ef63888065873317ae0a6d93fc1087a7151638b9e6d6
3
+ size 4781670360
model-00018-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d67daf51ecaf198219b7479aff6b13cfb866f723c3187f31ae95f9b72c43587
3
+ size 4964101416
model-00019-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab15f699cac522d6a24db646c4d738ba1b29e903e12ee79261dfc421a0155690
3
+ size 4781637360
model-00020-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bef5fa83d46b74024073bff3cf33d732ae0d558d3f90dea812da3ce30445b8d
3
+ size 4781670360
model-00021-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fb75d649ebc5395765e0936a094e8bb5ba2706640f703e071eb3b894ecf4063
3
+ size 4781670360
model-00022-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74a525ef818e442f70e7f6dbc3e6e06dd6c9b5126d79bb4c0170c0c2e501f775
3
+ size 4964101416
model-00023-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2c62d14f00f8e0a863aa71b08176ad4c15a40425ac2d929fb9d4407b23fedbe
3
+ size 4781637360
model-00024-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6af11728ff29cd60c2bc18207870afb13abfa6a31c6f3fc18d622c70473c0b22
3
+ size 4781670360
model-00025-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2e74444e9b102fd6b8d073be948636138d4658a5971b78380ce038b60a5a4f0
3
+ size 4781670360
model-00026-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c1fffc3205f8a3c75b3e12793464a4a927f9e5761f5532ce8f034a9d2d97968
3
+ size 4964101416
model-00027-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30712ebe96e70e8b8859de3e9d81f0007f3c231ded2dc6f5a87acdaaadfc4320
3
+ size 4781637360
model-00028-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7503ab827dabdd4114522914360410fbcc69730f6aa603c650f068e1672f63ae
3
+ size 4781670360
model-00029-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83d559459b453de2fc496db89e1863a197406ec82c803339894f66de49fc5642
3
+ size 4781670360
model-00030-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3257a2c0279fcccdcc3ffc2f9e9a9864ccfbb91a3d2874e075d23681754ce7f2
3
+ size 3208747032
model-00031-of-00031.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bcdbc55eb7bf31c5a041b5ed9c8d776e82910a63da1f8a19d7584d76f2103dd
3
+ size 2491416704
model.safetensors.index.json ADDED
@@ -0,0 +1,970 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 145412407296
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00031-of-00031.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00031.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00031.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00031.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00031.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00031.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00031.safetensors",
13
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00031.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00031.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00031.safetensors",
16
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00031.safetensors",
17
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00031.safetensors",
18
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00031.safetensors",
19
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00031.safetensors",
20
+ "model.layers.1.input_layernorm.weight": "model-00002-of-00031.safetensors",
21
+ "model.layers.1.mlp.down_proj.weight": "model-00002-of-00031.safetensors",
22
+ "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00031.safetensors",
23
+ "model.layers.1.mlp.up_proj.weight": "model-00002-of-00031.safetensors",
24
+ "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00031.safetensors",
25
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00031.safetensors",
26
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00031.safetensors",
27
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00031.safetensors",
28
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00031.safetensors",
29
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00031.safetensors",
30
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00031.safetensors",
31
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00031.safetensors",
32
+ "model.layers.10.input_layernorm.weight": "model-00005-of-00031.safetensors",
33
+ "model.layers.10.mlp.down_proj.weight": "model-00005-of-00031.safetensors",
34
+ "model.layers.10.mlp.gate_proj.weight": "model-00005-of-00031.safetensors",
35
+ "model.layers.10.mlp.up_proj.weight": "model-00005-of-00031.safetensors",
36
+ "model.layers.10.post_attention_layernorm.weight": "model-00005-of-00031.safetensors",
37
+ "model.layers.10.self_attn.k_proj.bias": "model-00005-of-00031.safetensors",
38
+ "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00031.safetensors",
39
+ "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00031.safetensors",
40
+ "model.layers.10.self_attn.q_proj.bias": "model-00005-of-00031.safetensors",
41
+ "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00031.safetensors",
42
+ "model.layers.10.self_attn.v_proj.bias": "model-00005-of-00031.safetensors",
43
+ "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00031.safetensors",
44
+ "model.layers.11.input_layernorm.weight": "model-00005-of-00031.safetensors",
45
+ "model.layers.11.mlp.down_proj.weight": "model-00005-of-00031.safetensors",
46
+ "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00031.safetensors",
47
+ "model.layers.11.mlp.up_proj.weight": "model-00005-of-00031.safetensors",
48
+ "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00031.safetensors",
49
+ "model.layers.11.self_attn.k_proj.bias": "model-00005-of-00031.safetensors",
50
+ "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00031.safetensors",
51
+ "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00031.safetensors",
52
+ "model.layers.11.self_attn.q_proj.bias": "model-00005-of-00031.safetensors",
53
+ "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00031.safetensors",
54
+ "model.layers.11.self_attn.v_proj.bias": "model-00005-of-00031.safetensors",
55
+ "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00031.safetensors",
56
+ "model.layers.12.input_layernorm.weight": "model-00006-of-00031.safetensors",
57
+ "model.layers.12.mlp.down_proj.weight": "model-00006-of-00031.safetensors",
58
+ "model.layers.12.mlp.gate_proj.weight": "model-00006-of-00031.safetensors",
59
+ "model.layers.12.mlp.up_proj.weight": "model-00006-of-00031.safetensors",
60
+ "model.layers.12.post_attention_layernorm.weight": "model-00006-of-00031.safetensors",
61
+ "model.layers.12.self_attn.k_proj.bias": "model-00005-of-00031.safetensors",
62
+ "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00031.safetensors",
63
+ "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00031.safetensors",
64
+ "model.layers.12.self_attn.q_proj.bias": "model-00005-of-00031.safetensors",
65
+ "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00031.safetensors",
66
+ "model.layers.12.self_attn.v_proj.bias": "model-00005-of-00031.safetensors",
67
+ "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00031.safetensors",
68
+ "model.layers.13.input_layernorm.weight": "model-00006-of-00031.safetensors",
69
+ "model.layers.13.mlp.down_proj.weight": "model-00006-of-00031.safetensors",
70
+ "model.layers.13.mlp.gate_proj.weight": "model-00006-of-00031.safetensors",
71
+ "model.layers.13.mlp.up_proj.weight": "model-00006-of-00031.safetensors",
72
+ "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00031.safetensors",
73
+ "model.layers.13.self_attn.k_proj.bias": "model-00006-of-00031.safetensors",
74
+ "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00031.safetensors",
75
+ "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00031.safetensors",
76
+ "model.layers.13.self_attn.q_proj.bias": "model-00006-of-00031.safetensors",
77
+ "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00031.safetensors",
78
+ "model.layers.13.self_attn.v_proj.bias": "model-00006-of-00031.safetensors",
79
+ "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00031.safetensors",
80
+ "model.layers.14.input_layernorm.weight": "model-00006-of-00031.safetensors",
81
+ "model.layers.14.mlp.down_proj.weight": "model-00006-of-00031.safetensors",
82
+ "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00031.safetensors",
83
+ "model.layers.14.mlp.up_proj.weight": "model-00006-of-00031.safetensors",
84
+ "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00031.safetensors",
85
+ "model.layers.14.self_attn.k_proj.bias": "model-00006-of-00031.safetensors",
86
+ "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00031.safetensors",
87
+ "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00031.safetensors",
88
+ "model.layers.14.self_attn.q_proj.bias": "model-00006-of-00031.safetensors",
89
+ "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00031.safetensors",
90
+ "model.layers.14.self_attn.v_proj.bias": "model-00006-of-00031.safetensors",
91
+ "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00031.safetensors",
92
+ "model.layers.15.input_layernorm.weight": "model-00007-of-00031.safetensors",
93
+ "model.layers.15.mlp.down_proj.weight": "model-00007-of-00031.safetensors",
94
+ "model.layers.15.mlp.gate_proj.weight": "model-00007-of-00031.safetensors",
95
+ "model.layers.15.mlp.up_proj.weight": "model-00007-of-00031.safetensors",
96
+ "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00031.safetensors",
97
+ "model.layers.15.self_attn.k_proj.bias": "model-00007-of-00031.safetensors",
98
+ "model.layers.15.self_attn.k_proj.weight": "model-00007-of-00031.safetensors",
99
+ "model.layers.15.self_attn.o_proj.weight": "model-00007-of-00031.safetensors",
100
+ "model.layers.15.self_attn.q_proj.bias": "model-00007-of-00031.safetensors",
101
+ "model.layers.15.self_attn.q_proj.weight": "model-00007-of-00031.safetensors",
102
+ "model.layers.15.self_attn.v_proj.bias": "model-00007-of-00031.safetensors",
103
+ "model.layers.15.self_attn.v_proj.weight": "model-00007-of-00031.safetensors",
104
+ "model.layers.16.input_layernorm.weight": "model-00007-of-00031.safetensors",
105
+ "model.layers.16.mlp.down_proj.weight": "model-00007-of-00031.safetensors",
106
+ "model.layers.16.mlp.gate_proj.weight": "model-00007-of-00031.safetensors",
107
+ "model.layers.16.mlp.up_proj.weight": "model-00007-of-00031.safetensors",
108
+ "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00031.safetensors",
109
+ "model.layers.16.self_attn.k_proj.bias": "model-00007-of-00031.safetensors",
110
+ "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00031.safetensors",
111
+ "model.layers.16.self_attn.o_proj.weight": "model-00007-of-00031.safetensors",
112
+ "model.layers.16.self_attn.q_proj.bias": "model-00007-of-00031.safetensors",
113
+ "model.layers.16.self_attn.q_proj.weight": "model-00007-of-00031.safetensors",
114
+ "model.layers.16.self_attn.v_proj.bias": "model-00007-of-00031.safetensors",
115
+ "model.layers.16.self_attn.v_proj.weight": "model-00007-of-00031.safetensors",
116
+ "model.layers.17.input_layernorm.weight": "model-00008-of-00031.safetensors",
117
+ "model.layers.17.mlp.down_proj.weight": "model-00008-of-00031.safetensors",
118
+ "model.layers.17.mlp.gate_proj.weight": "model-00007-of-00031.safetensors",
119
+ "model.layers.17.mlp.up_proj.weight": "model-00007-of-00031.safetensors",
120
+ "model.layers.17.post_attention_layernorm.weight": "model-00008-of-00031.safetensors",
121
+ "model.layers.17.self_attn.k_proj.bias": "model-00007-of-00031.safetensors",
122
+ "model.layers.17.self_attn.k_proj.weight": "model-00007-of-00031.safetensors",
123
+ "model.layers.17.self_attn.o_proj.weight": "model-00007-of-00031.safetensors",
124
+ "model.layers.17.self_attn.q_proj.bias": "model-00007-of-00031.safetensors",
125
+ "model.layers.17.self_attn.q_proj.weight": "model-00007-of-00031.safetensors",
126
+ "model.layers.17.self_attn.v_proj.bias": "model-00007-of-00031.safetensors",
127
+ "model.layers.17.self_attn.v_proj.weight": "model-00007-of-00031.safetensors",
128
+ "model.layers.18.input_layernorm.weight": "model-00008-of-00031.safetensors",
129
+ "model.layers.18.mlp.down_proj.weight": "model-00008-of-00031.safetensors",
130
+ "model.layers.18.mlp.gate_proj.weight": "model-00008-of-00031.safetensors",
131
+ "model.layers.18.mlp.up_proj.weight": "model-00008-of-00031.safetensors",
132
+ "model.layers.18.post_attention_layernorm.weight": "model-00008-of-00031.safetensors",
133
+ "model.layers.18.self_attn.k_proj.bias": "model-00008-of-00031.safetensors",
134
+ "model.layers.18.self_attn.k_proj.weight": "model-00008-of-00031.safetensors",
135
+ "model.layers.18.self_attn.o_proj.weight": "model-00008-of-00031.safetensors",
136
+ "model.layers.18.self_attn.q_proj.bias": "model-00008-of-00031.safetensors",
137
+ "model.layers.18.self_attn.q_proj.weight": "model-00008-of-00031.safetensors",
138
+ "model.layers.18.self_attn.v_proj.bias": "model-00008-of-00031.safetensors",
139
+ "model.layers.18.self_attn.v_proj.weight": "model-00008-of-00031.safetensors",
140
+ "model.layers.19.input_layernorm.weight": "model-00008-of-00031.safetensors",
141
+ "model.layers.19.mlp.down_proj.weight": "model-00008-of-00031.safetensors",
142
+ "model.layers.19.mlp.gate_proj.weight": "model-00008-of-00031.safetensors",
143
+ "model.layers.19.mlp.up_proj.weight": "model-00008-of-00031.safetensors",
144
+ "model.layers.19.post_attention_layernorm.weight": "model-00008-of-00031.safetensors",
145
+ "model.layers.19.self_attn.k_proj.bias": "model-00008-of-00031.safetensors",
146
+ "model.layers.19.self_attn.k_proj.weight": "model-00008-of-00031.safetensors",
147
+ "model.layers.19.self_attn.o_proj.weight": "model-00008-of-00031.safetensors",
148
+ "model.layers.19.self_attn.q_proj.bias": "model-00008-of-00031.safetensors",
149
+ "model.layers.19.self_attn.q_proj.weight": "model-00008-of-00031.safetensors",
150
+ "model.layers.19.self_attn.v_proj.bias": "model-00008-of-00031.safetensors",
151
+ "model.layers.19.self_attn.v_proj.weight": "model-00008-of-00031.safetensors",
152
+ "model.layers.2.input_layernorm.weight": "model-00002-of-00031.safetensors",
153
+ "model.layers.2.mlp.down_proj.weight": "model-00002-of-00031.safetensors",
154
+ "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00031.safetensors",
155
+ "model.layers.2.mlp.up_proj.weight": "model-00002-of-00031.safetensors",
156
+ "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00031.safetensors",
157
+ "model.layers.2.self_attn.k_proj.bias": "model-00002-of-00031.safetensors",
158
+ "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00031.safetensors",
159
+ "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00031.safetensors",
160
+ "model.layers.2.self_attn.q_proj.bias": "model-00002-of-00031.safetensors",
161
+ "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00031.safetensors",
162
+ "model.layers.2.self_attn.v_proj.bias": "model-00002-of-00031.safetensors",
163
+ "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00031.safetensors",
164
+ "model.layers.20.input_layernorm.weight": "model-00009-of-00031.safetensors",
165
+ "model.layers.20.mlp.down_proj.weight": "model-00009-of-00031.safetensors",
166
+ "model.layers.20.mlp.gate_proj.weight": "model-00008-of-00031.safetensors",
167
+ "model.layers.20.mlp.up_proj.weight": "model-00009-of-00031.safetensors",
168
+ "model.layers.20.post_attention_layernorm.weight": "model-00009-of-00031.safetensors",
169
+ "model.layers.20.self_attn.k_proj.bias": "model-00008-of-00031.safetensors",
170
+ "model.layers.20.self_attn.k_proj.weight": "model-00008-of-00031.safetensors",
171
+ "model.layers.20.self_attn.o_proj.weight": "model-00008-of-00031.safetensors",
172
+ "model.layers.20.self_attn.q_proj.bias": "model-00008-of-00031.safetensors",
173
+ "model.layers.20.self_attn.q_proj.weight": "model-00008-of-00031.safetensors",
174
+ "model.layers.20.self_attn.v_proj.bias": "model-00008-of-00031.safetensors",
175
+ "model.layers.20.self_attn.v_proj.weight": "model-00008-of-00031.safetensors",
176
+ "model.layers.21.input_layernorm.weight": "model-00009-of-00031.safetensors",
177
+ "model.layers.21.mlp.down_proj.weight": "model-00009-of-00031.safetensors",
178
+ "model.layers.21.mlp.gate_proj.weight": "model-00009-of-00031.safetensors",
179
+ "model.layers.21.mlp.up_proj.weight": "model-00009-of-00031.safetensors",
180
+ "model.layers.21.post_attention_layernorm.weight": "model-00009-of-00031.safetensors",
181
+ "model.layers.21.self_attn.k_proj.bias": "model-00009-of-00031.safetensors",
182
+ "model.layers.21.self_attn.k_proj.weight": "model-00009-of-00031.safetensors",
183
+ "model.layers.21.self_attn.o_proj.weight": "model-00009-of-00031.safetensors",
184
+ "model.layers.21.self_attn.q_proj.bias": "model-00009-of-00031.safetensors",
185
+ "model.layers.21.self_attn.q_proj.weight": "model-00009-of-00031.safetensors",
186
+ "model.layers.21.self_attn.v_proj.bias": "model-00009-of-00031.safetensors",
187
+ "model.layers.21.self_attn.v_proj.weight": "model-00009-of-00031.safetensors",
188
+ "model.layers.22.input_layernorm.weight": "model-00009-of-00031.safetensors",
189
+ "model.layers.22.mlp.down_proj.weight": "model-00009-of-00031.safetensors",
190
+ "model.layers.22.mlp.gate_proj.weight": "model-00009-of-00031.safetensors",
191
+ "model.layers.22.mlp.up_proj.weight": "model-00009-of-00031.safetensors",
192
+ "model.layers.22.post_attention_layernorm.weight": "model-00009-of-00031.safetensors",
193
+ "model.layers.22.self_attn.k_proj.bias": "model-00009-of-00031.safetensors",
194
+ "model.layers.22.self_attn.k_proj.weight": "model-00009-of-00031.safetensors",
195
+ "model.layers.22.self_attn.o_proj.weight": "model-00009-of-00031.safetensors",
196
+ "model.layers.22.self_attn.q_proj.bias": "model-00009-of-00031.safetensors",
197
+ "model.layers.22.self_attn.q_proj.weight": "model-00009-of-00031.safetensors",
198
+ "model.layers.22.self_attn.v_proj.bias": "model-00009-of-00031.safetensors",
199
+ "model.layers.22.self_attn.v_proj.weight": "model-00009-of-00031.safetensors",
200
+ "model.layers.23.input_layernorm.weight": "model-00010-of-00031.safetensors",
201
+ "model.layers.23.mlp.down_proj.weight": "model-00010-of-00031.safetensors",
202
+ "model.layers.23.mlp.gate_proj.weight": "model-00010-of-00031.safetensors",
203
+ "model.layers.23.mlp.up_proj.weight": "model-00010-of-00031.safetensors",
204
+ "model.layers.23.post_attention_layernorm.weight": "model-00010-of-00031.safetensors",
205
+ "model.layers.23.self_attn.k_proj.bias": "model-00009-of-00031.safetensors",
206
+ "model.layers.23.self_attn.k_proj.weight": "model-00009-of-00031.safetensors",
207
+ "model.layers.23.self_attn.o_proj.weight": "model-00009-of-00031.safetensors",
208
+ "model.layers.23.self_attn.q_proj.bias": "model-00009-of-00031.safetensors",
209
+ "model.layers.23.self_attn.q_proj.weight": "model-00009-of-00031.safetensors",
210
+ "model.layers.23.self_attn.v_proj.bias": "model-00009-of-00031.safetensors",
211
+ "model.layers.23.self_attn.v_proj.weight": "model-00009-of-00031.safetensors",
212
+ "model.layers.24.input_layernorm.weight": "model-00010-of-00031.safetensors",
213
+ "model.layers.24.mlp.down_proj.weight": "model-00010-of-00031.safetensors",
214
+ "model.layers.24.mlp.gate_proj.weight": "model-00010-of-00031.safetensors",
215
+ "model.layers.24.mlp.up_proj.weight": "model-00010-of-00031.safetensors",
216
+ "model.layers.24.post_attention_layernorm.weight": "model-00010-of-00031.safetensors",
217
+ "model.layers.24.self_attn.k_proj.bias": "model-00010-of-00031.safetensors",
218
+ "model.layers.24.self_attn.k_proj.weight": "model-00010-of-00031.safetensors",
219
+ "model.layers.24.self_attn.o_proj.weight": "model-00010-of-00031.safetensors",
220
+ "model.layers.24.self_attn.q_proj.bias": "model-00010-of-00031.safetensors",
221
+ "model.layers.24.self_attn.q_proj.weight": "model-00010-of-00031.safetensors",
222
+ "model.layers.24.self_attn.v_proj.bias": "model-00010-of-00031.safetensors",
223
+ "model.layers.24.self_attn.v_proj.weight": "model-00010-of-00031.safetensors",
224
+ "model.layers.25.input_layernorm.weight": "model-00010-of-00031.safetensors",
225
+ "model.layers.25.mlp.down_proj.weight": "model-00010-of-00031.safetensors",
226
+ "model.layers.25.mlp.gate_proj.weight": "model-00010-of-00031.safetensors",
227
+ "model.layers.25.mlp.up_proj.weight": "model-00010-of-00031.safetensors",
228
+ "model.layers.25.post_attention_layernorm.weight": "model-00010-of-00031.safetensors",
229
+ "model.layers.25.self_attn.k_proj.bias": "model-00010-of-00031.safetensors",
230
+ "model.layers.25.self_attn.k_proj.weight": "model-00010-of-00031.safetensors",
231
+ "model.layers.25.self_attn.o_proj.weight": "model-00010-of-00031.safetensors",
232
+ "model.layers.25.self_attn.q_proj.bias": "model-00010-of-00031.safetensors",
233
+ "model.layers.25.self_attn.q_proj.weight": "model-00010-of-00031.safetensors",
234
+ "model.layers.25.self_attn.v_proj.bias": "model-00010-of-00031.safetensors",
235
+ "model.layers.25.self_attn.v_proj.weight": "model-00010-of-00031.safetensors",
236
+ "model.layers.26.input_layernorm.weight": "model-00011-of-00031.safetensors",
237
+ "model.layers.26.mlp.down_proj.weight": "model-00011-of-00031.safetensors",
238
+ "model.layers.26.mlp.gate_proj.weight": "model-00011-of-00031.safetensors",
239
+ "model.layers.26.mlp.up_proj.weight": "model-00011-of-00031.safetensors",
240
+ "model.layers.26.post_attention_layernorm.weight": "model-00011-of-00031.safetensors",
241
+ "model.layers.26.self_attn.k_proj.bias": "model-00011-of-00031.safetensors",
242
+ "model.layers.26.self_attn.k_proj.weight": "model-00011-of-00031.safetensors",
243
+ "model.layers.26.self_attn.o_proj.weight": "model-00011-of-00031.safetensors",
244
+ "model.layers.26.self_attn.q_proj.bias": "model-00011-of-00031.safetensors",
245
+ "model.layers.26.self_attn.q_proj.weight": "model-00011-of-00031.safetensors",
246
+ "model.layers.26.self_attn.v_proj.bias": "model-00011-of-00031.safetensors",
247
+ "model.layers.26.self_attn.v_proj.weight": "model-00011-of-00031.safetensors",
248
+ "model.layers.27.input_layernorm.weight": "model-00011-of-00031.safetensors",
249
+ "model.layers.27.mlp.down_proj.weight": "model-00011-of-00031.safetensors",
250
+ "model.layers.27.mlp.gate_proj.weight": "model-00011-of-00031.safetensors",
251
+ "model.layers.27.mlp.up_proj.weight": "model-00011-of-00031.safetensors",
252
+ "model.layers.27.post_attention_layernorm.weight": "model-00011-of-00031.safetensors",
253
+ "model.layers.27.self_attn.k_proj.bias": "model-00011-of-00031.safetensors",
254
+ "model.layers.27.self_attn.k_proj.weight": "model-00011-of-00031.safetensors",
255
+ "model.layers.27.self_attn.o_proj.weight": "model-00011-of-00031.safetensors",
256
+ "model.layers.27.self_attn.q_proj.bias": "model-00011-of-00031.safetensors",
257
+ "model.layers.27.self_attn.q_proj.weight": "model-00011-of-00031.safetensors",
258
+ "model.layers.27.self_attn.v_proj.bias": "model-00011-of-00031.safetensors",
259
+ "model.layers.27.self_attn.v_proj.weight": "model-00011-of-00031.safetensors",
260
+ "model.layers.28.input_layernorm.weight": "model-00012-of-00031.safetensors",
261
+ "model.layers.28.mlp.down_proj.weight": "model-00012-of-00031.safetensors",
262
+ "model.layers.28.mlp.gate_proj.weight": "model-00011-of-00031.safetensors",
263
+ "model.layers.28.mlp.up_proj.weight": "model-00011-of-00031.safetensors",
264
+ "model.layers.28.post_attention_layernorm.weight": "model-00012-of-00031.safetensors",
265
+ "model.layers.28.self_attn.k_proj.bias": "model-00011-of-00031.safetensors",
266
+ "model.layers.28.self_attn.k_proj.weight": "model-00011-of-00031.safetensors",
267
+ "model.layers.28.self_attn.o_proj.weight": "model-00011-of-00031.safetensors",
268
+ "model.layers.28.self_attn.q_proj.bias": "model-00011-of-00031.safetensors",
269
+ "model.layers.28.self_attn.q_proj.weight": "model-00011-of-00031.safetensors",
270
+ "model.layers.28.self_attn.v_proj.bias": "model-00011-of-00031.safetensors",
271
+ "model.layers.28.self_attn.v_proj.weight": "model-00011-of-00031.safetensors",
272
+ "model.layers.29.input_layernorm.weight": "model-00012-of-00031.safetensors",
273
+ "model.layers.29.mlp.down_proj.weight": "model-00012-of-00031.safetensors",
274
+ "model.layers.29.mlp.gate_proj.weight": "model-00012-of-00031.safetensors",
275
+ "model.layers.29.mlp.up_proj.weight": "model-00012-of-00031.safetensors",
276
+ "model.layers.29.post_attention_layernorm.weight": "model-00012-of-00031.safetensors",
277
+ "model.layers.29.self_attn.k_proj.bias": "model-00012-of-00031.safetensors",
278
+ "model.layers.29.self_attn.k_proj.weight": "model-00012-of-00031.safetensors",
279
+ "model.layers.29.self_attn.o_proj.weight": "model-00012-of-00031.safetensors",
280
+ "model.layers.29.self_attn.q_proj.bias": "model-00012-of-00031.safetensors",
281
+ "model.layers.29.self_attn.q_proj.weight": "model-00012-of-00031.safetensors",
282
+ "model.layers.29.self_attn.v_proj.bias": "model-00012-of-00031.safetensors",
283
+ "model.layers.29.self_attn.v_proj.weight": "model-00012-of-00031.safetensors",
284
+ "model.layers.3.input_layernorm.weight": "model-00002-of-00031.safetensors",
285
+ "model.layers.3.mlp.down_proj.weight": "model-00002-of-00031.safetensors",
286
+ "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00031.safetensors",
287
+ "model.layers.3.mlp.up_proj.weight": "model-00002-of-00031.safetensors",
288
+ "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00031.safetensors",
289
+ "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00031.safetensors",
290
+ "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00031.safetensors",
291
+ "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00031.safetensors",
292
+ "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00031.safetensors",
293
+ "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00031.safetensors",
294
+ "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00031.safetensors",
295
+ "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00031.safetensors",
296
+ "model.layers.30.input_layernorm.weight": "model-00012-of-00031.safetensors",
297
+ "model.layers.30.mlp.down_proj.weight": "model-00012-of-00031.safetensors",
298
+ "model.layers.30.mlp.gate_proj.weight": "model-00012-of-00031.safetensors",
299
+ "model.layers.30.mlp.up_proj.weight": "model-00012-of-00031.safetensors",
300
+ "model.layers.30.post_attention_layernorm.weight": "model-00012-of-00031.safetensors",
301
+ "model.layers.30.self_attn.k_proj.bias": "model-00012-of-00031.safetensors",
302
+ "model.layers.30.self_attn.k_proj.weight": "model-00012-of-00031.safetensors",
303
+ "model.layers.30.self_attn.o_proj.weight": "model-00012-of-00031.safetensors",
304
+ "model.layers.30.self_attn.q_proj.bias": "model-00012-of-00031.safetensors",
305
+ "model.layers.30.self_attn.q_proj.weight": "model-00012-of-00031.safetensors",
306
+ "model.layers.30.self_attn.v_proj.bias": "model-00012-of-00031.safetensors",
307
+ "model.layers.30.self_attn.v_proj.weight": "model-00012-of-00031.safetensors",
308
+ "model.layers.31.input_layernorm.weight": "model-00013-of-00031.safetensors",
309
+ "model.layers.31.mlp.down_proj.weight": "model-00013-of-00031.safetensors",
310
+ "model.layers.31.mlp.gate_proj.weight": "model-00012-of-00031.safetensors",
311
+ "model.layers.31.mlp.up_proj.weight": "model-00013-of-00031.safetensors",
312
+ "model.layers.31.post_attention_layernorm.weight": "model-00013-of-00031.safetensors",
313
+ "model.layers.31.self_attn.k_proj.bias": "model-00012-of-00031.safetensors",
314
+ "model.layers.31.self_attn.k_proj.weight": "model-00012-of-00031.safetensors",
315
+ "model.layers.31.self_attn.o_proj.weight": "model-00012-of-00031.safetensors",
316
+ "model.layers.31.self_attn.q_proj.bias": "model-00012-of-00031.safetensors",
317
+ "model.layers.31.self_attn.q_proj.weight": "model-00012-of-00031.safetensors",
318
+ "model.layers.31.self_attn.v_proj.bias": "model-00012-of-00031.safetensors",
319
+ "model.layers.31.self_attn.v_proj.weight": "model-00012-of-00031.safetensors",
320
+ "model.layers.32.input_layernorm.weight": "model-00013-of-00031.safetensors",
321
+ "model.layers.32.mlp.down_proj.weight": "model-00013-of-00031.safetensors",
322
+ "model.layers.32.mlp.gate_proj.weight": "model-00013-of-00031.safetensors",
323
+ "model.layers.32.mlp.up_proj.weight": "model-00013-of-00031.safetensors",
324
+ "model.layers.32.post_attention_layernorm.weight": "model-00013-of-00031.safetensors",
325
+ "model.layers.32.self_attn.k_proj.bias": "model-00013-of-00031.safetensors",
326
+ "model.layers.32.self_attn.k_proj.weight": "model-00013-of-00031.safetensors",
327
+ "model.layers.32.self_attn.o_proj.weight": "model-00013-of-00031.safetensors",
328
+ "model.layers.32.self_attn.q_proj.bias": "model-00013-of-00031.safetensors",
329
+ "model.layers.32.self_attn.q_proj.weight": "model-00013-of-00031.safetensors",
330
+ "model.layers.32.self_attn.v_proj.bias": "model-00013-of-00031.safetensors",
331
+ "model.layers.32.self_attn.v_proj.weight": "model-00013-of-00031.safetensors",
332
+ "model.layers.33.input_layernorm.weight": "model-00013-of-00031.safetensors",
333
+ "model.layers.33.mlp.down_proj.weight": "model-00013-of-00031.safetensors",
334
+ "model.layers.33.mlp.gate_proj.weight": "model-00013-of-00031.safetensors",
335
+ "model.layers.33.mlp.up_proj.weight": "model-00013-of-00031.safetensors",
336
+ "model.layers.33.post_attention_layernorm.weight": "model-00013-of-00031.safetensors",
337
+ "model.layers.33.self_attn.k_proj.bias": "model-00013-of-00031.safetensors",
338
+ "model.layers.33.self_attn.k_proj.weight": "model-00013-of-00031.safetensors",
339
+ "model.layers.33.self_attn.o_proj.weight": "model-00013-of-00031.safetensors",
340
+ "model.layers.33.self_attn.q_proj.bias": "model-00013-of-00031.safetensors",
341
+ "model.layers.33.self_attn.q_proj.weight": "model-00013-of-00031.safetensors",
342
+ "model.layers.33.self_attn.v_proj.bias": "model-00013-of-00031.safetensors",
343
+ "model.layers.33.self_attn.v_proj.weight": "model-00013-of-00031.safetensors",
344
+ "model.layers.34.input_layernorm.weight": "model-00014-of-00031.safetensors",
345
+ "model.layers.34.mlp.down_proj.weight": "model-00014-of-00031.safetensors",
346
+ "model.layers.34.mlp.gate_proj.weight": "model-00014-of-00031.safetensors",
347
+ "model.layers.34.mlp.up_proj.weight": "model-00014-of-00031.safetensors",
348
+ "model.layers.34.post_attention_layernorm.weight": "model-00014-of-00031.safetensors",
349
+ "model.layers.34.self_attn.k_proj.bias": "model-00013-of-00031.safetensors",
350
+ "model.layers.34.self_attn.k_proj.weight": "model-00013-of-00031.safetensors",
351
+ "model.layers.34.self_attn.o_proj.weight": "model-00013-of-00031.safetensors",
352
+ "model.layers.34.self_attn.q_proj.bias": "model-00013-of-00031.safetensors",
353
+ "model.layers.34.self_attn.q_proj.weight": "model-00013-of-00031.safetensors",
354
+ "model.layers.34.self_attn.v_proj.bias": "model-00013-of-00031.safetensors",
355
+ "model.layers.34.self_attn.v_proj.weight": "model-00013-of-00031.safetensors",
356
+ "model.layers.35.input_layernorm.weight": "model-00014-of-00031.safetensors",
357
+ "model.layers.35.mlp.down_proj.weight": "model-00014-of-00031.safetensors",
358
+ "model.layers.35.mlp.gate_proj.weight": "model-00014-of-00031.safetensors",
359
+ "model.layers.35.mlp.up_proj.weight": "model-00014-of-00031.safetensors",
360
+ "model.layers.35.post_attention_layernorm.weight": "model-00014-of-00031.safetensors",
361
+ "model.layers.35.self_attn.k_proj.bias": "model-00014-of-00031.safetensors",
362
+ "model.layers.35.self_attn.k_proj.weight": "model-00014-of-00031.safetensors",
363
+ "model.layers.35.self_attn.o_proj.weight": "model-00014-of-00031.safetensors",
364
+ "model.layers.35.self_attn.q_proj.bias": "model-00014-of-00031.safetensors",
365
+ "model.layers.35.self_attn.q_proj.weight": "model-00014-of-00031.safetensors",
366
+ "model.layers.35.self_attn.v_proj.bias": "model-00014-of-00031.safetensors",
367
+ "model.layers.35.self_attn.v_proj.weight": "model-00014-of-00031.safetensors",
368
+ "model.layers.36.input_layernorm.weight": "model-00014-of-00031.safetensors",
369
+ "model.layers.36.mlp.down_proj.weight": "model-00014-of-00031.safetensors",
370
+ "model.layers.36.mlp.gate_proj.weight": "model-00014-of-00031.safetensors",
371
+ "model.layers.36.mlp.up_proj.weight": "model-00014-of-00031.safetensors",
372
+ "model.layers.36.post_attention_layernorm.weight": "model-00014-of-00031.safetensors",
373
+ "model.layers.36.self_attn.k_proj.bias": "model-00014-of-00031.safetensors",
374
+ "model.layers.36.self_attn.k_proj.weight": "model-00014-of-00031.safetensors",
375
+ "model.layers.36.self_attn.o_proj.weight": "model-00014-of-00031.safetensors",
376
+ "model.layers.36.self_attn.q_proj.bias": "model-00014-of-00031.safetensors",
377
+ "model.layers.36.self_attn.q_proj.weight": "model-00014-of-00031.safetensors",
378
+ "model.layers.36.self_attn.v_proj.bias": "model-00014-of-00031.safetensors",
379
+ "model.layers.36.self_attn.v_proj.weight": "model-00014-of-00031.safetensors",
380
+ "model.layers.37.input_layernorm.weight": "model-00015-of-00031.safetensors",
381
+ "model.layers.37.mlp.down_proj.weight": "model-00015-of-00031.safetensors",
382
+ "model.layers.37.mlp.gate_proj.weight": "model-00015-of-00031.safetensors",
383
+ "model.layers.37.mlp.up_proj.weight": "model-00015-of-00031.safetensors",
384
+ "model.layers.37.post_attention_layernorm.weight": "model-00015-of-00031.safetensors",
385
+ "model.layers.37.self_attn.k_proj.bias": "model-00015-of-00031.safetensors",
386
+ "model.layers.37.self_attn.k_proj.weight": "model-00015-of-00031.safetensors",
387
+ "model.layers.37.self_attn.o_proj.weight": "model-00015-of-00031.safetensors",
388
+ "model.layers.37.self_attn.q_proj.bias": "model-00015-of-00031.safetensors",
389
+ "model.layers.37.self_attn.q_proj.weight": "model-00015-of-00031.safetensors",
390
+ "model.layers.37.self_attn.v_proj.bias": "model-00015-of-00031.safetensors",
391
+ "model.layers.37.self_attn.v_proj.weight": "model-00015-of-00031.safetensors",
392
+ "model.layers.38.input_layernorm.weight": "model-00015-of-00031.safetensors",
393
+ "model.layers.38.mlp.down_proj.weight": "model-00015-of-00031.safetensors",
394
+ "model.layers.38.mlp.gate_proj.weight": "model-00015-of-00031.safetensors",
395
+ "model.layers.38.mlp.up_proj.weight": "model-00015-of-00031.safetensors",
396
+ "model.layers.38.post_attention_layernorm.weight": "model-00015-of-00031.safetensors",
397
+ "model.layers.38.self_attn.k_proj.bias": "model-00015-of-00031.safetensors",
398
+ "model.layers.38.self_attn.k_proj.weight": "model-00015-of-00031.safetensors",
399
+ "model.layers.38.self_attn.o_proj.weight": "model-00015-of-00031.safetensors",
400
+ "model.layers.38.self_attn.q_proj.bias": "model-00015-of-00031.safetensors",
401
+ "model.layers.38.self_attn.q_proj.weight": "model-00015-of-00031.safetensors",
402
+ "model.layers.38.self_attn.v_proj.bias": "model-00015-of-00031.safetensors",
403
+ "model.layers.38.self_attn.v_proj.weight": "model-00015-of-00031.safetensors",
404
+ "model.layers.39.input_layernorm.weight": "model-00016-of-00031.safetensors",
405
+ "model.layers.39.mlp.down_proj.weight": "model-00016-of-00031.safetensors",
406
+ "model.layers.39.mlp.gate_proj.weight": "model-00015-of-00031.safetensors",
407
+ "model.layers.39.mlp.up_proj.weight": "model-00015-of-00031.safetensors",
408
+ "model.layers.39.post_attention_layernorm.weight": "model-00016-of-00031.safetensors",
409
+ "model.layers.39.self_attn.k_proj.bias": "model-00015-of-00031.safetensors",
410
+ "model.layers.39.self_attn.k_proj.weight": "model-00015-of-00031.safetensors",
411
+ "model.layers.39.self_attn.o_proj.weight": "model-00015-of-00031.safetensors",
412
+ "model.layers.39.self_attn.q_proj.bias": "model-00015-of-00031.safetensors",
413
+ "model.layers.39.self_attn.q_proj.weight": "model-00015-of-00031.safetensors",
414
+ "model.layers.39.self_attn.v_proj.bias": "model-00015-of-00031.safetensors",
415
+ "model.layers.39.self_attn.v_proj.weight": "model-00015-of-00031.safetensors",
416
+ "model.layers.4.input_layernorm.weight": "model-00003-of-00031.safetensors",
417
+ "model.layers.4.mlp.down_proj.weight": "model-00003-of-00031.safetensors",
418
+ "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00031.safetensors",
419
+ "model.layers.4.mlp.up_proj.weight": "model-00003-of-00031.safetensors",
420
+ "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00031.safetensors",
421
+ "model.layers.4.self_attn.k_proj.bias": "model-00003-of-00031.safetensors",
422
+ "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00031.safetensors",
423
+ "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00031.safetensors",
424
+ "model.layers.4.self_attn.q_proj.bias": "model-00003-of-00031.safetensors",
425
+ "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00031.safetensors",
426
+ "model.layers.4.self_attn.v_proj.bias": "model-00003-of-00031.safetensors",
427
+ "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00031.safetensors",
428
+ "model.layers.40.input_layernorm.weight": "model-00016-of-00031.safetensors",
429
+ "model.layers.40.mlp.down_proj.weight": "model-00016-of-00031.safetensors",
430
+ "model.layers.40.mlp.gate_proj.weight": "model-00016-of-00031.safetensors",
431
+ "model.layers.40.mlp.up_proj.weight": "model-00016-of-00031.safetensors",
432
+ "model.layers.40.post_attention_layernorm.weight": "model-00016-of-00031.safetensors",
433
+ "model.layers.40.self_attn.k_proj.bias": "model-00016-of-00031.safetensors",
434
+ "model.layers.40.self_attn.k_proj.weight": "model-00016-of-00031.safetensors",
435
+ "model.layers.40.self_attn.o_proj.weight": "model-00016-of-00031.safetensors",
436
+ "model.layers.40.self_attn.q_proj.bias": "model-00016-of-00031.safetensors",
437
+ "model.layers.40.self_attn.q_proj.weight": "model-00016-of-00031.safetensors",
438
+ "model.layers.40.self_attn.v_proj.bias": "model-00016-of-00031.safetensors",
439
+ "model.layers.40.self_attn.v_proj.weight": "model-00016-of-00031.safetensors",
440
+ "model.layers.41.input_layernorm.weight": "model-00016-of-00031.safetensors",
441
+ "model.layers.41.mlp.down_proj.weight": "model-00016-of-00031.safetensors",
442
+ "model.layers.41.mlp.gate_proj.weight": "model-00016-of-00031.safetensors",
443
+ "model.layers.41.mlp.up_proj.weight": "model-00016-of-00031.safetensors",
444
+ "model.layers.41.post_attention_layernorm.weight": "model-00016-of-00031.safetensors",
445
+ "model.layers.41.self_attn.k_proj.bias": "model-00016-of-00031.safetensors",
446
+ "model.layers.41.self_attn.k_proj.weight": "model-00016-of-00031.safetensors",
447
+ "model.layers.41.self_attn.o_proj.weight": "model-00016-of-00031.safetensors",
448
+ "model.layers.41.self_attn.q_proj.bias": "model-00016-of-00031.safetensors",
449
+ "model.layers.41.self_attn.q_proj.weight": "model-00016-of-00031.safetensors",
450
+ "model.layers.41.self_attn.v_proj.bias": "model-00016-of-00031.safetensors",
451
+ "model.layers.41.self_attn.v_proj.weight": "model-00016-of-00031.safetensors",
452
+ "model.layers.42.input_layernorm.weight": "model-00017-of-00031.safetensors",
453
+ "model.layers.42.mlp.down_proj.weight": "model-00017-of-00031.safetensors",
454
+ "model.layers.42.mlp.gate_proj.weight": "model-00016-of-00031.safetensors",
455
+ "model.layers.42.mlp.up_proj.weight": "model-00017-of-00031.safetensors",
456
+ "model.layers.42.post_attention_layernorm.weight": "model-00017-of-00031.safetensors",
457
+ "model.layers.42.self_attn.k_proj.bias": "model-00016-of-00031.safetensors",
458
+ "model.layers.42.self_attn.k_proj.weight": "model-00016-of-00031.safetensors",
459
+ "model.layers.42.self_attn.o_proj.weight": "model-00016-of-00031.safetensors",
460
+ "model.layers.42.self_attn.q_proj.bias": "model-00016-of-00031.safetensors",
461
+ "model.layers.42.self_attn.q_proj.weight": "model-00016-of-00031.safetensors",
462
+ "model.layers.42.self_attn.v_proj.bias": "model-00016-of-00031.safetensors",
463
+ "model.layers.42.self_attn.v_proj.weight": "model-00016-of-00031.safetensors",
464
+ "model.layers.43.input_layernorm.weight": "model-00017-of-00031.safetensors",
465
+ "model.layers.43.mlp.down_proj.weight": "model-00017-of-00031.safetensors",
466
+ "model.layers.43.mlp.gate_proj.weight": "model-00017-of-00031.safetensors",
467
+ "model.layers.43.mlp.up_proj.weight": "model-00017-of-00031.safetensors",
468
+ "model.layers.43.post_attention_layernorm.weight": "model-00017-of-00031.safetensors",
469
+ "model.layers.43.self_attn.k_proj.bias": "model-00017-of-00031.safetensors",
470
+ "model.layers.43.self_attn.k_proj.weight": "model-00017-of-00031.safetensors",
471
+ "model.layers.43.self_attn.o_proj.weight": "model-00017-of-00031.safetensors",
472
+ "model.layers.43.self_attn.q_proj.bias": "model-00017-of-00031.safetensors",
473
+ "model.layers.43.self_attn.q_proj.weight": "model-00017-of-00031.safetensors",
474
+ "model.layers.43.self_attn.v_proj.bias": "model-00017-of-00031.safetensors",
475
+ "model.layers.43.self_attn.v_proj.weight": "model-00017-of-00031.safetensors",
476
+ "model.layers.44.input_layernorm.weight": "model-00017-of-00031.safetensors",
477
+ "model.layers.44.mlp.down_proj.weight": "model-00017-of-00031.safetensors",
478
+ "model.layers.44.mlp.gate_proj.weight": "model-00017-of-00031.safetensors",
479
+ "model.layers.44.mlp.up_proj.weight": "model-00017-of-00031.safetensors",
480
+ "model.layers.44.post_attention_layernorm.weight": "model-00017-of-00031.safetensors",
481
+ "model.layers.44.self_attn.k_proj.bias": "model-00017-of-00031.safetensors",
482
+ "model.layers.44.self_attn.k_proj.weight": "model-00017-of-00031.safetensors",
483
+ "model.layers.44.self_attn.o_proj.weight": "model-00017-of-00031.safetensors",
484
+ "model.layers.44.self_attn.q_proj.bias": "model-00017-of-00031.safetensors",
485
+ "model.layers.44.self_attn.q_proj.weight": "model-00017-of-00031.safetensors",
486
+ "model.layers.44.self_attn.v_proj.bias": "model-00017-of-00031.safetensors",
487
+ "model.layers.44.self_attn.v_proj.weight": "model-00017-of-00031.safetensors",
488
+ "model.layers.45.input_layernorm.weight": "model-00018-of-00031.safetensors",
489
+ "model.layers.45.mlp.down_proj.weight": "model-00018-of-00031.safetensors",
490
+ "model.layers.45.mlp.gate_proj.weight": "model-00018-of-00031.safetensors",
491
+ "model.layers.45.mlp.up_proj.weight": "model-00018-of-00031.safetensors",
492
+ "model.layers.45.post_attention_layernorm.weight": "model-00018-of-00031.safetensors",
493
+ "model.layers.45.self_attn.k_proj.bias": "model-00017-of-00031.safetensors",
494
+ "model.layers.45.self_attn.k_proj.weight": "model-00017-of-00031.safetensors",
495
+ "model.layers.45.self_attn.o_proj.weight": "model-00017-of-00031.safetensors",
496
+ "model.layers.45.self_attn.q_proj.bias": "model-00017-of-00031.safetensors",
497
+ "model.layers.45.self_attn.q_proj.weight": "model-00017-of-00031.safetensors",
498
+ "model.layers.45.self_attn.v_proj.bias": "model-00017-of-00031.safetensors",
499
+ "model.layers.45.self_attn.v_proj.weight": "model-00017-of-00031.safetensors",
500
+ "model.layers.46.input_layernorm.weight": "model-00018-of-00031.safetensors",
501
+ "model.layers.46.mlp.down_proj.weight": "model-00018-of-00031.safetensors",
502
+ "model.layers.46.mlp.gate_proj.weight": "model-00018-of-00031.safetensors",
503
+ "model.layers.46.mlp.up_proj.weight": "model-00018-of-00031.safetensors",
504
+ "model.layers.46.post_attention_layernorm.weight": "model-00018-of-00031.safetensors",
505
+ "model.layers.46.self_attn.k_proj.bias": "model-00018-of-00031.safetensors",
506
+ "model.layers.46.self_attn.k_proj.weight": "model-00018-of-00031.safetensors",
507
+ "model.layers.46.self_attn.o_proj.weight": "model-00018-of-00031.safetensors",
508
+ "model.layers.46.self_attn.q_proj.bias": "model-00018-of-00031.safetensors",
509
+ "model.layers.46.self_attn.q_proj.weight": "model-00018-of-00031.safetensors",
510
+ "model.layers.46.self_attn.v_proj.bias": "model-00018-of-00031.safetensors",
511
+ "model.layers.46.self_attn.v_proj.weight": "model-00018-of-00031.safetensors",
512
+ "model.layers.47.input_layernorm.weight": "model-00018-of-00031.safetensors",
513
+ "model.layers.47.mlp.down_proj.weight": "model-00018-of-00031.safetensors",
514
+ "model.layers.47.mlp.gate_proj.weight": "model-00018-of-00031.safetensors",
515
+ "model.layers.47.mlp.up_proj.weight": "model-00018-of-00031.safetensors",
516
+ "model.layers.47.post_attention_layernorm.weight": "model-00018-of-00031.safetensors",
517
+ "model.layers.47.self_attn.k_proj.bias": "model-00018-of-00031.safetensors",
518
+ "model.layers.47.self_attn.k_proj.weight": "model-00018-of-00031.safetensors",
519
+ "model.layers.47.self_attn.o_proj.weight": "model-00018-of-00031.safetensors",
520
+ "model.layers.47.self_attn.q_proj.bias": "model-00018-of-00031.safetensors",
521
+ "model.layers.47.self_attn.q_proj.weight": "model-00018-of-00031.safetensors",
522
+ "model.layers.47.self_attn.v_proj.bias": "model-00018-of-00031.safetensors",
523
+ "model.layers.47.self_attn.v_proj.weight": "model-00018-of-00031.safetensors",
524
+ "model.layers.48.input_layernorm.weight": "model-00019-of-00031.safetensors",
525
+ "model.layers.48.mlp.down_proj.weight": "model-00019-of-00031.safetensors",
526
+ "model.layers.48.mlp.gate_proj.weight": "model-00019-of-00031.safetensors",
527
+ "model.layers.48.mlp.up_proj.weight": "model-00019-of-00031.safetensors",
528
+ "model.layers.48.post_attention_layernorm.weight": "model-00019-of-00031.safetensors",
529
+ "model.layers.48.self_attn.k_proj.bias": "model-00019-of-00031.safetensors",
530
+ "model.layers.48.self_attn.k_proj.weight": "model-00019-of-00031.safetensors",
531
+ "model.layers.48.self_attn.o_proj.weight": "model-00019-of-00031.safetensors",
532
+ "model.layers.48.self_attn.q_proj.bias": "model-00019-of-00031.safetensors",
533
+ "model.layers.48.self_attn.q_proj.weight": "model-00019-of-00031.safetensors",
534
+ "model.layers.48.self_attn.v_proj.bias": "model-00019-of-00031.safetensors",
535
+ "model.layers.48.self_attn.v_proj.weight": "model-00019-of-00031.safetensors",
536
+ "model.layers.49.input_layernorm.weight": "model-00019-of-00031.safetensors",
537
+ "model.layers.49.mlp.down_proj.weight": "model-00019-of-00031.safetensors",
538
+ "model.layers.49.mlp.gate_proj.weight": "model-00019-of-00031.safetensors",
539
+ "model.layers.49.mlp.up_proj.weight": "model-00019-of-00031.safetensors",
540
+ "model.layers.49.post_attention_layernorm.weight": "model-00019-of-00031.safetensors",
541
+ "model.layers.49.self_attn.k_proj.bias": "model-00019-of-00031.safetensors",
542
+ "model.layers.49.self_attn.k_proj.weight": "model-00019-of-00031.safetensors",
543
+ "model.layers.49.self_attn.o_proj.weight": "model-00019-of-00031.safetensors",
544
+ "model.layers.49.self_attn.q_proj.bias": "model-00019-of-00031.safetensors",
545
+ "model.layers.49.self_attn.q_proj.weight": "model-00019-of-00031.safetensors",
546
+ "model.layers.49.self_attn.v_proj.bias": "model-00019-of-00031.safetensors",
547
+ "model.layers.49.self_attn.v_proj.weight": "model-00019-of-00031.safetensors",
548
+ "model.layers.5.input_layernorm.weight": "model-00003-of-00031.safetensors",
549
+ "model.layers.5.mlp.down_proj.weight": "model-00003-of-00031.safetensors",
550
+ "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00031.safetensors",
551
+ "model.layers.5.mlp.up_proj.weight": "model-00003-of-00031.safetensors",
552
+ "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00031.safetensors",
553
+ "model.layers.5.self_attn.k_proj.bias": "model-00003-of-00031.safetensors",
554
+ "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00031.safetensors",
555
+ "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00031.safetensors",
556
+ "model.layers.5.self_attn.q_proj.bias": "model-00003-of-00031.safetensors",
557
+ "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00031.safetensors",
558
+ "model.layers.5.self_attn.v_proj.bias": "model-00003-of-00031.safetensors",
559
+ "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00031.safetensors",
560
+ "model.layers.50.input_layernorm.weight": "model-00020-of-00031.safetensors",
561
+ "model.layers.50.mlp.down_proj.weight": "model-00020-of-00031.safetensors",
562
+ "model.layers.50.mlp.gate_proj.weight": "model-00019-of-00031.safetensors",
563
+ "model.layers.50.mlp.up_proj.weight": "model-00019-of-00031.safetensors",
564
+ "model.layers.50.post_attention_layernorm.weight": "model-00020-of-00031.safetensors",
565
+ "model.layers.50.self_attn.k_proj.bias": "model-00019-of-00031.safetensors",
566
+ "model.layers.50.self_attn.k_proj.weight": "model-00019-of-00031.safetensors",
567
+ "model.layers.50.self_attn.o_proj.weight": "model-00019-of-00031.safetensors",
568
+ "model.layers.50.self_attn.q_proj.bias": "model-00019-of-00031.safetensors",
569
+ "model.layers.50.self_attn.q_proj.weight": "model-00019-of-00031.safetensors",
570
+ "model.layers.50.self_attn.v_proj.bias": "model-00019-of-00031.safetensors",
571
+ "model.layers.50.self_attn.v_proj.weight": "model-00019-of-00031.safetensors",
572
+ "model.layers.51.input_layernorm.weight": "model-00020-of-00031.safetensors",
573
+ "model.layers.51.mlp.down_proj.weight": "model-00020-of-00031.safetensors",
574
+ "model.layers.51.mlp.gate_proj.weight": "model-00020-of-00031.safetensors",
575
+ "model.layers.51.mlp.up_proj.weight": "model-00020-of-00031.safetensors",
576
+ "model.layers.51.post_attention_layernorm.weight": "model-00020-of-00031.safetensors",
577
+ "model.layers.51.self_attn.k_proj.bias": "model-00020-of-00031.safetensors",
578
+ "model.layers.51.self_attn.k_proj.weight": "model-00020-of-00031.safetensors",
579
+ "model.layers.51.self_attn.o_proj.weight": "model-00020-of-00031.safetensors",
580
+ "model.layers.51.self_attn.q_proj.bias": "model-00020-of-00031.safetensors",
581
+ "model.layers.51.self_attn.q_proj.weight": "model-00020-of-00031.safetensors",
582
+ "model.layers.51.self_attn.v_proj.bias": "model-00020-of-00031.safetensors",
583
+ "model.layers.51.self_attn.v_proj.weight": "model-00020-of-00031.safetensors",
584
+ "model.layers.52.input_layernorm.weight": "model-00020-of-00031.safetensors",
585
+ "model.layers.52.mlp.down_proj.weight": "model-00020-of-00031.safetensors",
586
+ "model.layers.52.mlp.gate_proj.weight": "model-00020-of-00031.safetensors",
587
+ "model.layers.52.mlp.up_proj.weight": "model-00020-of-00031.safetensors",
588
+ "model.layers.52.post_attention_layernorm.weight": "model-00020-of-00031.safetensors",
589
+ "model.layers.52.self_attn.k_proj.bias": "model-00020-of-00031.safetensors",
590
+ "model.layers.52.self_attn.k_proj.weight": "model-00020-of-00031.safetensors",
591
+ "model.layers.52.self_attn.o_proj.weight": "model-00020-of-00031.safetensors",
592
+ "model.layers.52.self_attn.q_proj.bias": "model-00020-of-00031.safetensors",
593
+ "model.layers.52.self_attn.q_proj.weight": "model-00020-of-00031.safetensors",
594
+ "model.layers.52.self_attn.v_proj.bias": "model-00020-of-00031.safetensors",
595
+ "model.layers.52.self_attn.v_proj.weight": "model-00020-of-00031.safetensors",
596
+ "model.layers.53.input_layernorm.weight": "model-00021-of-00031.safetensors",
597
+ "model.layers.53.mlp.down_proj.weight": "model-00021-of-00031.safetensors",
598
+ "model.layers.53.mlp.gate_proj.weight": "model-00020-of-00031.safetensors",
599
+ "model.layers.53.mlp.up_proj.weight": "model-00021-of-00031.safetensors",
600
+ "model.layers.53.post_attention_layernorm.weight": "model-00021-of-00031.safetensors",
601
+ "model.layers.53.self_attn.k_proj.bias": "model-00020-of-00031.safetensors",
602
+ "model.layers.53.self_attn.k_proj.weight": "model-00020-of-00031.safetensors",
603
+ "model.layers.53.self_attn.o_proj.weight": "model-00020-of-00031.safetensors",
604
+ "model.layers.53.self_attn.q_proj.bias": "model-00020-of-00031.safetensors",
605
+ "model.layers.53.self_attn.q_proj.weight": "model-00020-of-00031.safetensors",
606
+ "model.layers.53.self_attn.v_proj.bias": "model-00020-of-00031.safetensors",
607
+ "model.layers.53.self_attn.v_proj.weight": "model-00020-of-00031.safetensors",
608
+ "model.layers.54.input_layernorm.weight": "model-00021-of-00031.safetensors",
609
+ "model.layers.54.mlp.down_proj.weight": "model-00021-of-00031.safetensors",
610
+ "model.layers.54.mlp.gate_proj.weight": "model-00021-of-00031.safetensors",
611
+ "model.layers.54.mlp.up_proj.weight": "model-00021-of-00031.safetensors",
612
+ "model.layers.54.post_attention_layernorm.weight": "model-00021-of-00031.safetensors",
613
+ "model.layers.54.self_attn.k_proj.bias": "model-00021-of-00031.safetensors",
614
+ "model.layers.54.self_attn.k_proj.weight": "model-00021-of-00031.safetensors",
615
+ "model.layers.54.self_attn.o_proj.weight": "model-00021-of-00031.safetensors",
616
+ "model.layers.54.self_attn.q_proj.bias": "model-00021-of-00031.safetensors",
617
+ "model.layers.54.self_attn.q_proj.weight": "model-00021-of-00031.safetensors",
618
+ "model.layers.54.self_attn.v_proj.bias": "model-00021-of-00031.safetensors",
619
+ "model.layers.54.self_attn.v_proj.weight": "model-00021-of-00031.safetensors",
620
+ "model.layers.55.input_layernorm.weight": "model-00021-of-00031.safetensors",
621
+ "model.layers.55.mlp.down_proj.weight": "model-00021-of-00031.safetensors",
622
+ "model.layers.55.mlp.gate_proj.weight": "model-00021-of-00031.safetensors",
623
+ "model.layers.55.mlp.up_proj.weight": "model-00021-of-00031.safetensors",
624
+ "model.layers.55.post_attention_layernorm.weight": "model-00021-of-00031.safetensors",
625
+ "model.layers.55.self_attn.k_proj.bias": "model-00021-of-00031.safetensors",
626
+ "model.layers.55.self_attn.k_proj.weight": "model-00021-of-00031.safetensors",
627
+ "model.layers.55.self_attn.o_proj.weight": "model-00021-of-00031.safetensors",
628
+ "model.layers.55.self_attn.q_proj.bias": "model-00021-of-00031.safetensors",
629
+ "model.layers.55.self_attn.q_proj.weight": "model-00021-of-00031.safetensors",
630
+ "model.layers.55.self_attn.v_proj.bias": "model-00021-of-00031.safetensors",
631
+ "model.layers.55.self_attn.v_proj.weight": "model-00021-of-00031.safetensors",
632
+ "model.layers.56.input_layernorm.weight": "model-00022-of-00031.safetensors",
633
+ "model.layers.56.mlp.down_proj.weight": "model-00022-of-00031.safetensors",
634
+ "model.layers.56.mlp.gate_proj.weight": "model-00022-of-00031.safetensors",
635
+ "model.layers.56.mlp.up_proj.weight": "model-00022-of-00031.safetensors",
636
+ "model.layers.56.post_attention_layernorm.weight": "model-00022-of-00031.safetensors",
637
+ "model.layers.56.self_attn.k_proj.bias": "model-00021-of-00031.safetensors",
638
+ "model.layers.56.self_attn.k_proj.weight": "model-00021-of-00031.safetensors",
639
+ "model.layers.56.self_attn.o_proj.weight": "model-00021-of-00031.safetensors",
640
+ "model.layers.56.self_attn.q_proj.bias": "model-00021-of-00031.safetensors",
641
+ "model.layers.56.self_attn.q_proj.weight": "model-00021-of-00031.safetensors",
642
+ "model.layers.56.self_attn.v_proj.bias": "model-00021-of-00031.safetensors",
643
+ "model.layers.56.self_attn.v_proj.weight": "model-00021-of-00031.safetensors",
644
+ "model.layers.57.input_layernorm.weight": "model-00022-of-00031.safetensors",
645
+ "model.layers.57.mlp.down_proj.weight": "model-00022-of-00031.safetensors",
646
+ "model.layers.57.mlp.gate_proj.weight": "model-00022-of-00031.safetensors",
647
+ "model.layers.57.mlp.up_proj.weight": "model-00022-of-00031.safetensors",
648
+ "model.layers.57.post_attention_layernorm.weight": "model-00022-of-00031.safetensors",
649
+ "model.layers.57.self_attn.k_proj.bias": "model-00022-of-00031.safetensors",
650
+ "model.layers.57.self_attn.k_proj.weight": "model-00022-of-00031.safetensors",
651
+ "model.layers.57.self_attn.o_proj.weight": "model-00022-of-00031.safetensors",
652
+ "model.layers.57.self_attn.q_proj.bias": "model-00022-of-00031.safetensors",
653
+ "model.layers.57.self_attn.q_proj.weight": "model-00022-of-00031.safetensors",
654
+ "model.layers.57.self_attn.v_proj.bias": "model-00022-of-00031.safetensors",
655
+ "model.layers.57.self_attn.v_proj.weight": "model-00022-of-00031.safetensors",
656
+ "model.layers.58.input_layernorm.weight": "model-00022-of-00031.safetensors",
657
+ "model.layers.58.mlp.down_proj.weight": "model-00022-of-00031.safetensors",
658
+ "model.layers.58.mlp.gate_proj.weight": "model-00022-of-00031.safetensors",
659
+ "model.layers.58.mlp.up_proj.weight": "model-00022-of-00031.safetensors",
660
+ "model.layers.58.post_attention_layernorm.weight": "model-00022-of-00031.safetensors",
661
+ "model.layers.58.self_attn.k_proj.bias": "model-00022-of-00031.safetensors",
662
+ "model.layers.58.self_attn.k_proj.weight": "model-00022-of-00031.safetensors",
663
+ "model.layers.58.self_attn.o_proj.weight": "model-00022-of-00031.safetensors",
664
+ "model.layers.58.self_attn.q_proj.bias": "model-00022-of-00031.safetensors",
665
+ "model.layers.58.self_attn.q_proj.weight": "model-00022-of-00031.safetensors",
666
+ "model.layers.58.self_attn.v_proj.bias": "model-00022-of-00031.safetensors",
667
+ "model.layers.58.self_attn.v_proj.weight": "model-00022-of-00031.safetensors",
668
+ "model.layers.59.input_layernorm.weight": "model-00023-of-00031.safetensors",
669
+ "model.layers.59.mlp.down_proj.weight": "model-00023-of-00031.safetensors",
670
+ "model.layers.59.mlp.gate_proj.weight": "model-00023-of-00031.safetensors",
671
+ "model.layers.59.mlp.up_proj.weight": "model-00023-of-00031.safetensors",
672
+ "model.layers.59.post_attention_layernorm.weight": "model-00023-of-00031.safetensors",
673
+ "model.layers.59.self_attn.k_proj.bias": "model-00023-of-00031.safetensors",
674
+ "model.layers.59.self_attn.k_proj.weight": "model-00023-of-00031.safetensors",
675
+ "model.layers.59.self_attn.o_proj.weight": "model-00023-of-00031.safetensors",
676
+ "model.layers.59.self_attn.q_proj.bias": "model-00023-of-00031.safetensors",
677
+ "model.layers.59.self_attn.q_proj.weight": "model-00023-of-00031.safetensors",
678
+ "model.layers.59.self_attn.v_proj.bias": "model-00023-of-00031.safetensors",
679
+ "model.layers.59.self_attn.v_proj.weight": "model-00023-of-00031.safetensors",
680
+ "model.layers.6.input_layernorm.weight": "model-00004-of-00031.safetensors",
681
+ "model.layers.6.mlp.down_proj.weight": "model-00004-of-00031.safetensors",
682
+ "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00031.safetensors",
683
+ "model.layers.6.mlp.up_proj.weight": "model-00003-of-00031.safetensors",
684
+ "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00031.safetensors",
685
+ "model.layers.6.self_attn.k_proj.bias": "model-00003-of-00031.safetensors",
686
+ "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00031.safetensors",
687
+ "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00031.safetensors",
688
+ "model.layers.6.self_attn.q_proj.bias": "model-00003-of-00031.safetensors",
689
+ "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00031.safetensors",
690
+ "model.layers.6.self_attn.v_proj.bias": "model-00003-of-00031.safetensors",
691
+ "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00031.safetensors",
692
+ "model.layers.60.input_layernorm.weight": "model-00023-of-00031.safetensors",
693
+ "model.layers.60.mlp.down_proj.weight": "model-00023-of-00031.safetensors",
694
+ "model.layers.60.mlp.gate_proj.weight": "model-00023-of-00031.safetensors",
695
+ "model.layers.60.mlp.up_proj.weight": "model-00023-of-00031.safetensors",
696
+ "model.layers.60.post_attention_layernorm.weight": "model-00023-of-00031.safetensors",
697
+ "model.layers.60.self_attn.k_proj.bias": "model-00023-of-00031.safetensors",
698
+ "model.layers.60.self_attn.k_proj.weight": "model-00023-of-00031.safetensors",
699
+ "model.layers.60.self_attn.o_proj.weight": "model-00023-of-00031.safetensors",
700
+ "model.layers.60.self_attn.q_proj.bias": "model-00023-of-00031.safetensors",
701
+ "model.layers.60.self_attn.q_proj.weight": "model-00023-of-00031.safetensors",
702
+ "model.layers.60.self_attn.v_proj.bias": "model-00023-of-00031.safetensors",
703
+ "model.layers.60.self_attn.v_proj.weight": "model-00023-of-00031.safetensors",
704
+ "model.layers.61.input_layernorm.weight": "model-00024-of-00031.safetensors",
705
+ "model.layers.61.mlp.down_proj.weight": "model-00024-of-00031.safetensors",
706
+ "model.layers.61.mlp.gate_proj.weight": "model-00023-of-00031.safetensors",
707
+ "model.layers.61.mlp.up_proj.weight": "model-00023-of-00031.safetensors",
708
+ "model.layers.61.post_attention_layernorm.weight": "model-00024-of-00031.safetensors",
709
+ "model.layers.61.self_attn.k_proj.bias": "model-00023-of-00031.safetensors",
710
+ "model.layers.61.self_attn.k_proj.weight": "model-00023-of-00031.safetensors",
711
+ "model.layers.61.self_attn.o_proj.weight": "model-00023-of-00031.safetensors",
712
+ "model.layers.61.self_attn.q_proj.bias": "model-00023-of-00031.safetensors",
713
+ "model.layers.61.self_attn.q_proj.weight": "model-00023-of-00031.safetensors",
714
+ "model.layers.61.self_attn.v_proj.bias": "model-00023-of-00031.safetensors",
715
+ "model.layers.61.self_attn.v_proj.weight": "model-00023-of-00031.safetensors",
716
+ "model.layers.62.input_layernorm.weight": "model-00024-of-00031.safetensors",
717
+ "model.layers.62.mlp.down_proj.weight": "model-00024-of-00031.safetensors",
718
+ "model.layers.62.mlp.gate_proj.weight": "model-00024-of-00031.safetensors",
719
+ "model.layers.62.mlp.up_proj.weight": "model-00024-of-00031.safetensors",
720
+ "model.layers.62.post_attention_layernorm.weight": "model-00024-of-00031.safetensors",
721
+ "model.layers.62.self_attn.k_proj.bias": "model-00024-of-00031.safetensors",
722
+ "model.layers.62.self_attn.k_proj.weight": "model-00024-of-00031.safetensors",
723
+ "model.layers.62.self_attn.o_proj.weight": "model-00024-of-00031.safetensors",
724
+ "model.layers.62.self_attn.q_proj.bias": "model-00024-of-00031.safetensors",
725
+ "model.layers.62.self_attn.q_proj.weight": "model-00024-of-00031.safetensors",
726
+ "model.layers.62.self_attn.v_proj.bias": "model-00024-of-00031.safetensors",
727
+ "model.layers.62.self_attn.v_proj.weight": "model-00024-of-00031.safetensors",
728
+ "model.layers.63.input_layernorm.weight": "model-00024-of-00031.safetensors",
729
+ "model.layers.63.mlp.down_proj.weight": "model-00024-of-00031.safetensors",
730
+ "model.layers.63.mlp.gate_proj.weight": "model-00024-of-00031.safetensors",
731
+ "model.layers.63.mlp.up_proj.weight": "model-00024-of-00031.safetensors",
732
+ "model.layers.63.post_attention_layernorm.weight": "model-00024-of-00031.safetensors",
733
+ "model.layers.63.self_attn.k_proj.bias": "model-00024-of-00031.safetensors",
734
+ "model.layers.63.self_attn.k_proj.weight": "model-00024-of-00031.safetensors",
735
+ "model.layers.63.self_attn.o_proj.weight": "model-00024-of-00031.safetensors",
736
+ "model.layers.63.self_attn.q_proj.bias": "model-00024-of-00031.safetensors",
737
+ "model.layers.63.self_attn.q_proj.weight": "model-00024-of-00031.safetensors",
738
+ "model.layers.63.self_attn.v_proj.bias": "model-00024-of-00031.safetensors",
739
+ "model.layers.63.self_attn.v_proj.weight": "model-00024-of-00031.safetensors",
740
+ "model.layers.64.input_layernorm.weight": "model-00025-of-00031.safetensors",
741
+ "model.layers.64.mlp.down_proj.weight": "model-00025-of-00031.safetensors",
742
+ "model.layers.64.mlp.gate_proj.weight": "model-00024-of-00031.safetensors",
743
+ "model.layers.64.mlp.up_proj.weight": "model-00025-of-00031.safetensors",
744
+ "model.layers.64.post_attention_layernorm.weight": "model-00025-of-00031.safetensors",
745
+ "model.layers.64.self_attn.k_proj.bias": "model-00024-of-00031.safetensors",
746
+ "model.layers.64.self_attn.k_proj.weight": "model-00024-of-00031.safetensors",
747
+ "model.layers.64.self_attn.o_proj.weight": "model-00024-of-00031.safetensors",
748
+ "model.layers.64.self_attn.q_proj.bias": "model-00024-of-00031.safetensors",
749
+ "model.layers.64.self_attn.q_proj.weight": "model-00024-of-00031.safetensors",
750
+ "model.layers.64.self_attn.v_proj.bias": "model-00024-of-00031.safetensors",
751
+ "model.layers.64.self_attn.v_proj.weight": "model-00024-of-00031.safetensors",
752
+ "model.layers.65.input_layernorm.weight": "model-00025-of-00031.safetensors",
753
+ "model.layers.65.mlp.down_proj.weight": "model-00025-of-00031.safetensors",
754
+ "model.layers.65.mlp.gate_proj.weight": "model-00025-of-00031.safetensors",
755
+ "model.layers.65.mlp.up_proj.weight": "model-00025-of-00031.safetensors",
756
+ "model.layers.65.post_attention_layernorm.weight": "model-00025-of-00031.safetensors",
757
+ "model.layers.65.self_attn.k_proj.bias": "model-00025-of-00031.safetensors",
758
+ "model.layers.65.self_attn.k_proj.weight": "model-00025-of-00031.safetensors",
759
+ "model.layers.65.self_attn.o_proj.weight": "model-00025-of-00031.safetensors",
760
+ "model.layers.65.self_attn.q_proj.bias": "model-00025-of-00031.safetensors",
761
+ "model.layers.65.self_attn.q_proj.weight": "model-00025-of-00031.safetensors",
762
+ "model.layers.65.self_attn.v_proj.bias": "model-00025-of-00031.safetensors",
763
+ "model.layers.65.self_attn.v_proj.weight": "model-00025-of-00031.safetensors",
764
+ "model.layers.66.input_layernorm.weight": "model-00025-of-00031.safetensors",
765
+ "model.layers.66.mlp.down_proj.weight": "model-00025-of-00031.safetensors",
766
+ "model.layers.66.mlp.gate_proj.weight": "model-00025-of-00031.safetensors",
767
+ "model.layers.66.mlp.up_proj.weight": "model-00025-of-00031.safetensors",
768
+ "model.layers.66.post_attention_layernorm.weight": "model-00025-of-00031.safetensors",
769
+ "model.layers.66.self_attn.k_proj.bias": "model-00025-of-00031.safetensors",
770
+ "model.layers.66.self_attn.k_proj.weight": "model-00025-of-00031.safetensors",
771
+ "model.layers.66.self_attn.o_proj.weight": "model-00025-of-00031.safetensors",
772
+ "model.layers.66.self_attn.q_proj.bias": "model-00025-of-00031.safetensors",
773
+ "model.layers.66.self_attn.q_proj.weight": "model-00025-of-00031.safetensors",
774
+ "model.layers.66.self_attn.v_proj.bias": "model-00025-of-00031.safetensors",
775
+ "model.layers.66.self_attn.v_proj.weight": "model-00025-of-00031.safetensors",
776
+ "model.layers.67.input_layernorm.weight": "model-00026-of-00031.safetensors",
777
+ "model.layers.67.mlp.down_proj.weight": "model-00026-of-00031.safetensors",
778
+ "model.layers.67.mlp.gate_proj.weight": "model-00026-of-00031.safetensors",
779
+ "model.layers.67.mlp.up_proj.weight": "model-00026-of-00031.safetensors",
780
+ "model.layers.67.post_attention_layernorm.weight": "model-00026-of-00031.safetensors",
781
+ "model.layers.67.self_attn.k_proj.bias": "model-00025-of-00031.safetensors",
782
+ "model.layers.67.self_attn.k_proj.weight": "model-00025-of-00031.safetensors",
783
+ "model.layers.67.self_attn.o_proj.weight": "model-00025-of-00031.safetensors",
784
+ "model.layers.67.self_attn.q_proj.bias": "model-00025-of-00031.safetensors",
785
+ "model.layers.67.self_attn.q_proj.weight": "model-00025-of-00031.safetensors",
786
+ "model.layers.67.self_attn.v_proj.bias": "model-00025-of-00031.safetensors",
787
+ "model.layers.67.self_attn.v_proj.weight": "model-00025-of-00031.safetensors",
788
+ "model.layers.68.input_layernorm.weight": "model-00026-of-00031.safetensors",
789
+ "model.layers.68.mlp.down_proj.weight": "model-00026-of-00031.safetensors",
790
+ "model.layers.68.mlp.gate_proj.weight": "model-00026-of-00031.safetensors",
791
+ "model.layers.68.mlp.up_proj.weight": "model-00026-of-00031.safetensors",
792
+ "model.layers.68.post_attention_layernorm.weight": "model-00026-of-00031.safetensors",
793
+ "model.layers.68.self_attn.k_proj.bias": "model-00026-of-00031.safetensors",
794
+ "model.layers.68.self_attn.k_proj.weight": "model-00026-of-00031.safetensors",
795
+ "model.layers.68.self_attn.o_proj.weight": "model-00026-of-00031.safetensors",
796
+ "model.layers.68.self_attn.q_proj.bias": "model-00026-of-00031.safetensors",
797
+ "model.layers.68.self_attn.q_proj.weight": "model-00026-of-00031.safetensors",
798
+ "model.layers.68.self_attn.v_proj.bias": "model-00026-of-00031.safetensors",
799
+ "model.layers.68.self_attn.v_proj.weight": "model-00026-of-00031.safetensors",
800
+ "model.layers.69.input_layernorm.weight": "model-00026-of-00031.safetensors",
801
+ "model.layers.69.mlp.down_proj.weight": "model-00026-of-00031.safetensors",
802
+ "model.layers.69.mlp.gate_proj.weight": "model-00026-of-00031.safetensors",
803
+ "model.layers.69.mlp.up_proj.weight": "model-00026-of-00031.safetensors",
804
+ "model.layers.69.post_attention_layernorm.weight": "model-00026-of-00031.safetensors",
805
+ "model.layers.69.self_attn.k_proj.bias": "model-00026-of-00031.safetensors",
806
+ "model.layers.69.self_attn.k_proj.weight": "model-00026-of-00031.safetensors",
807
+ "model.layers.69.self_attn.o_proj.weight": "model-00026-of-00031.safetensors",
808
+ "model.layers.69.self_attn.q_proj.bias": "model-00026-of-00031.safetensors",
809
+ "model.layers.69.self_attn.q_proj.weight": "model-00026-of-00031.safetensors",
810
+ "model.layers.69.self_attn.v_proj.bias": "model-00026-of-00031.safetensors",
811
+ "model.layers.69.self_attn.v_proj.weight": "model-00026-of-00031.safetensors",
812
+ "model.layers.7.input_layernorm.weight": "model-00004-of-00031.safetensors",
813
+ "model.layers.7.mlp.down_proj.weight": "model-00004-of-00031.safetensors",
814
+ "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00031.safetensors",
815
+ "model.layers.7.mlp.up_proj.weight": "model-00004-of-00031.safetensors",
816
+ "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00031.safetensors",
817
+ "model.layers.7.self_attn.k_proj.bias": "model-00004-of-00031.safetensors",
818
+ "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00031.safetensors",
819
+ "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00031.safetensors",
820
+ "model.layers.7.self_attn.q_proj.bias": "model-00004-of-00031.safetensors",
821
+ "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00031.safetensors",
822
+ "model.layers.7.self_attn.v_proj.bias": "model-00004-of-00031.safetensors",
823
+ "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00031.safetensors",
824
+ "model.layers.70.input_layernorm.weight": "model-00027-of-00031.safetensors",
825
+ "model.layers.70.mlp.down_proj.weight": "model-00027-of-00031.safetensors",
826
+ "model.layers.70.mlp.gate_proj.weight": "model-00027-of-00031.safetensors",
827
+ "model.layers.70.mlp.up_proj.weight": "model-00027-of-00031.safetensors",
828
+ "model.layers.70.post_attention_layernorm.weight": "model-00027-of-00031.safetensors",
829
+ "model.layers.70.self_attn.k_proj.bias": "model-00027-of-00031.safetensors",
830
+ "model.layers.70.self_attn.k_proj.weight": "model-00027-of-00031.safetensors",
831
+ "model.layers.70.self_attn.o_proj.weight": "model-00027-of-00031.safetensors",
832
+ "model.layers.70.self_attn.q_proj.bias": "model-00027-of-00031.safetensors",
833
+ "model.layers.70.self_attn.q_proj.weight": "model-00027-of-00031.safetensors",
834
+ "model.layers.70.self_attn.v_proj.bias": "model-00027-of-00031.safetensors",
835
+ "model.layers.70.self_attn.v_proj.weight": "model-00027-of-00031.safetensors",
836
+ "model.layers.71.input_layernorm.weight": "model-00027-of-00031.safetensors",
837
+ "model.layers.71.mlp.down_proj.weight": "model-00027-of-00031.safetensors",
838
+ "model.layers.71.mlp.gate_proj.weight": "model-00027-of-00031.safetensors",
839
+ "model.layers.71.mlp.up_proj.weight": "model-00027-of-00031.safetensors",
840
+ "model.layers.71.post_attention_layernorm.weight": "model-00027-of-00031.safetensors",
841
+ "model.layers.71.self_attn.k_proj.bias": "model-00027-of-00031.safetensors",
842
+ "model.layers.71.self_attn.k_proj.weight": "model-00027-of-00031.safetensors",
843
+ "model.layers.71.self_attn.o_proj.weight": "model-00027-of-00031.safetensors",
844
+ "model.layers.71.self_attn.q_proj.bias": "model-00027-of-00031.safetensors",
845
+ "model.layers.71.self_attn.q_proj.weight": "model-00027-of-00031.safetensors",
846
+ "model.layers.71.self_attn.v_proj.bias": "model-00027-of-00031.safetensors",
847
+ "model.layers.71.self_attn.v_proj.weight": "model-00027-of-00031.safetensors",
848
+ "model.layers.72.input_layernorm.weight": "model-00028-of-00031.safetensors",
849
+ "model.layers.72.mlp.down_proj.weight": "model-00028-of-00031.safetensors",
850
+ "model.layers.72.mlp.gate_proj.weight": "model-00027-of-00031.safetensors",
851
+ "model.layers.72.mlp.up_proj.weight": "model-00027-of-00031.safetensors",
852
+ "model.layers.72.post_attention_layernorm.weight": "model-00028-of-00031.safetensors",
853
+ "model.layers.72.self_attn.k_proj.bias": "model-00027-of-00031.safetensors",
854
+ "model.layers.72.self_attn.k_proj.weight": "model-00027-of-00031.safetensors",
855
+ "model.layers.72.self_attn.o_proj.weight": "model-00027-of-00031.safetensors",
856
+ "model.layers.72.self_attn.q_proj.bias": "model-00027-of-00031.safetensors",
857
+ "model.layers.72.self_attn.q_proj.weight": "model-00027-of-00031.safetensors",
858
+ "model.layers.72.self_attn.v_proj.bias": "model-00027-of-00031.safetensors",
859
+ "model.layers.72.self_attn.v_proj.weight": "model-00027-of-00031.safetensors",
860
+ "model.layers.73.input_layernorm.weight": "model-00028-of-00031.safetensors",
861
+ "model.layers.73.mlp.down_proj.weight": "model-00028-of-00031.safetensors",
862
+ "model.layers.73.mlp.gate_proj.weight": "model-00028-of-00031.safetensors",
863
+ "model.layers.73.mlp.up_proj.weight": "model-00028-of-00031.safetensors",
864
+ "model.layers.73.post_attention_layernorm.weight": "model-00028-of-00031.safetensors",
865
+ "model.layers.73.self_attn.k_proj.bias": "model-00028-of-00031.safetensors",
866
+ "model.layers.73.self_attn.k_proj.weight": "model-00028-of-00031.safetensors",
867
+ "model.layers.73.self_attn.o_proj.weight": "model-00028-of-00031.safetensors",
868
+ "model.layers.73.self_attn.q_proj.bias": "model-00028-of-00031.safetensors",
869
+ "model.layers.73.self_attn.q_proj.weight": "model-00028-of-00031.safetensors",
870
+ "model.layers.73.self_attn.v_proj.bias": "model-00028-of-00031.safetensors",
871
+ "model.layers.73.self_attn.v_proj.weight": "model-00028-of-00031.safetensors",
872
+ "model.layers.74.input_layernorm.weight": "model-00028-of-00031.safetensors",
873
+ "model.layers.74.mlp.down_proj.weight": "model-00028-of-00031.safetensors",
874
+ "model.layers.74.mlp.gate_proj.weight": "model-00028-of-00031.safetensors",
875
+ "model.layers.74.mlp.up_proj.weight": "model-00028-of-00031.safetensors",
876
+ "model.layers.74.post_attention_layernorm.weight": "model-00028-of-00031.safetensors",
877
+ "model.layers.74.self_attn.k_proj.bias": "model-00028-of-00031.safetensors",
878
+ "model.layers.74.self_attn.k_proj.weight": "model-00028-of-00031.safetensors",
879
+ "model.layers.74.self_attn.o_proj.weight": "model-00028-of-00031.safetensors",
880
+ "model.layers.74.self_attn.q_proj.bias": "model-00028-of-00031.safetensors",
881
+ "model.layers.74.self_attn.q_proj.weight": "model-00028-of-00031.safetensors",
882
+ "model.layers.74.self_attn.v_proj.bias": "model-00028-of-00031.safetensors",
883
+ "model.layers.74.self_attn.v_proj.weight": "model-00028-of-00031.safetensors",
884
+ "model.layers.75.input_layernorm.weight": "model-00029-of-00031.safetensors",
885
+ "model.layers.75.mlp.down_proj.weight": "model-00029-of-00031.safetensors",
886
+ "model.layers.75.mlp.gate_proj.weight": "model-00028-of-00031.safetensors",
887
+ "model.layers.75.mlp.up_proj.weight": "model-00029-of-00031.safetensors",
888
+ "model.layers.75.post_attention_layernorm.weight": "model-00029-of-00031.safetensors",
889
+ "model.layers.75.self_attn.k_proj.bias": "model-00028-of-00031.safetensors",
890
+ "model.layers.75.self_attn.k_proj.weight": "model-00028-of-00031.safetensors",
891
+ "model.layers.75.self_attn.o_proj.weight": "model-00028-of-00031.safetensors",
892
+ "model.layers.75.self_attn.q_proj.bias": "model-00028-of-00031.safetensors",
893
+ "model.layers.75.self_attn.q_proj.weight": "model-00028-of-00031.safetensors",
894
+ "model.layers.75.self_attn.v_proj.bias": "model-00028-of-00031.safetensors",
895
+ "model.layers.75.self_attn.v_proj.weight": "model-00028-of-00031.safetensors",
896
+ "model.layers.76.input_layernorm.weight": "model-00029-of-00031.safetensors",
897
+ "model.layers.76.mlp.down_proj.weight": "model-00029-of-00031.safetensors",
898
+ "model.layers.76.mlp.gate_proj.weight": "model-00029-of-00031.safetensors",
899
+ "model.layers.76.mlp.up_proj.weight": "model-00029-of-00031.safetensors",
900
+ "model.layers.76.post_attention_layernorm.weight": "model-00029-of-00031.safetensors",
901
+ "model.layers.76.self_attn.k_proj.bias": "model-00029-of-00031.safetensors",
902
+ "model.layers.76.self_attn.k_proj.weight": "model-00029-of-00031.safetensors",
903
+ "model.layers.76.self_attn.o_proj.weight": "model-00029-of-00031.safetensors",
904
+ "model.layers.76.self_attn.q_proj.bias": "model-00029-of-00031.safetensors",
905
+ "model.layers.76.self_attn.q_proj.weight": "model-00029-of-00031.safetensors",
906
+ "model.layers.76.self_attn.v_proj.bias": "model-00029-of-00031.safetensors",
907
+ "model.layers.76.self_attn.v_proj.weight": "model-00029-of-00031.safetensors",
908
+ "model.layers.77.input_layernorm.weight": "model-00029-of-00031.safetensors",
909
+ "model.layers.77.mlp.down_proj.weight": "model-00029-of-00031.safetensors",
910
+ "model.layers.77.mlp.gate_proj.weight": "model-00029-of-00031.safetensors",
911
+ "model.layers.77.mlp.up_proj.weight": "model-00029-of-00031.safetensors",
912
+ "model.layers.77.post_attention_layernorm.weight": "model-00029-of-00031.safetensors",
913
+ "model.layers.77.self_attn.k_proj.bias": "model-00029-of-00031.safetensors",
914
+ "model.layers.77.self_attn.k_proj.weight": "model-00029-of-00031.safetensors",
915
+ "model.layers.77.self_attn.o_proj.weight": "model-00029-of-00031.safetensors",
916
+ "model.layers.77.self_attn.q_proj.bias": "model-00029-of-00031.safetensors",
917
+ "model.layers.77.self_attn.q_proj.weight": "model-00029-of-00031.safetensors",
918
+ "model.layers.77.self_attn.v_proj.bias": "model-00029-of-00031.safetensors",
919
+ "model.layers.77.self_attn.v_proj.weight": "model-00029-of-00031.safetensors",
920
+ "model.layers.78.input_layernorm.weight": "model-00030-of-00031.safetensors",
921
+ "model.layers.78.mlp.down_proj.weight": "model-00030-of-00031.safetensors",
922
+ "model.layers.78.mlp.gate_proj.weight": "model-00030-of-00031.safetensors",
923
+ "model.layers.78.mlp.up_proj.weight": "model-00030-of-00031.safetensors",
924
+ "model.layers.78.post_attention_layernorm.weight": "model-00030-of-00031.safetensors",
925
+ "model.layers.78.self_attn.k_proj.bias": "model-00029-of-00031.safetensors",
926
+ "model.layers.78.self_attn.k_proj.weight": "model-00029-of-00031.safetensors",
927
+ "model.layers.78.self_attn.o_proj.weight": "model-00029-of-00031.safetensors",
928
+ "model.layers.78.self_attn.q_proj.bias": "model-00029-of-00031.safetensors",
929
+ "model.layers.78.self_attn.q_proj.weight": "model-00029-of-00031.safetensors",
930
+ "model.layers.78.self_attn.v_proj.bias": "model-00029-of-00031.safetensors",
931
+ "model.layers.78.self_attn.v_proj.weight": "model-00029-of-00031.safetensors",
932
+ "model.layers.79.input_layernorm.weight": "model-00030-of-00031.safetensors",
933
+ "model.layers.79.mlp.down_proj.weight": "model-00030-of-00031.safetensors",
934
+ "model.layers.79.mlp.gate_proj.weight": "model-00030-of-00031.safetensors",
935
+ "model.layers.79.mlp.up_proj.weight": "model-00030-of-00031.safetensors",
936
+ "model.layers.79.post_attention_layernorm.weight": "model-00030-of-00031.safetensors",
937
+ "model.layers.79.self_attn.k_proj.bias": "model-00030-of-00031.safetensors",
938
+ "model.layers.79.self_attn.k_proj.weight": "model-00030-of-00031.safetensors",
939
+ "model.layers.79.self_attn.o_proj.weight": "model-00030-of-00031.safetensors",
940
+ "model.layers.79.self_attn.q_proj.bias": "model-00030-of-00031.safetensors",
941
+ "model.layers.79.self_attn.q_proj.weight": "model-00030-of-00031.safetensors",
942
+ "model.layers.79.self_attn.v_proj.bias": "model-00030-of-00031.safetensors",
943
+ "model.layers.79.self_attn.v_proj.weight": "model-00030-of-00031.safetensors",
944
+ "model.layers.8.input_layernorm.weight": "model-00004-of-00031.safetensors",
945
+ "model.layers.8.mlp.down_proj.weight": "model-00004-of-00031.safetensors",
946
+ "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00031.safetensors",
947
+ "model.layers.8.mlp.up_proj.weight": "model-00004-of-00031.safetensors",
948
+ "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00031.safetensors",
949
+ "model.layers.8.self_attn.k_proj.bias": "model-00004-of-00031.safetensors",
950
+ "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00031.safetensors",
951
+ "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00031.safetensors",
952
+ "model.layers.8.self_attn.q_proj.bias": "model-00004-of-00031.safetensors",
953
+ "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00031.safetensors",
954
+ "model.layers.8.self_attn.v_proj.bias": "model-00004-of-00031.safetensors",
955
+ "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00031.safetensors",
956
+ "model.layers.9.input_layernorm.weight": "model-00005-of-00031.safetensors",
957
+ "model.layers.9.mlp.down_proj.weight": "model-00005-of-00031.safetensors",
958
+ "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00031.safetensors",
959
+ "model.layers.9.mlp.up_proj.weight": "model-00005-of-00031.safetensors",
960
+ "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00031.safetensors",
961
+ "model.layers.9.self_attn.k_proj.bias": "model-00004-of-00031.safetensors",
962
+ "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00031.safetensors",
963
+ "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00031.safetensors",
964
+ "model.layers.9.self_attn.q_proj.bias": "model-00004-of-00031.safetensors",
965
+ "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00031.safetensors",
966
+ "model.layers.9.self_attn.v_proj.bias": "model-00004-of-00031.safetensors",
967
+ "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00031.safetensors",
968
+ "model.norm.weight": "model-00030-of-00031.safetensors"
969
+ }
970
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "eos_token": {
7
+ "content": "<|im_end|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "pad_token": {
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ }
20
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ }
28
+ },
29
+ "additional_special_tokens": [
30
+ "<|im_start|>",
31
+ "<|im_end|>"
32
+ ],
33
+ "bos_token": null,
34
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
35
+ "clean_up_tokenization_spaces": false,
36
+ "eos_token": "<|im_end|>",
37
+ "errors": "replace",
38
+ "model_max_length": 32768,
39
+ "pad_token": "<|endoftext|>",
40
+ "split_special_tokens": false,
41
+ "tokenizer_class": "Qwen2Tokenizer",
42
+ "unk_token": null
43
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff