PocketDoc commited on
Commit
07ac8ab
1 Parent(s): d4e0f1d

End of training

Browse files
README.md ADDED
@@ -0,0 +1,456 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ base_model: Dans-DiscountModels/Mistral-Nemo-Base-2407-ChatML-Mod
4
+ tags:
5
+ - axolotl
6
+ - generated_from_trainer
7
+ datasets:
8
+ - PocketDoc/Dans-MemoryCore-CoreCurriculum-Small
9
+ - AquaV/Energetic-Materials-Sharegpt
10
+ - AquaV/Chemical-Biological-Safety-Applications-Sharegpt
11
+ - AquaV/US-Army-Survival-Sharegpt
12
+ - AquaV/Resistance-Sharegpt
13
+ - AquaV/Interrogation-Sharegpt
14
+ - AquaV/Multi-Environment-Operations-Sharegpt
15
+ - PocketDoc/Dans-Mathmaxx
16
+ - PocketDoc/Dans-Mathmaxx-Numina-CoT
17
+ - PJMixers/Math-Multiturn-1K-ShareGPT
18
+ - PocketDoc/Dans-Benchmaxx
19
+ - PocketDoc/Dans-Benchmaxx-COT
20
+ - PocketDoc/Dans-Codemaxx-LeetCode
21
+ - PocketDoc/Dans-Codemaxx-CodeFeedback-Conversations
22
+ - PocketDoc/Dans-Codemaxx-CodeFeedback-SingleTurn
23
+ - PocketDoc/Dans-Codemaxx-Bigcode-SelfInstruct
24
+ - PocketDoc/Dans-Taskmaxx
25
+ - PocketDoc/Dans-Taskmaxx-DataPrepper
26
+ - PocketDoc/Dans-Taskmaxx-ConcurrentQA-Reworked
27
+ - PocketDoc/Dans-Taskmaxx-TableGPT
28
+ - PocketDoc/Dans-Taskmaxx-SciRIFF
29
+ - PocketDoc/Dans-Taskmaxx-Edit
30
+ - PocketDoc/Dans-Systemmaxx
31
+ - PocketDoc/Dans-Toolmaxx-Agent
32
+ - PocketDoc/Dans-Toolmaxx-ShellCommands
33
+ - PocketDoc/Dans-Toolmaxx-Functions-Toolbench
34
+ - PocketDoc/Dans-Toolmaxx-Functions-ToolACE
35
+ - PocketDoc/Dans-Toolmaxx-Functions-apigen
36
+ - PocketDoc/Dans-ASCIIMaxx-Wordart
37
+ - PocketDoc/Dans-Prosemaxx-Gutenberg
38
+ - PocketDoc/Dans-Prosemaxx-Cowriter-M
39
+ - PocketDoc/Dans-Prosemaxx-Adventure
40
+ - PocketDoc/Dans-Prosemaxx-Gryphe-GPT4o-WritingPrompts
41
+ - PocketDoc/Dans-Assistantmaxx-Sharegpt
42
+ - PocketDoc/Dans-Assistantmaxx-OpenAssistant2
43
+ - PocketDoc/Dans-Assistantmaxx-Opus-Merge
44
+ - PocketDoc/Dans-Assistantmaxx-sonnetorca-subset
45
+ - PocketDoc/Dans-Assistantmaxx-sonnetorca-subset-2
46
+ - PocketDoc/Dans-Assistantmaxx-NoRobots
47
+ - PocketDoc/Dans-Assistantmaxx-Synthia
48
+ - PocketDoc/Dans-Assistantmaxx-ASL
49
+ - PocketDoc/Dans-Assistantmaxx-PersonaLLM-Opus
50
+ - PocketDoc/Dans-Assistantmaxx-UnnaturalInstructions-GPT4
51
+ - PocketDoc/Dans-Assistantmaxx-LongAlign
52
+ - PocketDoc/Dans-Assistantmaxx-EvolKit
53
+ - PocketDoc/Dans-Assistantmaxx-Camel-GPT4
54
+ - PocketDoc/Dans-Assistantmaxx-Tulu3-IF
55
+ - PocketDoc/Dans-Logicmaxx-Skunkworks
56
+ - PocketDoc/Dans-Logicmaxx-SAT-AP
57
+ - PocketDoc/Dans-Logicmaxx-Magpie-Ultra
58
+ - PJMixers/grimulkan_theory-of-mind-ShareGPT
59
+ - PJMixers/grimulkan_physical-reasoning-ShareGPT
60
+ - PocketDoc/Dans-Personamaxx
61
+ - PocketDoc/Dans-Personamaxx-Rainy
62
+ - PocketDoc/Dans-Personamaxx-Aesir
63
+ - PocketDoc/Dans-Kinomaxx-VanillaBackrooms
64
+ model-index:
65
+ - name: Mistral-12b-Test-V0.0.3
66
+ results: []
67
+ ---
68
+
69
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
70
+ should probably proofread and complete it, then remove this comment. -->
71
+
72
+ [<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
73
+ <details><summary>See axolotl config</summary>
74
+
75
+ axolotl version: `0.2.1.dev1343+g8e11cb1`
76
+ ```yaml
77
+ base_model: Dans-DiscountModels/Mistral-Nemo-Base-2407-ChatML-Mod
78
+ model_type: AutoModelForCausalLM
79
+ tokenizer_type: AutoTokenizer
80
+
81
+ trust_remote_code:
82
+
83
+ # wandb configuration
84
+ wandb_project: mistral-12b-dans-test
85
+ wandb_watch:
86
+
87
+ wandb_run_id: V0.0.3-4-1 # V{Version}-{Run Number}-{Attempt Number}
88
+ wandb_log_model:
89
+
90
+ # push checkpoints to hub
91
+ hub_model_id: PocketDoc/Mistral-12b-Test-V0.0.3
92
+ # how to push checkpoints to hub
93
+ # https://huggingface.co/docs/transformers/v4.31.0/en/main_classes/trainer#transformers.TrainingArguments.hub_strategy
94
+ hub_strategy: "every_save"
95
+ # Whether to use hf `use_auth_token` for loading datasets. Useful for fetching private datasets
96
+ # Required to be true when used in combination with `push_dataset_to_hub`
97
+ hf_use_auth_token: true
98
+
99
+ # where to save the finished model to
100
+ output_dir: ./mistral-12b-dans-test
101
+
102
+ # dataset settings (local or huggingface repo)
103
+ datasets:
104
+ - path: PocketDoc/Dans-MemoryCore-CoreCurriculum-Small
105
+ type: dan-chat-advanced
106
+ - path: AquaV/Energetic-Materials-Sharegpt
107
+ type: dan-chat-advanced
108
+ - path: AquaV/Chemical-Biological-Safety-Applications-Sharegpt
109
+ type: dan-chat-advanced
110
+ - path: AquaV/US-Army-Survival-Sharegpt
111
+ type: dan-chat-advanced
112
+ - path: AquaV/Resistance-Sharegpt
113
+ type: dan-chat-advanced
114
+ - path: AquaV/Interrogation-Sharegpt
115
+ type: dan-chat-advanced
116
+ - path: AquaV/Multi-Environment-Operations-Sharegpt
117
+ type: dan-chat-advanced
118
+ - path: PocketDoc/Dans-Mathmaxx
119
+ type: dan-chat-advanced
120
+ - path: PocketDoc/Dans-Mathmaxx-Numina-CoT
121
+ type: dan-chat-advanced
122
+ - path: PJMixers/Math-Multiturn-1K-ShareGPT
123
+ type: dan-chat-advanced
124
+ - path: PocketDoc/Dans-Benchmaxx
125
+ type: dan-chat-advanced
126
+ - path: PocketDoc/Dans-Benchmaxx-COT
127
+ type: dan-chat-advanced
128
+ - path: PocketDoc/Dans-Codemaxx-LeetCode
129
+ type: dan-chat-advanced
130
+ - path: PocketDoc/Dans-Codemaxx-CodeFeedback-Conversations
131
+ type: dan-chat-advanced
132
+ - path: PocketDoc/Dans-Codemaxx-CodeFeedback-SingleTurn
133
+ type: dan-chat-advanced
134
+ - path: PocketDoc/Dans-Codemaxx-Bigcode-SelfInstruct
135
+ type: dan-chat-advanced
136
+ - path: PocketDoc/Dans-Taskmaxx
137
+ type: dan-chat-advanced
138
+ - path: PocketDoc/Dans-Taskmaxx-DataPrepper
139
+ type: dan-chat-advanced
140
+ - path: PocketDoc/Dans-Taskmaxx-ConcurrentQA-Reworked
141
+ type: dan-chat-advanced
142
+ - path: PocketDoc/Dans-Taskmaxx-TableGPT
143
+ type: dan-chat-advanced
144
+ - path: PocketDoc/Dans-Taskmaxx-SciRIFF
145
+ type: dan-chat-advanced
146
+ - path: PocketDoc/Dans-Taskmaxx-Edit
147
+ type: dan-chat-advanced
148
+ - path: PocketDoc/Dans-Systemmaxx
149
+ type: dan-chat-advanced
150
+ - path: PocketDoc/Dans-Toolmaxx-Agent
151
+ type: dan-chat-advanced
152
+ - path: PocketDoc/Dans-Toolmaxx-ShellCommands
153
+ type: dan-chat-advanced
154
+ - path: PocketDoc/Dans-Toolmaxx-Functions-Toolbench
155
+ type: dan-chat-advanced
156
+ - path: PocketDoc/Dans-Toolmaxx-Functions-ToolACE
157
+ type: dan-chat-advanced
158
+ - path: PocketDoc/Dans-Toolmaxx-Functions-apigen
159
+ type: dan-chat-advanced
160
+ - path: PocketDoc/Dans-ASCIIMaxx-Wordart
161
+ type: dan-chat-advanced
162
+ - path: PocketDoc/Dans-Prosemaxx-Gutenberg
163
+ type: dan-chat-advanced
164
+ - path: PocketDoc/Dans-Prosemaxx-Cowriter-M
165
+ type: dan-chat-advanced
166
+ - path: PocketDoc/Dans-Prosemaxx-Adventure
167
+ type: dan-chat-advanced
168
+ - path: PocketDoc/Dans-Prosemaxx-Gryphe-GPT4o-WritingPrompts
169
+ type: dan-chat-advanced
170
+ - path: PocketDoc/Dans-Assistantmaxx-Sharegpt
171
+ type: dan-chat-advanced
172
+ - path: PocketDoc/Dans-Assistantmaxx-OpenAssistant2
173
+ type: dan-chat-advanced
174
+ - path: PocketDoc/Dans-Assistantmaxx-Opus-Merge
175
+ type: dan-chat-advanced
176
+ - path: PocketDoc/Dans-Assistantmaxx-sonnetorca-subset
177
+ type: dan-chat-advanced
178
+ - path: PocketDoc/Dans-Assistantmaxx-sonnetorca-subset-2
179
+ type: dan-chat-advanced
180
+ - path: PocketDoc/Dans-Assistantmaxx-NoRobots
181
+ type: dan-chat-advanced
182
+ - path: PocketDoc/Dans-Assistantmaxx-Synthia
183
+ type: dan-chat-advanced
184
+ - path: PocketDoc/Dans-Assistantmaxx-ASL
185
+ type: dan-chat-advanced
186
+ - path: PocketDoc/Dans-Assistantmaxx-PersonaLLM-Opus
187
+ type: dan-chat-advanced
188
+ - path: PocketDoc/Dans-Assistantmaxx-UnnaturalInstructions-GPT4
189
+ type: dan-chat-advanced
190
+ - path: PocketDoc/Dans-Assistantmaxx-LongAlign
191
+ type: dan-chat-advanced
192
+ - path: PocketDoc/Dans-Assistantmaxx-EvolKit
193
+ type: dan-chat-advanced
194
+ - path: PocketDoc/Dans-Assistantmaxx-Camel-GPT4
195
+ type: dan-chat-advanced
196
+ - path: PocketDoc/Dans-Assistantmaxx-Tulu3-IF
197
+ type: dan-chat-advanced
198
+ - path: PocketDoc/Dans-Logicmaxx-Skunkworks
199
+ type: dan-chat-advanced
200
+ - path: PocketDoc/Dans-Logicmaxx-SAT-AP
201
+ type: dan-chat-advanced
202
+ - path: PocketDoc/Dans-Logicmaxx-Magpie-Ultra
203
+ type: dan-chat-advanced
204
+ - path: PJMixers/grimulkan_theory-of-mind-ShareGPT
205
+ type: dan-chat-advanced
206
+ - path: PJMixers/grimulkan_physical-reasoning-ShareGPT
207
+ type: dan-chat-advanced
208
+ - path: PocketDoc/Dans-Personamaxx
209
+ type: dan-chat-advanced
210
+ - path: PocketDoc/Dans-Personamaxx-Rainy
211
+ type: dan-chat-advanced
212
+ - path: PocketDoc/Dans-Personamaxx-Aesir
213
+ type: dan-chat-advanced
214
+ - path: PocketDoc/Dans-Kinomaxx-VanillaBackrooms
215
+ type: dan-chat-advanced
216
+
217
+ chat_template: chatml
218
+
219
+ plugins:
220
+ - axolotl.integrations.liger.LigerPlugin
221
+ liger_rope: true
222
+ liger_rms_norm: true
223
+ liger_swiglu: true
224
+ liger_fused_linear_cross_entropy: true
225
+
226
+ load_in_8bit: false
227
+ load_in_4bit: false
228
+ strict: false
229
+
230
+ adapter:
231
+ lora_model_dir:
232
+
233
+ lora_r: 128
234
+ lora_alpha: 128
235
+ lora_dropout: 0.1
236
+ lora_target_linear: True
237
+ lora_target_modules:
238
+ lora_modules_to_save:
239
+ - embed_tokens
240
+ - lm_head
241
+ lora_fan_in_fan_out:
242
+ peft_use_rslora: true
243
+
244
+ dataset_prepared_path: ./mistral-12b-dans-test-data
245
+ val_set_size: 0.003
246
+
247
+ sequence_len: 32768
248
+
249
+ sample_packing: true
250
+ eval_sample_packing: true
251
+
252
+ pad_to_sequence_len: true
253
+
254
+ gradient_checkpointing: true
255
+ gradient_checkpointing_kwargs:
256
+ use_reentrant: false
257
+
258
+ gradient_accumulation_steps: 8
259
+ micro_batch_size: 1
260
+
261
+ num_epochs: 2
262
+
263
+ optimizer: adamw_torch
264
+
265
+ lr_scheduler: cosine
266
+ learning_rate: 0.000012
267
+ cosine_min_lr_ratio: 0.1
268
+
269
+ weight_decay: 0.1
270
+
271
+ max_grad_norm: 10
272
+
273
+ train_on_inputs: false
274
+ group_by_length: true
275
+
276
+ bf16: true
277
+ fp16: false
278
+ tf32: false
279
+
280
+ early_stopping_patience:
281
+
282
+ resume_from_checkpoint:
283
+ auto_resume_from_checkpoints: true
284
+
285
+ local_rank:
286
+ logging_steps: 1
287
+ xformers_attention:
288
+ flash_attention: true
289
+
290
+ warmup_ratio: 0.05
291
+
292
+ evals_per_epoch: 50
293
+ eval_table_size:
294
+ eval_max_new_tokens:
295
+
296
+ saves_per_epoch: 40
297
+ save_total_limit: 2
298
+
299
+ debug: false
300
+
301
+ # deepspeed: deepspeed_configs/zero2.json
302
+
303
+ fsdp:
304
+ fsdp_config:
305
+
306
+ special_tokens:
307
+ pad_token: "<pad>"
308
+ ```
309
+
310
+ </details><br>
311
+
312
+ # Mistral-12b-Test-V0.0.3
313
+
314
+ This model is a fine-tuned version of [Dans-DiscountModels/Mistral-Nemo-Base-2407-ChatML-Mod](https://huggingface.co/Dans-DiscountModels/Mistral-Nemo-Base-2407-ChatML-Mod) on the PocketDoc/Dans-MemoryCore-CoreCurriculum-Small, the AquaV/Energetic-Materials-Sharegpt, the AquaV/Chemical-Biological-Safety-Applications-Sharegpt, the AquaV/US-Army-Survival-Sharegpt, the AquaV/Resistance-Sharegpt, the AquaV/Interrogation-Sharegpt, the AquaV/Multi-Environment-Operations-Sharegpt, the PocketDoc/Dans-Mathmaxx, the PocketDoc/Dans-Mathmaxx-Numina-CoT, the PJMixers/Math-Multiturn-1K-ShareGPT, the PocketDoc/Dans-Benchmaxx, the PocketDoc/Dans-Benchmaxx-COT, the PocketDoc/Dans-Codemaxx-LeetCode, the PocketDoc/Dans-Codemaxx-CodeFeedback-Conversations, the PocketDoc/Dans-Codemaxx-CodeFeedback-SingleTurn, the PocketDoc/Dans-Codemaxx-Bigcode-SelfInstruct, the PocketDoc/Dans-Taskmaxx, the PocketDoc/Dans-Taskmaxx-DataPrepper, the PocketDoc/Dans-Taskmaxx-ConcurrentQA-Reworked, the PocketDoc/Dans-Taskmaxx-TableGPT, the PocketDoc/Dans-Taskmaxx-SciRIFF, the PocketDoc/Dans-Taskmaxx-Edit, the PocketDoc/Dans-Systemmaxx, the PocketDoc/Dans-Toolmaxx-Agent, the PocketDoc/Dans-Toolmaxx-ShellCommands, the PocketDoc/Dans-Toolmaxx-Functions-Toolbench, the PocketDoc/Dans-Toolmaxx-Functions-ToolACE, the PocketDoc/Dans-Toolmaxx-Functions-apigen, the PocketDoc/Dans-ASCIIMaxx-Wordart, the PocketDoc/Dans-Prosemaxx-Gutenberg, the PocketDoc/Dans-Prosemaxx-Cowriter-M, the PocketDoc/Dans-Prosemaxx-Adventure, the PocketDoc/Dans-Prosemaxx-Gryphe-GPT4o-WritingPrompts, the PocketDoc/Dans-Assistantmaxx-Sharegpt, the PocketDoc/Dans-Assistantmaxx-OpenAssistant2, the PocketDoc/Dans-Assistantmaxx-Opus-Merge, the PocketDoc/Dans-Assistantmaxx-sonnetorca-subset, the PocketDoc/Dans-Assistantmaxx-sonnetorca-subset-2, the PocketDoc/Dans-Assistantmaxx-NoRobots, the PocketDoc/Dans-Assistantmaxx-Synthia, the PocketDoc/Dans-Assistantmaxx-ASL, the PocketDoc/Dans-Assistantmaxx-PersonaLLM-Opus, the PocketDoc/Dans-Assistantmaxx-UnnaturalInstructions-GPT4, the PocketDoc/Dans-Assistantmaxx-LongAlign, the PocketDoc/Dans-Assistantmaxx-EvolKit, the PocketDoc/Dans-Assistantmaxx-Camel-GPT4, the PocketDoc/Dans-Assistantmaxx-Tulu3-IF, the PocketDoc/Dans-Logicmaxx-Skunkworks, the PocketDoc/Dans-Logicmaxx-SAT-AP, the PocketDoc/Dans-Logicmaxx-Magpie-Ultra, the PJMixers/grimulkan_theory-of-mind-ShareGPT, the PJMixers/grimulkan_physical-reasoning-ShareGPT, the PocketDoc/Dans-Personamaxx, the PocketDoc/Dans-Personamaxx-Rainy, the PocketDoc/Dans-Personamaxx-Aesir and the PocketDoc/Dans-Kinomaxx-VanillaBackrooms datasets.
315
+ It achieves the following results on the evaluation set:
316
+ - Loss: 0.9245
317
+
318
+ ## Model description
319
+
320
+ More information needed
321
+
322
+ ## Intended uses & limitations
323
+
324
+ More information needed
325
+
326
+ ## Training and evaluation data
327
+
328
+ More information needed
329
+
330
+ ## Training procedure
331
+
332
+ ### Training hyperparameters
333
+
334
+ The following hyperparameters were used during training:
335
+ - learning_rate: 1.2e-05
336
+ - train_batch_size: 1
337
+ - eval_batch_size: 1
338
+ - seed: 42
339
+ - gradient_accumulation_steps: 8
340
+ - total_train_batch_size: 8
341
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
342
+ - lr_scheduler_type: cosine
343
+ - lr_scheduler_warmup_steps: 323
344
+ - num_epochs: 2
345
+
346
+ ### Training results
347
+
348
+ | Training Loss | Epoch | Step | Validation Loss |
349
+ |:-------------:|:------:|:----:|:---------------:|
350
+ | 1.0434 | 0.0201 | 65 | 1.0926 |
351
+ | 0.921 | 0.0403 | 130 | 1.0358 |
352
+ | 1.2079 | 0.0604 | 195 | 1.0140 |
353
+ | 0.8875 | 0.0805 | 260 | 1.0010 |
354
+ | 0.9807 | 0.1006 | 325 | 0.9937 |
355
+ | 1.1095 | 0.1208 | 390 | 0.9873 |
356
+ | 1.1175 | 0.1409 | 455 | 0.9797 |
357
+ | 1.1872 | 0.1610 | 520 | 0.9761 |
358
+ | 0.9521 | 0.1811 | 585 | 0.9717 |
359
+ | 1.0389 | 0.2013 | 650 | 0.9677 |
360
+ | 0.8448 | 0.2214 | 715 | 0.9668 |
361
+ | 0.9762 | 0.2415 | 780 | 0.9623 |
362
+ | 1.0434 | 0.2617 | 845 | 0.9618 |
363
+ | 0.9349 | 0.2818 | 910 | 0.9583 |
364
+ | 0.9665 | 0.3019 | 975 | 0.9563 |
365
+ | 0.9301 | 0.3220 | 1040 | 0.9536 |
366
+ | 0.9949 | 0.3422 | 1105 | 0.9518 |
367
+ | 0.8425 | 0.3623 | 1170 | 0.9508 |
368
+ | 0.7933 | 0.3824 | 1235 | 0.9497 |
369
+ | 1.0998 | 0.4026 | 1300 | 0.9484 |
370
+ | 0.9383 | 0.4227 | 1365 | 0.9462 |
371
+ | 0.8035 | 0.4428 | 1430 | 0.9463 |
372
+ | 1.1832 | 0.4629 | 1495 | 0.9451 |
373
+ | 0.9757 | 0.4831 | 1560 | 0.9460 |
374
+ | 0.9442 | 0.5032 | 1625 | 0.9426 |
375
+ | 0.7945 | 0.5233 | 1690 | 0.9407 |
376
+ | 0.7675 | 0.5434 | 1755 | 0.9401 |
377
+ | 1.0714 | 0.5636 | 1820 | 0.9396 |
378
+ | 1.0514 | 0.5837 | 1885 | 0.9391 |
379
+ | 1.0412 | 0.6038 | 1950 | 0.9384 |
380
+ | 0.9938 | 0.6240 | 2015 | 0.9365 |
381
+ | 0.9127 | 0.6441 | 2080 | 0.9361 |
382
+ | 1.0269 | 0.6642 | 2145 | 0.9346 |
383
+ | 1.0585 | 0.6843 | 2210 | 0.9336 |
384
+ | 0.9536 | 0.7045 | 2275 | 0.9339 |
385
+ | 1.1411 | 0.7246 | 2340 | 0.9332 |
386
+ | 0.8952 | 0.7447 | 2405 | 0.9322 |
387
+ | 0.8552 | 0.7649 | 2470 | 0.9317 |
388
+ | 0.9325 | 0.7850 | 2535 | 0.9321 |
389
+ | 1.0898 | 0.8051 | 2600 | 0.9318 |
390
+ | 1.0294 | 0.8252 | 2665 | 0.9312 |
391
+ | 0.8656 | 0.8454 | 2730 | 0.9306 |
392
+ | 1.0665 | 0.8655 | 2795 | 0.9298 |
393
+ | 0.9063 | 0.8856 | 2860 | 0.9290 |
394
+ | 0.9511 | 0.9057 | 2925 | 0.9282 |
395
+ | 1.265 | 0.9259 | 2990 | 0.9280 |
396
+ | 0.9484 | 0.9460 | 3055 | 0.9276 |
397
+ | 0.6954 | 0.9661 | 3120 | 0.9274 |
398
+ | 0.9956 | 0.9863 | 3185 | 0.9272 |
399
+ | 1.1228 | 1.0064 | 3250 | 0.9274 |
400
+ | 0.8879 | 1.0265 | 3315 | 0.9273 |
401
+ | 0.8009 | 1.0466 | 3380 | 0.9275 |
402
+ | 0.7103 | 1.0668 | 3445 | 0.9274 |
403
+ | 0.722 | 1.0869 | 3510 | 0.9272 |
404
+ | 0.8266 | 1.1070 | 3575 | 0.9270 |
405
+ | 0.8938 | 1.1272 | 3640 | 0.9269 |
406
+ | 0.9929 | 1.1473 | 3705 | 0.9268 |
407
+ | 0.9501 | 1.1674 | 3770 | 0.9265 |
408
+ | 0.7072 | 1.1875 | 3835 | 0.9266 |
409
+ | 0.9863 | 1.2077 | 3900 | 0.9264 |
410
+ | 0.9762 | 1.2278 | 3965 | 0.9264 |
411
+ | 0.8581 | 1.2479 | 4030 | 0.9262 |
412
+ | 0.6733 | 1.2680 | 4095 | 0.9260 |
413
+ | 0.8357 | 1.2882 | 4160 | 0.9258 |
414
+ | 0.939 | 1.3083 | 4225 | 0.9258 |
415
+ | 0.7996 | 1.3284 | 4290 | 0.9259 |
416
+ | 0.9214 | 1.3486 | 4355 | 0.9255 |
417
+ | 0.825 | 1.3687 | 4420 | 0.9255 |
418
+ | 1.0337 | 1.3888 | 4485 | 0.9254 |
419
+ | 0.8741 | 1.4089 | 4550 | 0.9252 |
420
+ | 0.8318 | 1.4291 | 4615 | 0.9252 |
421
+ | 0.8853 | 1.4492 | 4680 | 0.9251 |
422
+ | 0.7564 | 1.4693 | 4745 | 0.9250 |
423
+ | 0.9914 | 1.4895 | 4810 | 0.9250 |
424
+ | 0.9055 | 1.5096 | 4875 | 0.9249 |
425
+ | 0.7521 | 1.5297 | 4940 | 0.9249 |
426
+ | 0.8773 | 1.5498 | 5005 | 0.9248 |
427
+ | 0.6887 | 1.5700 | 5070 | 0.9248 |
428
+ | 0.8286 | 1.5901 | 5135 | 0.9248 |
429
+ | 0.8133 | 1.6102 | 5200 | 0.9247 |
430
+ | 0.8619 | 1.6303 | 5265 | 0.9248 |
431
+ | 0.829 | 1.6505 | 5330 | 0.9248 |
432
+ | 0.8122 | 1.6706 | 5395 | 0.9247 |
433
+ | 0.9736 | 1.6907 | 5460 | 0.9247 |
434
+ | 0.9063 | 1.7109 | 5525 | 0.9247 |
435
+ | 0.8728 | 1.7310 | 5590 | 0.9246 |
436
+ | 0.9878 | 1.7511 | 5655 | 0.9246 |
437
+ | 0.7732 | 1.7712 | 5720 | 0.9246 |
438
+ | 0.7927 | 1.7914 | 5785 | 0.9246 |
439
+ | 0.93 | 1.8115 | 5850 | 0.9247 |
440
+ | 0.7857 | 1.8316 | 5915 | 0.9246 |
441
+ | 0.9063 | 1.8518 | 5980 | 0.9246 |
442
+ | 0.731 | 1.8719 | 6045 | 0.9246 |
443
+ | 1.0279 | 1.8920 | 6110 | 0.9246 |
444
+ | 0.8261 | 1.9121 | 6175 | 0.9245 |
445
+ | 0.8415 | 1.9323 | 6240 | 0.9246 |
446
+ | 0.8725 | 1.9524 | 6305 | 0.9245 |
447
+ | 0.9803 | 1.9725 | 6370 | 0.9245 |
448
+ | 1.0718 | 1.9926 | 6435 | 0.9245 |
449
+
450
+
451
+ ### Framework versions
452
+
453
+ - Transformers 4.46.3
454
+ - Pytorch 2.5.1+cu124
455
+ - Datasets 3.1.0
456
+ - Tokenizers 0.20.3
pytorch_model-00001-of-00005.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0d068e8c379b218242401dbda4623feb88cfc3a9e5e9f5235bae8c9fbee2908
3
+ size 4865537030
pytorch_model-00002-of-00005.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:705a299420a3a80e462050a5617e8e056c363204cad3e20138e5cab29e33c65d
3
+ size 4907548904
pytorch_model-00003-of-00005.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:172e9d7e61606571b4e3a1e1d062183c2622b8f9c87606edb64a1b2708648630
3
+ size 4907548968
pytorch_model-00004-of-00005.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48fe5298c33c19621ae8b80455a81ff895190a8ae212fe5a1e0bc1eed6d2aa53
3
+ size 4907548968
pytorch_model-00005-of-00005.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7437507e44bf95a0d52006d5ebc5255dd62e6a7646938382100529d73c7f7d3c
3
+ size 4907510770
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,370 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 24495564800
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00005-of-00005.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00005.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
10
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
11
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
13
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
14
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
15
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
16
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
17
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
18
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
19
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
20
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
21
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
22
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
23
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
24
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
25
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
26
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
27
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
28
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
29
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
30
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
31
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
32
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
33
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
34
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
35
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
36
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
37
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
38
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
39
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
40
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
41
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
42
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
43
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
44
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
45
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
46
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
47
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
48
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
49
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
50
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
51
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
52
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
53
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
54
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
55
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
56
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
57
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
58
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
59
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
60
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
61
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
62
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
63
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
64
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
65
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
66
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
67
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
68
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
69
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
70
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
71
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
72
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
73
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
74
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
75
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
76
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
77
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
78
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
79
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
80
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
81
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
82
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
83
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
84
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
85
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
86
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
87
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
88
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
89
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
90
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
91
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
92
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
93
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
94
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
95
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
96
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
97
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
98
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
99
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
100
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
101
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
102
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
103
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
104
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
105
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
106
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
107
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
108
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
109
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
110
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
111
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
112
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
113
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
114
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
115
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
116
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
117
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
118
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
119
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
120
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
121
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
122
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
123
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
124
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
125
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
126
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
127
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
128
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
129
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
130
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
131
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
132
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
133
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
134
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
135
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
136
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
137
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
138
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
139
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
140
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
141
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
142
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
143
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
144
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
145
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
146
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
147
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
148
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
149
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
150
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
151
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
152
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
153
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
154
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
155
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
156
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
157
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
158
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
159
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
160
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
161
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
162
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
163
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
164
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
165
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
166
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
167
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
168
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
169
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
170
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
171
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
172
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
173
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
174
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
175
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
176
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
177
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
178
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
179
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
180
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
181
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
182
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
183
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
184
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
185
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
186
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
187
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
188
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
189
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
190
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
191
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
192
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
193
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
194
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
195
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
196
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
197
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
198
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
199
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
200
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
201
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
202
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
203
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
204
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
205
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
206
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
207
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
208
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
209
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
210
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
211
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
212
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
213
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
214
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
215
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
216
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
217
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
218
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
219
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
220
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
221
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
222
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
223
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
224
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
225
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
226
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
227
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
228
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
229
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
230
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
231
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
232
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
233
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
234
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
235
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
236
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
237
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
238
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
239
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
240
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
241
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
242
+ "model.layers.32.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
243
+ "model.layers.32.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
244
+ "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
245
+ "model.layers.32.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
246
+ "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
247
+ "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
248
+ "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
249
+ "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
250
+ "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
251
+ "model.layers.33.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
252
+ "model.layers.33.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin",
253
+ "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
254
+ "model.layers.33.mlp.up_proj.weight": "pytorch_model-00005-of-00005.bin",
255
+ "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
256
+ "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
257
+ "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
258
+ "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
259
+ "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
260
+ "model.layers.34.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
261
+ "model.layers.34.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin",
262
+ "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00005-of-00005.bin",
263
+ "model.layers.34.mlp.up_proj.weight": "pytorch_model-00005-of-00005.bin",
264
+ "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
265
+ "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00005-of-00005.bin",
266
+ "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00005-of-00005.bin",
267
+ "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00005-of-00005.bin",
268
+ "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00005-of-00005.bin",
269
+ "model.layers.35.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
270
+ "model.layers.35.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin",
271
+ "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00005-of-00005.bin",
272
+ "model.layers.35.mlp.up_proj.weight": "pytorch_model-00005-of-00005.bin",
273
+ "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
274
+ "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00005-of-00005.bin",
275
+ "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00005-of-00005.bin",
276
+ "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00005-of-00005.bin",
277
+ "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00005-of-00005.bin",
278
+ "model.layers.36.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
279
+ "model.layers.36.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin",
280
+ "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00005-of-00005.bin",
281
+ "model.layers.36.mlp.up_proj.weight": "pytorch_model-00005-of-00005.bin",
282
+ "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
283
+ "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00005-of-00005.bin",
284
+ "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00005-of-00005.bin",
285
+ "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00005-of-00005.bin",
286
+ "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00005-of-00005.bin",
287
+ "model.layers.37.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
288
+ "model.layers.37.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin",
289
+ "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00005-of-00005.bin",
290
+ "model.layers.37.mlp.up_proj.weight": "pytorch_model-00005-of-00005.bin",
291
+ "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
292
+ "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00005-of-00005.bin",
293
+ "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00005-of-00005.bin",
294
+ "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00005-of-00005.bin",
295
+ "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00005-of-00005.bin",
296
+ "model.layers.38.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
297
+ "model.layers.38.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin",
298
+ "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00005-of-00005.bin",
299
+ "model.layers.38.mlp.up_proj.weight": "pytorch_model-00005-of-00005.bin",
300
+ "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
301
+ "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00005-of-00005.bin",
302
+ "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00005-of-00005.bin",
303
+ "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00005-of-00005.bin",
304
+ "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00005-of-00005.bin",
305
+ "model.layers.39.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
306
+ "model.layers.39.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin",
307
+ "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00005-of-00005.bin",
308
+ "model.layers.39.mlp.up_proj.weight": "pytorch_model-00005-of-00005.bin",
309
+ "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
310
+ "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00005-of-00005.bin",
311
+ "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00005-of-00005.bin",
312
+ "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00005-of-00005.bin",
313
+ "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00005-of-00005.bin",
314
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
315
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
316
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
317
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
318
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
319
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
320
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
321
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
322
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
323
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
324
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
325
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
326
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
327
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
328
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
329
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
330
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
331
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
332
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
333
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
334
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
335
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
336
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
337
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
338
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
339
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
340
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
341
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
342
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
343
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
344
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
345
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
346
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
347
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
348
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
349
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
350
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
351
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
352
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
353
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
354
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
355
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
356
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
357
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
358
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
359
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
360
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
361
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
362
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
363
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
364
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
365
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
366
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
367
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
368
+ "model.norm.weight": "pytorch_model-00005-of-00005.bin"
369
+ }
370
+ }