Hugging Face's logo

EVA-UNIT-01
/
EVA-Qwen2.5-14B-v0.2

Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
2
Kearm commited on
Commit
669ae9e
•
1 Parent(s): e3aab6e

Upload folder using huggingface_hub

Browse files
Files changed (18) hide show
  1. .gitattributes +1 -0
  2. README.md +424 -0
  3. added_tokens.json +24 -0
  4. config.json +28 -0
  5. generation_config.json +7 -0
  6. merges.txt +0 -0
  7. model-00001-of-00006.safetensors +3 -0
  8. model-00002-of-00006.safetensors +3 -0
  9. model-00003-of-00006.safetensors +3 -0
  10. model-00004-of-00006.safetensors +3 -0
  11. model-00005-of-00006.safetensors +3 -0
  12. model-00006-of-00006.safetensors +3 -0
  13. model.safetensors.index.json +586 -0
  14. special_tokens_map.json +31 -0
  15. tokenizer.json +3 -0
  16. tokenizer_config.json +207 -0
  17. training_args.bin +3 -0
  18. vocab.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,424 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: Qwen/Qwen2.5-14B
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: EVA-Qwen2.5-14B-SFFT-v0.2
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ [<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)
16
+ <details><summary>See axolotl config</summary>
17
+
18
+ axolotl version: `0.4.1`
19
+ ```yaml
20
+ base_model: Qwen/Qwen2.5-14B
21
+
22
+ load_in_8bit: false
23
+ load_in_4bit: false
24
+ strict: false
25
+
26
+ plugins:
27
+ - axolotl.integrations.liger.LigerPlugin
28
+ liger_rope: true
29
+ liger_rms_norm: true
30
+ liger_swiglu: true
31
+ liger_fused_linear_cross_entropy: true
32
+
33
+ # plugins:
34
+ # - axolotl.integrations.spectrum.SpectrumPlugin
35
+
36
+ # spectrum_top_fraction: 0.5
37
+ # # Optional if using a pre-scanned model as your base_model. Useful if using a model mirror
38
+ # spectrum_model_name: Qwen/Qwen2.5-32B
39
+
40
+ datasets:
41
+ - path: datasets/Celeste_Filtered_utf8fix.jsonl
42
+ type: sharegpt
43
+ - path: datasets/deduped_not_samantha_norefusals.jsonl
44
+ type: sharegpt
45
+ - path: datasets/deduped_SynthRP-Gens_processed_ShareGPT_converted_cleaned.jsonl
46
+ type: sharegpt
47
+ - path: datasets/deduped_Synthstruct-Gens_processed_sharegpt_converted_cleaned.jsonl
48
+ type: sharegpt
49
+ - path: datasets/Gryphe-4o-WP-filtered-sharegpt_utf8fix.jsonl
50
+ type: sharegpt
51
+ - path: datasets/opus-instruct-22k-no_refusals-filtered_utf8fix.jsonl
52
+ type: sharegpt
53
+ - path: datasets/Sonnet3-5-charcard-names-filtered-sharegpt_utf8fix.jsonl
54
+ type: sharegpt
55
+ - path: datasets/SystemChat_subset_filtered_sharegpt_utf8fix.jsonl
56
+ type: sharegpt
57
+
58
+ chat_template: chatml
59
+ shuffle_merged_datasets: true
60
+ val_set_size: 0.001
61
+ output_dir: ./EVA-Qwen2.5-14B-SFFT-v0.2
62
+
63
+ sequence_len: 10240
64
+ sample_packing: true
65
+ eval_sample_packing: false
66
+ pad_to_sequence_len: true
67
+
68
+ # adapter: qlora
69
+ # lora_model_dir:
70
+ # lora_r: 64
71
+ # lora_alpha: 128
72
+ # lora_dropout: 0.05
73
+ # lora_target_linear: true
74
+ # peft_use_dora: true
75
+
76
+ base_model: Qwen/Qwen2.5-14B
77
+
78
+ load_in_8bit: false
79
+ load_in_4bit: false
80
+ strict: false
81
+
82
+ plugins:
83
+ - axolotl.integrations.liger.LigerPlugin
84
+ liger_rope: true
85
+ liger_rms_norm: true
86
+ liger_swiglu: true
87
+ liger_fused_linear_cross_entropy: true
88
+
89
+ datasets:
90
+ - path: datasets/Celeste_Filtered_utf8fix.jsonl
91
+ type: sharegpt
92
+ - path: datasets/deduped_not_samantha_norefusals.jsonl
93
+ type: sharegpt
94
+ - path: datasets/deduped_SynthRP-Gens_processed_ShareGPT_converted_cleaned.jsonl
95
+ type: sharegpt
96
+ - path: datasets/deduped_Synthstruct-Gens_processed_sharegpt_converted_cleaned.jsonl
97
+ type: sharegpt
98
+ - path: datasets/Gryphe-4o-WP-filtered-sharegpt_utf8fix.jsonl
99
+ type: sharegpt
100
+ - path: datasets/opus-instruct-22k-no_refusals-filtered_utf8fix.jsonl
101
+ type: sharegpt
102
+ - path: datasets/Sonnet3-5-charcard-names-filtered-sharegpt_utf8fix.jsonl
103
+ type: sharegpt
104
+ - path: datasets/SystemChat_subset_filtered_sharegpt_utf8fix.jsonl
105
+ type: sharegpt
106
+
107
+ chat_template: chatml
108
+ shuffle_merged_datasets: true
109
+ val_set_size: 0.005
110
+ output_dir: ./EVA-Qwen2.5-14B-SFFT-v0.2
111
+
112
+ sequence_len: 10240
113
+ sample_packing: true
114
+ eval_sample_packing: false
115
+ pad_to_sequence_len: true
116
+
117
+ # adapter: qlora
118
+ # lora_model_dir:
119
+ # lora_r: 32
120
+ # lora_alpha: 16
121
+ # lora_dropout: 0.05
122
+ # lora_target_linear: true
123
+ # peft_use_dora: true
124
+
125
+ unfrozen_parameters:
126
+ - ^lm_head.weight$
127
+ - ^model.embed_tokens.weight$
128
+ # mlp.down_proj layers
129
+ - model.layers.1.mlp.down_proj
130
+ - model.layers.35.mlp.down_proj
131
+ - model.layers.38.mlp.down_proj
132
+ - model.layers.37.mlp.down_proj
133
+ - model.layers.36.mlp.down_proj
134
+ - model.layers.15.mlp.down_proj
135
+ - model.layers.11.mlp.down_proj
136
+ - model.layers.12.mlp.down_proj
137
+ - model.layers.34.mlp.down_proj
138
+ - model.layers.44.mlp.down_proj
139
+ - model.layers.45.mlp.down_proj
140
+ - model.layers.9.mlp.down_proj
141
+ - model.layers.41.mlp.down_proj
142
+ - model.layers.33.mlp.down_proj
143
+ - model.layers.43.mlp.down_proj
144
+ - model.layers.40.mlp.down_proj
145
+ - model.layers.13.mlp.down_proj
146
+ - model.layers.8.mlp.down_proj
147
+ - model.layers.39.mlp.down_proj
148
+ - model.layers.10.mlp.down_proj
149
+ - model.layers.14.mlp.down_proj
150
+ - model.layers.16.mlp.down_proj
151
+ - model.layers.31.mlp.down_proj
152
+ - model.layers.32.mlp.down_proj
153
+ # mlp.gate_proj layers
154
+ - model.layers.1.mlp.gate_proj
155
+ - model.layers.44.mlp.gate_proj
156
+ - model.layers.46.mlp.gate_proj
157
+ - model.layers.45.mlp.gate_proj
158
+ - model.layers.43.mlp.gate_proj
159
+ - model.layers.47.mlp.gate_proj
160
+ - model.layers.42.mlp.gate_proj
161
+ - model.layers.32.mlp.gate_proj
162
+ - model.layers.27.mlp.gate_proj
163
+ - model.layers.33.mlp.gate_proj
164
+ - model.layers.28.mlp.gate_proj
165
+ - model.layers.39.mlp.gate_proj
166
+ - model.layers.41.mlp.gate_proj
167
+ - model.layers.40.mlp.gate_proj
168
+ - model.layers.30.mlp.gate_proj
169
+ - model.layers.29.mlp.gate_proj
170
+ - model.layers.31.mlp.gate_proj
171
+ - model.layers.37.mlp.gate_proj
172
+ - model.layers.26.mlp.gate_proj
173
+ - model.layers.10.mlp.gate_proj
174
+ - model.layers.38.mlp.gate_proj
175
+ - model.layers.36.mlp.gate_proj
176
+ - model.layers.12.mlp.gate_proj
177
+ - model.layers.13.mlp.gate_proj
178
+ # mlp.up_proj layers
179
+ - model.layers.1.mlp.up_proj
180
+ - model.layers.13.mlp.up_proj
181
+ - model.layers.11.mlp.up_proj
182
+ - model.layers.14.mlp.up_proj
183
+ - model.layers.15.mlp.up_proj
184
+ - model.layers.12.mlp.up_proj
185
+ - model.layers.8.mlp.up_proj
186
+ - model.layers.16.mlp.up_proj
187
+ - model.layers.9.mlp.up_proj
188
+ - model.layers.19.mlp.up_proj
189
+ - model.layers.10.mlp.up_proj
190
+ - model.layers.7.mlp.up_proj
191
+ - model.layers.17.mlp.up_proj
192
+ - model.layers.20.mlp.up_proj
193
+ - model.layers.21.mlp.up_proj
194
+ - model.layers.18.mlp.up_proj
195
+ - model.layers.37.mlp.up_proj
196
+ - model.layers.38.mlp.up_proj
197
+ - model.layers.39.mlp.up_proj
198
+ - model.layers.42.mlp.up_proj
199
+ - model.layers.41.mlp.up_proj
200
+ - model.layers.27.mlp.up_proj
201
+ - model.layers.28.mlp.up_proj
202
+ - model.layers.36.mlp.up_proj
203
+ # self_attn.k_proj layers
204
+ - model.layers.47.self_attn.k_proj
205
+ - model.layers.39.self_attn.k_proj
206
+ - model.layers.41.self_attn.k_proj
207
+ - model.layers.37.self_attn.k_proj
208
+ - model.layers.35.self_attn.k_proj
209
+ - model.layers.44.self_attn.k_proj
210
+ - model.layers.38.self_attn.k_proj
211
+ - model.layers.14.self_attn.k_proj
212
+ - model.layers.7.self_attn.k_proj
213
+ - model.layers.12.self_attn.k_proj
214
+ - model.layers.11.self_attn.k_proj
215
+ - model.layers.32.self_attn.k_proj
216
+ - model.layers.10.self_attn.k_proj
217
+ - model.layers.8.self_attn.k_proj
218
+ - model.layers.6.self_attn.k_proj
219
+ - model.layers.9.self_attn.k_proj
220
+ - model.layers.45.self_attn.k_proj
221
+ - model.layers.42.self_attn.k_proj
222
+ - model.layers.40.self_attn.k_proj
223
+ - model.layers.5.self_attn.k_proj
224
+ - model.layers.0.self_attn.k_proj
225
+ - model.layers.33.self_attn.k_proj
226
+ - model.layers.34.self_attn.k_proj
227
+ - model.layers.13.self_attn.k_proj
228
+ # self_attn.o_proj layers
229
+ - model.layers.12.self_attn.o_proj
230
+ - model.layers.5.self_attn.o_proj
231
+ - model.layers.14.self_attn.o_proj
232
+ - model.layers.16.self_attn.o_proj
233
+ - model.layers.20.self_attn.o_proj
234
+ - model.layers.13.self_attn.o_proj
235
+ - model.layers.11.self_attn.o_proj
236
+ - model.layers.4.self_attn.o_proj
237
+ - model.layers.6.self_attn.o_proj
238
+ - model.layers.19.self_attn.o_proj
239
+ - model.layers.7.self_attn.o_proj
240
+ - model.layers.18.self_attn.o_proj
241
+ - model.layers.8.self_attn.o_proj
242
+ - model.layers.38.self_attn.o_proj
243
+ - model.layers.15.self_attn.o_proj
244
+ - model.layers.17.self_attn.o_proj
245
+ - model.layers.9.self_attn.o_proj
246
+ - model.layers.10.self_attn.o_proj
247
+ - model.layers.21.self_attn.o_proj
248
+ - model.layers.28.self_attn.o_proj
249
+ - model.layers.32.self_attn.o_proj
250
+ - model.layers.35.self_attn.o_proj
251
+ - model.layers.39.self_attn.o_proj
252
+ - model.layers.3.self_attn.o_proj
253
+ # self_attn.q_proj layers
254
+ - model.layers.1.self_attn.q_proj
255
+ - model.layers.2.self_attn.q_proj
256
+ - model.layers.3.self_attn.q_proj
257
+ - model.layers.44.self_attn.q_proj
258
+ - model.layers.29.self_attn.q_proj
259
+ - model.layers.45.self_attn.q_proj
260
+ - model.layers.43.self_attn.q_proj
261
+ - model.layers.32.self_attn.q_proj
262
+ - model.layers.38.self_attn.q_proj
263
+ - model.layers.19.self_attn.q_proj
264
+ - model.layers.42.self_attn.q_proj
265
+ - model.layers.34.self_attn.q_proj
266
+ - model.layers.36.self_attn.q_proj
267
+ - model.layers.40.self_attn.q_proj
268
+ - model.layers.26.self_attn.q_proj
269
+ - model.layers.20.self_attn.q_proj
270
+ - model.layers.28.self_attn.q_proj
271
+ - model.layers.39.self_attn.q_proj
272
+ - model.layers.41.self_attn.q_proj
273
+ - model.layers.33.self_attn.q_proj
274
+ - model.layers.35.self_attn.q_proj
275
+ - model.layers.25.self_attn.q_proj
276
+ - model.layers.30.self_attn.q_proj
277
+ - model.layers.27.self_attn.q_proj
278
+ # self_attn.v_proj layers
279
+ - model.layers.0.self_attn.v_proj
280
+ - model.layers.7.self_attn.v_proj
281
+ - model.layers.39.self_attn.v_proj
282
+ - model.layers.31.self_attn.v_proj
283
+ - model.layers.15.self_attn.v_proj
284
+ - model.layers.10.self_attn.v_proj
285
+ - model.layers.41.self_attn.v_proj
286
+ - model.layers.32.self_attn.v_proj
287
+ - model.layers.6.self_attn.v_proj
288
+ - model.layers.33.self_attn.v_proj
289
+ - model.layers.42.self_attn.v_proj
290
+ - model.layers.29.self_attn.v_proj
291
+ - model.layers.9.self_attn.v_proj
292
+ - model.layers.14.self_attn.v_proj
293
+ - model.layers.35.self_attn.v_proj
294
+ - model.layers.38.self_attn.v_proj
295
+ - model.layers.13.self_attn.v_proj
296
+ - model.layers.30.self_attn.v_proj
297
+ - model.layers.34.self_attn.v_proj
298
+ - model.layers.5.self_attn.v_proj
299
+ - model.layers.28.self_attn.v_proj
300
+ - model.layers.37.self_attn.v_proj
301
+ - model.layers.27.self_attn.v_proj
302
+ - model.layers.11.self_attn.v_proj
303
+
304
+ wandb_project: EVA-Qwen2.5-14B-SFFT-v0.2
305
+ wandb_entity:
306
+ wandb_watch:
307
+ wandb_name: Unit-02
308
+ wandb_log_model:
309
+
310
+ gradient_accumulation_steps: 8
311
+ micro_batch_size: 2
312
+ num_epochs: 3
313
+ optimizer: paged_ademamix_8bit
314
+ lr_scheduler: cosine
315
+ learning_rate: 0.00005
316
+ max_grad_norm: 3
317
+
318
+ train_on_inputs: false
319
+ group_by_length: false
320
+ bf16: auto
321
+ fp16:
322
+ tf32: false
323
+
324
+ gradient_checkpointing: "unsloth"
325
+ # gradient_checkpointing_kwargs:
326
+ # use_reentrant: true
327
+ early_stopping_patience:
328
+ resume_from_checkpoint:
329
+ local_rank:
330
+ logging_steps: 1
331
+ xformers_attention:
332
+ flash_attention: true
333
+
334
+ warmup_steps: 20
335
+ evals_per_epoch: 4
336
+ saves_per_epoch: 4
337
+ save_safetensors: true
338
+ hub_model_id:
339
+ hub_strategy:
340
+ debug:
341
+ deepspeed: deepspeed_configs/zero3_bf16.json
342
+ weight_decay: 0.1
343
+ # fsdp:
344
+ # - full_shard
345
+ # - auto_wrap
346
+ # fsdp_config:
347
+ # fsdp_limit_all_gathers: true
348
+ # fsdp_sync_module_states: false
349
+ # fsdp_offload_params: true
350
+ # fsdp_cpu_ram_efficient_loading: true
351
+ # fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
352
+ # fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
353
+ # fsdp_activation_checkpointing: true
354
+ # fsdp_state_dict_type: SHARDED_STATE_DICT # Changed from FULL_STATE_DICT
355
+ # fsdp_sharding_strategy: FULL_SHARD
356
+ # fsdp_forward_prefetch: false # Added
357
+ # fsdp_backward_prefetch: "BACKWARD_PRE" # Added
358
+ # fsdp_backward_prefetch_limit: 1 # Added
359
+ # fsdp_mixed_precision: BF16 # Added
360
+ ```
361
+
362
+ </details><br>
363
+
364
+ # EVA-Qwen2.5-14B-SFFT-v0.2
365
+
366
+ This model is a fine-tuned version of [Qwen/Qwen2.5-14B](https://huggingface.co/Qwen/Qwen2.5-14B) on the None dataset.
367
+ It achieves the following results on the evaluation set:
368
+ - Loss: 3.0986
369
+
370
+ ## Model description
371
+
372
+ More information needed
373
+
374
+ ## Intended uses & limitations
375
+
376
+ More information needed
377
+
378
+ ## Training and evaluation data
379
+
380
+ More information needed
381
+
382
+ ## Training procedure
383
+
384
+ ### Training hyperparameters
385
+
386
+ The following hyperparameters were used during training:
387
+ - learning_rate: 5e-05
388
+ - train_batch_size: 2
389
+ - eval_batch_size: 2
390
+ - seed: 42
391
+ - distributed_type: multi-GPU
392
+ - num_devices: 8
393
+ - gradient_accumulation_steps: 8
394
+ - total_train_batch_size: 128
395
+ - total_eval_batch_size: 16
396
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
397
+ - lr_scheduler_type: cosine
398
+ - lr_scheduler_warmup_steps: 20
399
+ - num_epochs: 3
400
+
401
+ ### Training results
402
+
403
+ | Training Loss | Epoch | Step | Validation Loss |
404
+ |:-------------:|:------:|:----:|:---------------:|
405
+ | 1.4236 | 0.0170 | 1 | 2.6557 |
406
+ | 1.2513 | 0.2553 | 15 | 3.4606 |
407
+ | 1.1338 | 0.5106 | 30 | 3.5536 |
408
+ | 1.0985 | 0.7660 | 45 | 3.1957 |
409
+ | 0.8794 | 1.0170 | 60 | 3.0346 |
410
+ | 0.8584 | 1.2718 | 75 | 3.0551 |
411
+ | 0.8421 | 1.5265 | 90 | 3.0168 |
412
+ | 0.8081 | 1.7813 | 105 | 3.0335 |
413
+ | 0.8227 | 2.0361 | 120 | 3.0369 |
414
+ | 0.7416 | 2.2909 | 135 | 3.0876 |
415
+ | 0.7396 | 2.5456 | 150 | 3.1023 |
416
+ | 0.7775 | 2.8004 | 165 | 3.0986 |
417
+
418
+
419
+ ### Framework versions
420
+
421
+ - Transformers 4.45.1
422
+ - Pytorch 2.4.0+cu121
423
+ - Datasets 2.21.0
424
+ - Tokenizers 0.20.2
added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Qwen/Qwen2.5-14B",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "eos_token_id": 151643,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 5120,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 13824,
12
+ "max_position_embeddings": 131072,
13
+ "max_window_layers": 48,
14
+ "model_type": "qwen2",
15
+ "num_attention_heads": 40,
16
+ "num_hidden_layers": 48,
17
+ "num_key_value_heads": 8,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_scaling": null,
20
+ "rope_theta": 1000000.0,
21
+ "sliding_window": null,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.45.1",
25
+ "use_cache": false,
26
+ "use_sliding_window": false,
27
+ "vocab_size": 152064
28
+ }
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": "4.45.1"
7
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca3ceb36bae82d97e737423b3d45e10c6ae243f61439f3ddcb4b69727f796f03
3
+ size 4986211280
model-00002-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab172d7c4575c3b933c9d3b35e84fba0e8737e0096f796584b164f770194499f
3
+ size 4954847344
model-00003-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83906c384bc856078b53c776a3f174a5f3ddafccd58c098f5c4d6434e5bf1523
3
+ size 4954847392
model-00004-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f9ce10581f969024e9caefe656e513eb5f000d933af1f05ca2569708497940e
3
+ size 4954847392
model-00005-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c114767d56ba3e2c99cf66ede6f68bbcbd44352faf0edb37713bb02234528c71
3
+ size 4954847392
model-00006-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3dd4edb047e3b2cde2f674015a939b0e60d6f2d3a0b961766e4185cbd9cbcea2
3
+ size 4734533160
model.safetensors.index.json ADDED
@@ -0,0 +1,586 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 29540067328
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00006-of-00006.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
13
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
16
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
17
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
18
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
19
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
20
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
21
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
22
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
23
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
24
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
25
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
26
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
27
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
28
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
29
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
30
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
31
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
32
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
33
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
34
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
35
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
36
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
37
+ "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
38
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
39
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
40
+ "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
41
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
42
+ "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
43
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
44
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
45
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
46
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
47
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
48
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
49
+ "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
50
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
51
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
52
+ "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
53
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
54
+ "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
55
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
56
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
57
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
58
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
59
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
60
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
61
+ "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
62
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
63
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
64
+ "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
65
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
66
+ "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
67
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
68
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors",
69
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
70
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
71
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
72
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
73
+ "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
74
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
75
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
76
+ "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
77
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
78
+ "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
79
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
80
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors",
81
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
82
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
83
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
84
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
85
+ "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
86
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
87
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
88
+ "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
89
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
90
+ "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
91
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
92
+ "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
93
+ "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
94
+ "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
95
+ "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
96
+ "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
97
+ "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
98
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
99
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
100
+ "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
101
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
102
+ "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
103
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
104
+ "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
105
+ "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
106
+ "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
107
+ "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
108
+ "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
109
+ "model.layers.16.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
110
+ "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
111
+ "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
112
+ "model.layers.16.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
113
+ "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
114
+ "model.layers.16.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
115
+ "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
116
+ "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
117
+ "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
118
+ "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
119
+ "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
120
+ "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
121
+ "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
122
+ "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
123
+ "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
124
+ "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
125
+ "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
126
+ "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
127
+ "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
128
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
129
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
130
+ "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
131
+ "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
132
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
133
+ "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
134
+ "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
135
+ "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
136
+ "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
137
+ "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
138
+ "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
139
+ "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
140
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
141
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
142
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
143
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
144
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
145
+ "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
146
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
147
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
148
+ "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
149
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
150
+ "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
151
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
152
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
153
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
154
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
155
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
156
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
157
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
158
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
159
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
160
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
161
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
162
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
163
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
164
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors",
165
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
166
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
167
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
168
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
169
+ "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
170
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
171
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
172
+ "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
173
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
174
+ "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
175
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
176
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors",
177
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
178
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
179
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
180
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
181
+ "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
182
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
183
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
184
+ "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
185
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
186
+ "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
187
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
188
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00006.safetensors",
189
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
190
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
191
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
192
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
193
+ "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
194
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
195
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
196
+ "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
197
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
198
+ "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
199
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
200
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00006.safetensors",
201
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
202
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
203
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
204
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
205
+ "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
206
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
207
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
208
+ "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
209
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
210
+ "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
211
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
212
+ "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
213
+ "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
214
+ "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
215
+ "model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
216
+ "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
217
+ "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
218
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
219
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
220
+ "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
221
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
222
+ "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
223
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
224
+ "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
225
+ "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
226
+ "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
227
+ "model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
228
+ "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
229
+ "model.layers.25.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
230
+ "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
231
+ "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
232
+ "model.layers.25.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
233
+ "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
234
+ "model.layers.25.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
235
+ "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
236
+ "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
237
+ "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
238
+ "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
239
+ "model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
240
+ "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
241
+ "model.layers.26.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
242
+ "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
243
+ "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
244
+ "model.layers.26.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
245
+ "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
246
+ "model.layers.26.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
247
+ "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
248
+ "model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors",
249
+ "model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
250
+ "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
251
+ "model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
252
+ "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
253
+ "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
254
+ "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
255
+ "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
256
+ "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
257
+ "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
258
+ "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
259
+ "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
260
+ "model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors",
261
+ "model.layers.28.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
262
+ "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
263
+ "model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
264
+ "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
265
+ "model.layers.28.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
266
+ "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
267
+ "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
268
+ "model.layers.28.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
269
+ "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
270
+ "model.layers.28.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
271
+ "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
272
+ "model.layers.29.input_layernorm.weight": "model-00004-of-00006.safetensors",
273
+ "model.layers.29.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
274
+ "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
275
+ "model.layers.29.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
276
+ "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
277
+ "model.layers.29.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
278
+ "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
279
+ "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
280
+ "model.layers.29.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
281
+ "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
282
+ "model.layers.29.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
283
+ "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
284
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
285
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
286
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
287
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
288
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
289
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
290
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
291
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
292
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
293
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
294
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
295
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
296
+ "model.layers.30.input_layernorm.weight": "model-00004-of-00006.safetensors",
297
+ "model.layers.30.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
298
+ "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
299
+ "model.layers.30.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
300
+ "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
301
+ "model.layers.30.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
302
+ "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
303
+ "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
304
+ "model.layers.30.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
305
+ "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
306
+ "model.layers.30.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
307
+ "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
308
+ "model.layers.31.input_layernorm.weight": "model-00004-of-00006.safetensors",
309
+ "model.layers.31.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
310
+ "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
311
+ "model.layers.31.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
312
+ "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
313
+ "model.layers.31.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
314
+ "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
315
+ "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
316
+ "model.layers.31.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
317
+ "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
318
+ "model.layers.31.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
319
+ "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
320
+ "model.layers.32.input_layernorm.weight": "model-00004-of-00006.safetensors",
321
+ "model.layers.32.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
322
+ "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
323
+ "model.layers.32.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
324
+ "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
325
+ "model.layers.32.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
326
+ "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
327
+ "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
328
+ "model.layers.32.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
329
+ "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
330
+ "model.layers.32.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
331
+ "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
332
+ "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
333
+ "model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
334
+ "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
335
+ "model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
336
+ "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
337
+ "model.layers.33.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
338
+ "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
339
+ "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
340
+ "model.layers.33.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
341
+ "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
342
+ "model.layers.33.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
343
+ "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
344
+ "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
345
+ "model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
346
+ "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
347
+ "model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
348
+ "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
349
+ "model.layers.34.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
350
+ "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
351
+ "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
352
+ "model.layers.34.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
353
+ "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
354
+ "model.layers.34.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
355
+ "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
356
+ "model.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors",
357
+ "model.layers.35.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
358
+ "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
359
+ "model.layers.35.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
360
+ "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
361
+ "model.layers.35.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
362
+ "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
363
+ "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
364
+ "model.layers.35.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
365
+ "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
366
+ "model.layers.35.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
367
+ "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
368
+ "model.layers.36.input_layernorm.weight": "model-00005-of-00006.safetensors",
369
+ "model.layers.36.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
370
+ "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
371
+ "model.layers.36.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
372
+ "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
373
+ "model.layers.36.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
374
+ "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
375
+ "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
376
+ "model.layers.36.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
377
+ "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
378
+ "model.layers.36.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
379
+ "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
380
+ "model.layers.37.input_layernorm.weight": "model-00005-of-00006.safetensors",
381
+ "model.layers.37.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
382
+ "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
383
+ "model.layers.37.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
384
+ "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
385
+ "model.layers.37.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
386
+ "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
387
+ "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
388
+ "model.layers.37.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
389
+ "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
390
+ "model.layers.37.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
391
+ "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
392
+ "model.layers.38.input_layernorm.weight": "model-00005-of-00006.safetensors",
393
+ "model.layers.38.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
394
+ "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
395
+ "model.layers.38.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
396
+ "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
397
+ "model.layers.38.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
398
+ "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
399
+ "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
400
+ "model.layers.38.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
401
+ "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
402
+ "model.layers.38.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
403
+ "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
404
+ "model.layers.39.input_layernorm.weight": "model-00005-of-00006.safetensors",
405
+ "model.layers.39.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
406
+ "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
407
+ "model.layers.39.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
408
+ "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
409
+ "model.layers.39.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
410
+ "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
411
+ "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
412
+ "model.layers.39.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
413
+ "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
414
+ "model.layers.39.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
415
+ "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
416
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
417
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
418
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
419
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
420
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
421
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
422
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
423
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
424
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
425
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
426
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
427
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
428
+ "model.layers.40.input_layernorm.weight": "model-00005-of-00006.safetensors",
429
+ "model.layers.40.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
430
+ "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
431
+ "model.layers.40.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
432
+ "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
433
+ "model.layers.40.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
434
+ "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
435
+ "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
436
+ "model.layers.40.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
437
+ "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
438
+ "model.layers.40.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
439
+ "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
440
+ "model.layers.41.input_layernorm.weight": "model-00005-of-00006.safetensors",
441
+ "model.layers.41.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
442
+ "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
443
+ "model.layers.41.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
444
+ "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
445
+ "model.layers.41.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
446
+ "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
447
+ "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
448
+ "model.layers.41.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
449
+ "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
450
+ "model.layers.41.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
451
+ "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
452
+ "model.layers.42.input_layernorm.weight": "model-00006-of-00006.safetensors",
453
+ "model.layers.42.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
454
+ "model.layers.42.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
455
+ "model.layers.42.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
456
+ "model.layers.42.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
457
+ "model.layers.42.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
458
+ "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
459
+ "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
460
+ "model.layers.42.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
461
+ "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
462
+ "model.layers.42.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
463
+ "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
464
+ "model.layers.43.input_layernorm.weight": "model-00006-of-00006.safetensors",
465
+ "model.layers.43.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
466
+ "model.layers.43.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
467
+ "model.layers.43.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
468
+ "model.layers.43.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
469
+ "model.layers.43.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
470
+ "model.layers.43.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
471
+ "model.layers.43.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
472
+ "model.layers.43.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
473
+ "model.layers.43.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
474
+ "model.layers.43.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
475
+ "model.layers.43.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
476
+ "model.layers.44.input_layernorm.weight": "model-00006-of-00006.safetensors",
477
+ "model.layers.44.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
478
+ "model.layers.44.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
479
+ "model.layers.44.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
480
+ "model.layers.44.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
481
+ "model.layers.44.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
482
+ "model.layers.44.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
483
+ "model.layers.44.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
484
+ "model.layers.44.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
485
+ "model.layers.44.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
486
+ "model.layers.44.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
487
+ "model.layers.44.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
488
+ "model.layers.45.input_layernorm.weight": "model-00006-of-00006.safetensors",
489
+ "model.layers.45.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
490
+ "model.layers.45.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
491
+ "model.layers.45.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
492
+ "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
493
+ "model.layers.45.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
494
+ "model.layers.45.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
495
+ "model.layers.45.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
496
+ "model.layers.45.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
497
+ "model.layers.45.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
498
+ "model.layers.45.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
499
+ "model.layers.45.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
500
+ "model.layers.46.input_layernorm.weight": "model-00006-of-00006.safetensors",
501
+ "model.layers.46.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
502
+ "model.layers.46.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
503
+ "model.layers.46.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
504
+ "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
505
+ "model.layers.46.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
506
+ "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
507
+ "model.layers.46.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
508
+ "model.layers.46.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
509
+ "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
510
+ "model.layers.46.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
511
+ "model.layers.46.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
512
+ "model.layers.47.input_layernorm.weight": "model-00006-of-00006.safetensors",
513
+ "model.layers.47.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
514
+ "model.layers.47.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
515
+ "model.layers.47.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
516
+ "model.layers.47.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
517
+ "model.layers.47.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
518
+ "model.layers.47.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
519
+ "model.layers.47.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
520
+ "model.layers.47.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
521
+ "model.layers.47.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
522
+ "model.layers.47.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
523
+ "model.layers.47.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
524
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
525
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
526
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
527
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
528
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
529
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
530
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
531
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
532
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
533
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
534
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
535
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
536
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
537
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
538
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
539
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
540
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
541
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
542
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
543
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
544
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
545
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
546
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
547
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
548
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
549
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
550
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
551
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
552
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
553
+ "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
554
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
555
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
556
+ "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
557
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
558
+ "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
559
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
560
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
561
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
562
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
563
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
564
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
565
+ "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
566
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
567
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
568
+ "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
569
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
570
+ "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
571
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
572
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
573
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
574
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
575
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
576
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
577
+ "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
578
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
579
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
580
+ "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
581
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
582
+ "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
583
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
584
+ "model.norm.weight": "model-00006-of-00006.safetensors"
585
+ }
586
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
tokenizer_config.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "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 %}",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|endoftext|>",
201
+ "errors": "replace",
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "split_special_tokens": false,
205
+ "tokenizer_class": "Qwen2Tokenizer",
206
+ "unk_token": null
207
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e2367e64e93370cefbe9d352c95e5c9ee3effb08432854f09a95b6f4f15f14e
3
+ size 8056
vocab.json ADDED
The diff for this file is too large to render. See raw diff