Hugging Face's logo

LLMTeamAkiyama
/
sft_cleand_open-r1_codeforces-cots

Safetensors
qwen2
Model card Files
xet
Community
if001 commited on
Commit
3e5c9d0
·
verified ·
1 Parent(s): 9aef1d6

update files

Browse files
Files changed (20) hide show
  1. .gitattributes +1 -0
  2. args.json +385 -0
  3. config.json +29 -0
  4. model-00001-of-00014.safetensors +3 -0
  5. model-00002-of-00014.safetensors +3 -0
  6. model-00003-of-00014.safetensors +3 -0
  7. model-00004-of-00014.safetensors +3 -0
  8. model-00005-of-00014.safetensors +3 -0
  9. model-00006-of-00014.safetensors +3 -0
  10. model-00007-of-00014.safetensors +3 -0
  11. model-00008-of-00014.safetensors +3 -0
  12. model-00009-of-00014.safetensors +3 -0
  13. model-00010-of-00014.safetensors +3 -0
  14. model-00011-of-00014.safetensors +3 -0
  15. model-00012-of-00014.safetensors +3 -0
  16. model-00013-of-00014.safetensors +3 -0
  17. model-00014-of-00014.safetensors +3 -0
  18. model.safetensors.index.json +778 -0
  19. tokenizer.json +3 -0
  20. tokenizer_config.json +35 -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
args.json ADDED
@@ -0,0 +1,385 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "output_dir": "/home/Competition2025/P09/P09U016/llm_sft_dpo_grpo/outputs/sft_cleand_open-r1_codeforces-cots/v0-20250808-190458",
3
+ "overwrite_output_dir": false,
4
+ "do_train": false,
5
+ "do_eval": false,
6
+ "do_predict": false,
7
+ "eval_strategy": "steps",
8
+ "prediction_loss_only": false,
9
+ "per_device_train_batch_size": 1,
10
+ "per_device_eval_batch_size": 1,
11
+ "per_gpu_train_batch_size": null,
12
+ "per_gpu_eval_batch_size": null,
13
+ "gradient_accumulation_steps": 1,
14
+ "eval_accumulation_steps": null,
15
+ "eval_delay": 0,
16
+ "torch_empty_cache_steps": null,
17
+ "learning_rate": 1e-05,
18
+ "weight_decay": 0.1,
19
+ "adam_beta1": 0.9,
20
+ "adam_beta2": 0.95,
21
+ "adam_epsilon": 1e-08,
22
+ "max_grad_norm": 1.0,
23
+ "num_train_epochs": 1.0,
24
+ "max_steps": -1,
25
+ "lr_scheduler_type": "cosine",
26
+ "lr_scheduler_kwargs": null,
27
+ "warmup_ratio": 0.05,
28
+ "warmup_steps": 0,
29
+ "log_level": "passive",
30
+ "log_level_replica": "warning",
31
+ "log_on_each_node": true,
32
+ "logging_dir": "/home/Competition2025/P09/P09U016/llm_sft_dpo_grpo/outputs/sft_cleand_open-r1_codeforces-cots/v0-20250808-190458/runs",
33
+ "logging_strategy": "steps",
34
+ "logging_first_step": true,
35
+ "logging_steps": 5,
36
+ "logging_nan_inf_filter": true,
37
+ "save_strategy": "steps",
38
+ "save_steps": 1000.0,
39
+ "save_total_limit": 2,
40
+ "save_safetensors": true,
41
+ "save_on_each_node": false,
42
+ "save_only_model": false,
43
+ "restore_callback_states_from_checkpoint": false,
44
+ "no_cuda": false,
45
+ "use_cpu": false,
46
+ "use_mps_device": false,
47
+ "seed": 42,
48
+ "data_seed": 42,
49
+ "jit_mode_eval": false,
50
+ "use_ipex": false,
51
+ "bf16": true,
52
+ "fp16": false,
53
+ "fp16_opt_level": "O1",
54
+ "half_precision_backend": "auto",
55
+ "bf16_full_eval": false,
56
+ "fp16_full_eval": false,
57
+ "tf32": null,
58
+ "local_rank": 0,
59
+ "ddp_backend": null,
60
+ "tpu_num_cores": null,
61
+ "tpu_metrics_debug": false,
62
+ "debug": null,
63
+ "dataloader_drop_last": false,
64
+ "eval_steps": 1000.0,
65
+ "dataloader_num_workers": 2,
66
+ "dataloader_prefetch_factor": null,
67
+ "past_index": -1,
68
+ "run_name": "sft_sft_cleand_open-r1_codeforces-cots-n2-gpu4-pp8-gc1-batch1-zero3",
69
+ "disable_tqdm": null,
70
+ "remove_unused_columns": true,
71
+ "label_names": null,
72
+ "load_best_model_at_end": false,
73
+ "metric_for_best_model": "loss",
74
+ "greater_is_better": false,
75
+ "ignore_data_skip": false,
76
+ "fsdp": "",
77
+ "fsdp_min_num_params": 0,
78
+ "fsdp_config": null,
79
+ "fsdp_transformer_layer_cls_to_wrap": null,
80
+ "accelerator_config": {
81
+ "dispatch_batches": false
82
+ },
83
+ "deepspeed": {
84
+ "fp16": {
85
+ "enabled": "auto"
86
+ },
87
+ "bf16": {
88
+ "enabled": "auto"
89
+ },
90
+ "zero_optimization": {
91
+ "stage": 3,
92
+ "offload_optimizer": {
93
+ "device": "none",
94
+ "pin_memory": true
95
+ },
96
+ "offload_param": {
97
+ "device": "none",
98
+ "pin_memory": true
99
+ },
100
+ "overlap_comm": false,
101
+ "contiguous_gradients": true,
102
+ "sub_group_size": 1000000000.0,
103
+ "reduce_bucket_size": "auto",
104
+ "zero_quantized_weights": false,
105
+ "zero_quantized_gradients": false,
106
+ "stage3_prefetch_bucket_size": "auto",
107
+ "stage3_param_persistence_threshold": "auto",
108
+ "stage3_max_live_parameters": 1000000000.0,
109
+ "stage3_max_reuse_distance": 1000000000.0,
110
+ "stage3_gather_16bit_weights_on_model_save": true
111
+ },
112
+ "gradient_accumulation_steps": "auto",
113
+ "gradient_clipping": "auto",
114
+ "steps_per_print": 2000,
115
+ "train_batch_size": "auto",
116
+ "train_micro_batch_size_per_gpu": "auto",
117
+ "wall_clock_breakdown": false,
118
+ "pipeline_parallel": {
119
+ "enabled": true,
120
+ "pp_size": 8
121
+ },
122
+ "activation_checkpointing": {
123
+ "partition_activations": true,
124
+ "cpu_checkpointing": false,
125
+ "contiguous_memory_optimization": true,
126
+ "number_checkpoints": null,
127
+ "synchronize_checkpoint_boundary": false,
128
+ "profile": false
129
+ }
130
+ },
131
+ "label_smoothing_factor": 0.0,
132
+ "optim": "adamw_torch",
133
+ "optim_args": null,
134
+ "adafactor": false,
135
+ "group_by_length": false,
136
+ "length_column_name": "length",
137
+ "report_to": [
138
+ "wandb"
139
+ ],
140
+ "ddp_find_unused_parameters": null,
141
+ "ddp_bucket_cap_mb": null,
142
+ "ddp_broadcast_buffers": null,
143
+ "dataloader_pin_memory": true,
144
+ "dataloader_persistent_workers": false,
145
+ "skip_memory_metrics": true,
146
+ "use_legacy_prediction_loop": false,
147
+ "push_to_hub": false,
148
+ "resume_from_checkpoint": null,
149
+ "hub_model_id": null,
150
+ "hub_strategy": "every_save",
151
+ "hub_token": null,
152
+ "hub_private_repo": null,
153
+ "hub_always_push": false,
154
+ "gradient_checkpointing": true,
155
+ "gradient_checkpointing_kwargs": null,
156
+ "include_inputs_for_metrics": false,
157
+ "include_for_metrics": [],
158
+ "eval_do_concat_batches": true,
159
+ "fp16_backend": "auto",
160
+ "push_to_hub_model_id": null,
161
+ "push_to_hub_organization": null,
162
+ "push_to_hub_token": null,
163
+ "mp_parameters": "",
164
+ "auto_find_batch_size": false,
165
+ "full_determinism": false,
166
+ "torchdynamo": null,
167
+ "ray_scope": "last",
168
+ "ddp_timeout": 18000000,
169
+ "torch_compile": false,
170
+ "torch_compile_backend": null,
171
+ "torch_compile_mode": null,
172
+ "include_tokens_per_second": false,
173
+ "include_num_input_tokens_seen": false,
174
+ "neftune_noise_alpha": null,
175
+ "optim_target_modules": null,
176
+ "batch_eval_metrics": false,
177
+ "eval_on_start": false,
178
+ "use_liger_kernel": false,
179
+ "eval_use_gather_object": false,
180
+ "average_tokens_across_devices": false,
181
+ "sortish_sampler": false,
182
+ "predict_with_generate": false,
183
+ "generation_max_length": null,
184
+ "generation_num_beams": null,
185
+ "generation_config": null,
186
+ "vit_gradient_checkpointing": null,
187
+ "check_model": true,
188
+ "acc_strategy": "token",
189
+ "train_dataloader_shuffle": true,
190
+ "max_epochs": null,
191
+ "aligner_lr": null,
192
+ "vit_lr": null,
193
+ "optimizer": null,
194
+ "use_logits_to_keep": null,
195
+ "channels": null,
196
+ "ds3_gather_for_generation": true,
197
+ "metric_warmup_step": 0,
198
+ "fsdp_num": 1,
199
+ "acc_steps": 1,
200
+ "eval_use_evalscope": false,
201
+ "eval_dataset": [],
202
+ "eval_dataset_args": null,
203
+ "eval_limit": null,
204
+ "eval_generation_config": null,
205
+ "model": "/home/Competition2025/P09/shareP09/models/DeepSeek-R1-Distill-Qwen-32B",
206
+ "model_type": "deepseek_r1_distill",
207
+ "model_revision": null,
208
+ "task_type": "causal_lm",
209
+ "torch_dtype": "bfloat16",
210
+ "attn_impl": "flash_attn",
211
+ "num_labels": null,
212
+ "problem_type": null,
213
+ "rope_scaling": null,
214
+ "device_map": null,
215
+ "max_memory": {},
216
+ "local_repo_path": null,
217
+ "init_strategy": null,
218
+ "template": "deepseek_r1",
219
+ "system": "You are a helpful assistant.",
220
+ "max_length": 2048,
221
+ "truncation_strategy": "delete",
222
+ "max_pixels": null,
223
+ "agent_template": null,
224
+ "norm_bbox": null,
225
+ "use_chat_template": true,
226
+ "padding_free": false,
227
+ "padding_side": "right",
228
+ "loss_scale": "ignore_empty_think",
229
+ "sequence_parallel_size": 1,
230
+ "response_prefix": null,
231
+ "template_backend": "swift",
232
+ "dataset": [
233
+ "hf::LLMTeamAkiyama/cleand_open-r1_codeforces-cots#100000"
234
+ ],
235
+ "val_dataset": [],
236
+ "split_dataset_ratio": 0.01,
237
+ "dataset_num_proc": 12,
238
+ "load_from_cache_file": true,
239
+ "dataset_shuffle": true,
240
+ "val_dataset_shuffle": false,
241
+ "streaming": false,
242
+ "interleave_prob": null,
243
+ "stopping_strategy": "first_exhausted",
244
+ "shuffle_buffer_size": 1000,
245
+ "download_mode": "reuse_dataset_if_exists",
246
+ "columns": {},
247
+ "strict": false,
248
+ "model_name": [
249
+ "swift-robot"
250
+ ],
251
+ "model_author": [
252
+ "swift"
253
+ ],
254
+ "custom_dataset_info": [],
255
+ "quant_method": null,
256
+ "quant_bits": null,
257
+ "hqq_axis": null,
258
+ "bnb_4bit_compute_dtype": "bfloat16",
259
+ "bnb_4bit_quant_type": "nf4",
260
+ "bnb_4bit_use_double_quant": true,
261
+ "bnb_4bit_quant_storage": null,
262
+ "max_new_tokens": 64,
263
+ "temperature": 0.0,
264
+ "top_k": null,
265
+ "top_p": null,
266
+ "repetition_penalty": null,
267
+ "num_beams": 1,
268
+ "stream": false,
269
+ "stop_words": [],
270
+ "logprobs": false,
271
+ "top_logprobs": null,
272
+ "ckpt_dir": null,
273
+ "lora_modules": [],
274
+ "tuner_backend": "peft",
275
+ "train_type": "full",
276
+ "adapters": [],
277
+ "external_plugins": [],
278
+ "model_kwargs": {
279
+ "device_map": null
280
+ },
281
+ "load_args": false,
282
+ "load_data_args": false,
283
+ "packing": true,
284
+ "packing_cache": null,
285
+ "custom_register_path": [],
286
+ "use_hf": true,
287
+ "ignore_args_error": false,
288
+ "use_swift_lora": false,
289
+ "freeze_parameters": [],
290
+ "freeze_parameters_regex": null,
291
+ "freeze_parameters_ratio": 0.0,
292
+ "trainable_parameters": [],
293
+ "trainable_parameters_regex": null,
294
+ "freeze_llm": false,
295
+ "freeze_vit": true,
296
+ "freeze_aligner": true,
297
+ "target_modules": [
298
+ "all-linear"
299
+ ],
300
+ "target_regex": null,
301
+ "modules_to_save": [],
302
+ "lora_rank": 8,
303
+ "lora_alpha": 32,
304
+ "lora_dropout": 0.05,
305
+ "lora_bias": "none",
306
+ "lora_dtype": null,
307
+ "lorap_lr_ratio": null,
308
+ "use_rslora": false,
309
+ "use_dora": false,
310
+ "lora_ga_batch_size": 2,
311
+ "lora_ga_iters": 2,
312
+ "lora_ga_max_length": 1024,
313
+ "lora_ga_direction": "ArB2r",
314
+ "lora_ga_scale": "stable",
315
+ "lora_ga_stable_gamma": 16,
316
+ "init_weights": true,
317
+ "fourier_n_frequency": 2000,
318
+ "fourier_scaling": 300.0,
319
+ "boft_block_size": 4,
320
+ "boft_block_num": 0,
321
+ "boft_n_butterfly_factor": 1,
322
+ "boft_dropout": 0.0,
323
+ "vera_rank": 256,
324
+ "vera_projection_prng_key": 0,
325
+ "vera_dropout": 0.0,
326
+ "vera_d_initial": 0.1,
327
+ "adapter_act": "gelu",
328
+ "adapter_length": 128,
329
+ "use_galore": false,
330
+ "galore_target_modules": null,
331
+ "galore_rank": 128,
332
+ "galore_update_proj_gap": 50,
333
+ "galore_scale": 1.0,
334
+ "galore_proj_type": "std",
335
+ "galore_optim_per_parameter": false,
336
+ "galore_with_embedding": false,
337
+ "galore_quantization": false,
338
+ "galore_proj_quant": false,
339
+ "galore_proj_bits": 4,
340
+ "galore_proj_group_size": 256,
341
+ "galore_cos_threshold": 0.4,
342
+ "galore_gamma_proj": 2,
343
+ "galore_queue_size": 5,
344
+ "adalora_target_r": 8,
345
+ "adalora_init_r": 12,
346
+ "adalora_tinit": 0,
347
+ "adalora_tfinal": 0,
348
+ "adalora_deltaT": 1,
349
+ "adalora_beta1": 0.85,
350
+ "adalora_beta2": 0.85,
351
+ "adalora_orth_reg_weight": 0.5,
352
+ "llamapro_num_new_blocks": 4,
353
+ "llamapro_num_groups": null,
354
+ "lisa_activated_layers": 0,
355
+ "lisa_step_interval": 20,
356
+ "reft_layer_key": null,
357
+ "reft_layers": null,
358
+ "reft_rank": 4,
359
+ "reft_intervention_type": "LoreftIntervention",
360
+ "reft_args": null,
361
+ "swanlab_token": null,
362
+ "swanlab_project": null,
363
+ "swanlab_workspace": null,
364
+ "swanlab_exp_name": null,
365
+ "swanlab_lark_webhook_url": null,
366
+ "swanlab_lark_secret": null,
367
+ "swanlab_mode": "cloud",
368
+ "add_version": true,
369
+ "resume_only_model": false,
370
+ "create_checkpoint_symlink": false,
371
+ "lazy_tokenize": false,
372
+ "loss_type": null,
373
+ "metric": null,
374
+ "zero_hpz_partition_size": null,
375
+ "rank": 0,
376
+ "global_world_size": 8,
377
+ "local_world_size": 4,
378
+ "model_suffix": "DeepSeek-R1-Distill-Qwen-32B",
379
+ "model_info": "ModelInfo(model_type='deepseek_r1_distill', model_dir='/home/Competition2025/P09/shareP09/models/DeepSeek-R1-Distill-Qwen-32B', torch_dtype=torch.bfloat16, max_model_len=131072, quant_method=None, quant_bits=None, rope_scaling=None, config=None, task_type='causal_lm', num_labels=None)",
380
+ "model_meta": "ModelMeta(model_type='deepseek_r1_distill', model_groups=[ModelGroup(models=[Model(ms_model_id='deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B', hf_model_id='deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='deepseek-ai/DeepSeek-R1-Distill-Qwen-7B', hf_model_id='deepseek-ai/DeepSeek-R1-Distill-Qwen-7B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='deepseek-ai/DeepSeek-R1-Distill-Qwen-14B', hf_model_id='deepseek-ai/DeepSeek-R1-Distill-Qwen-14B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='deepseek-ai/DeepSeek-R1-Distill-Qwen-32B', hf_model_id='deepseek-ai/DeepSeek-R1-Distill-Qwen-32B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='iic/QwenLong-L1-32B', hf_model_id='Tongyi-Zhiwen/QwenLong-L1-32B', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=['transformers>=4.37'], tags=[]), ModelGroup(models=[Model(ms_model_id='deepseek-ai/DeepSeek-R1-Distill-Llama-8B', hf_model_id='deepseek-ai/DeepSeek-R1-Distill-Llama-8B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='deepseek-ai/DeepSeek-R1-Distill-Llama-70B', hf_model_id='deepseek-ai/DeepSeek-R1-Distill-Llama-70B', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='deepseek-ai/DeepSeek-R1-0528-Qwen3-8B', hf_model_id='deepseek-ai/DeepSeek-R1-0528-Qwen3-8B', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='deepseek_r1', get_function=<function get_model_tokenizer_with_flash_attn at 0x1499b3da63b0>, model_arch='llama', architectures=['Qwen2ForCausalLM', 'LlamaForCausalLM', 'Qwen3ForCausalLM'], additional_saved_files=[], torch_dtype=None, is_multimodal=False, is_reward=False, task_type=None, ignore_patterns=None, requires=[], tags=[])",
381
+ "model_dir": "/home/Competition2025/P09/shareP09/models/DeepSeek-R1-Distill-Qwen-32B",
382
+ "hub": "<class 'swift.hub.hub.HFHub'>",
383
+ "evaluation_strategy": "steps",
384
+ "training_args": "Seq2SeqTrainingArguments(output_dir='/home/Competition2025/P09/P09U016/llm_sft_dpo_grpo/outputs/sft_cleand_open-r1_codeforces-cots/v0-20250808-190458', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=<IntervalStrategy.STEPS: 'steps'>, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=1, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=1e-05, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=1.0, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/home/Competition2025/P09/P09U016/llm_sft_dpo_grpo/outputs/sft_cleand_open-r1_codeforces-cots/v0-20250808-190458/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=1000, save_total_limit=2, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, use_ipex=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=1000, dataloader_num_workers=2, dataloader_prefetch_factor=10, past_index=-1, run_name='sft_sft_cleand_open-r1_codeforces-cots-n2-gpu4-pp8-gc1-batch1-zero3', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), deepspeed={'fp16': {'enabled': 'auto'}, 'bf16': {'enabled': 'auto'}, 'zero_optimization': {'stage': 3, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'offload_param': {'device': 'none', 'pin_memory': True}, 'overlap_comm': False, 'contiguous_gradients': True, 'sub_group_size': 1000000000.0, 'reduce_bucket_size': 'auto', 'zero_quantized_weights': False, 'zero_quantized_gradients': False, 'stage3_prefetch_bucket_size': 'auto', 'stage3_param_persistence_threshold': 'auto', 'stage3_max_live_parameters': 1000000000.0, 'stage3_max_reuse_distance': 1000000000.0, 'stage3_gather_16bit_weights_on_model_save': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': 2000, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False, 'pipeline_parallel': {'enabled': True, 'pp_size': 8}, 'activation_checkpointing': {'partition_activations': True, 'cpu_checkpointing': False, 'contiguous_memory_optimization': True, 'number_checkpoints': None, 'synchronize_checkpoint_boundary': False, 'profile': False}}, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH: 'adamw_torch'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['wandb'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=None, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=18000000, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, include_tokens_per_second=None, include_num_input_tokens_seen=None, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, eval_use_gather_object=False, average_tokens_across_devices=None, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=None, vit_gradient_checkpointing=True, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, aligner_lr=None, vit_lr=None, optimizer=None, use_logits_to_keep=None, channels=None, ds3_gather_for_generation=True, metric_warmup_step=0, fsdp_num=1, acc_steps=1, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, sft_alpha=0, train_type='full', local_repo_path=None, galore_config=None)"
385
+ }
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "eos_token_id": 151643,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 5120,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 27648,
12
+ "max_position_embeddings": 131072,
13
+ "max_window_layers": 64,
14
+ "model_type": "qwen2",
15
+ "num_attention_heads": 40,
16
+ "num_hidden_layers": 64,
17
+ "num_key_value_heads": 8,
18
+ "pad_token_id": 151643,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_scaling": null,
21
+ "rope_theta": 1000000.0,
22
+ "sliding_window": 131072,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.52.4",
26
+ "use_cache": false,
27
+ "use_sliding_window": false,
28
+ "vocab_size": 152064
29
+ }
model-00001-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31eda33bbe7dc151d6c977e963a8c750d92b4b24279d11f2572e9a3449fd0d39
3
+ size 4891730992
model-00002-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ee3e3482c98bbdafa40bfe07e879de0d114552081e5f8332285033832fbcf72
3
+ size 4876059352
model-00003-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dab350056e5b0f88580a8e84ce9f0452caa38150125e90d30a88e554a514ec1
3
+ size 4876059384
model-00004-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee6b971718397e40bdfd451f1158025c9fe9bdcf6512f748419269452a10979a
3
+ size 4876059416
model-00005-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afb73ba47cc099e11fe614bbe2df66b0111987c699f4b6391dc7f97af75270f4
3
+ size 4876059416
model-00006-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dec1ffcd2c851084da7960881b4c0bfcb1faf588b514a609a6de14c471df8493
3
+ size 4876059416
model-00007-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c797dc6bf3a523f7328ab1a465a44231637e09141c63f0664757177ca9e08bfa
3
+ size 4876059416
model-00008-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d8157bfb6de3ebf6739340d0c300f0b71ddf01244289214304f46f64a087021
3
+ size 4876059416
model-00009-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbb2cdc04beb50c8be5816317f75b1e7a739591bb10b6b1a55aba6aa1bd80591
3
+ size 4876059416
model-00010-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71c0a157eed9610aabd1cd3d0ceff9c7743c370bd9168468e4d019c93d7aac0e
3
+ size 4876059416
model-00011-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6b6079d0a9ff53f8e668857882bb5812fc970eda5c31ed42c38163811be3795
3
+ size 4876059416
model-00012-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bf1dacf72a7663eae65bd2a35ff5da4be6302b4a92d64974f8a895ee91a72fb
3
+ size 4876059416
model-00013-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d265c9a0e72d0460a7644134ba6eb1acff7839db6472501bc683379c1fcc8c3
3
+ size 4876059416
model-00014-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3bfc62a82ab9b7bd0568a191b314331399e7252e1f9bc393bc7f7f69f06caaa
3
+ size 2123397800
model.safetensors.index.json ADDED
@@ -0,0 +1,778 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 65527752704
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00014-of-00014.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00014.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
13
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
16
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
17
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
18
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
19
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
20
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors",
21
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
22
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
23
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
24
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
25
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
26
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
27
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
28
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
29
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
30
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
31
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
32
+ "model.layers.10.input_layernorm.weight": "model-00003-of-00014.safetensors",
33
+ "model.layers.10.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
34
+ "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
35
+ "model.layers.10.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
36
+ "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
37
+ "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
38
+ "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
39
+ "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
40
+ "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
41
+ "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
42
+ "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
43
+ "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
44
+ "model.layers.11.input_layernorm.weight": "model-00003-of-00014.safetensors",
45
+ "model.layers.11.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
46
+ "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
47
+ "model.layers.11.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
48
+ "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
49
+ "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
50
+ "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
51
+ "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
52
+ "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
53
+ "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
54
+ "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
55
+ "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
56
+ "model.layers.12.input_layernorm.weight": "model-00003-of-00014.safetensors",
57
+ "model.layers.12.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
58
+ "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
59
+ "model.layers.12.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
60
+ "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
61
+ "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
62
+ "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
63
+ "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
64
+ "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
65
+ "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
66
+ "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
67
+ "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
68
+ "model.layers.13.input_layernorm.weight": "model-00004-of-00014.safetensors",
69
+ "model.layers.13.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
70
+ "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
71
+ "model.layers.13.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
72
+ "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
73
+ "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
74
+ "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
75
+ "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
76
+ "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
77
+ "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
78
+ "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
79
+ "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
80
+ "model.layers.14.input_layernorm.weight": "model-00004-of-00014.safetensors",
81
+ "model.layers.14.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
82
+ "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
83
+ "model.layers.14.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
84
+ "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
85
+ "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
86
+ "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
87
+ "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
88
+ "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
89
+ "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
90
+ "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
91
+ "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
92
+ "model.layers.15.input_layernorm.weight": "model-00004-of-00014.safetensors",
93
+ "model.layers.15.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
94
+ "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
95
+ "model.layers.15.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
96
+ "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
97
+ "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
98
+ "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
99
+ "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
100
+ "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
101
+ "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
102
+ "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
103
+ "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
104
+ "model.layers.16.input_layernorm.weight": "model-00004-of-00014.safetensors",
105
+ "model.layers.16.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
106
+ "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
107
+ "model.layers.16.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
108
+ "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
109
+ "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
110
+ "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
111
+ "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
112
+ "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
113
+ "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
114
+ "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
115
+ "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
116
+ "model.layers.17.input_layernorm.weight": "model-00004-of-00014.safetensors",
117
+ "model.layers.17.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
118
+ "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
119
+ "model.layers.17.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
120
+ "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
121
+ "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
122
+ "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
123
+ "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
124
+ "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
125
+ "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
126
+ "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
127
+ "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
128
+ "model.layers.18.input_layernorm.weight": "model-00005-of-00014.safetensors",
129
+ "model.layers.18.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
130
+ "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
131
+ "model.layers.18.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
132
+ "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
133
+ "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
134
+ "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
135
+ "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
136
+ "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
137
+ "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
138
+ "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
139
+ "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
140
+ "model.layers.19.input_layernorm.weight": "model-00005-of-00014.safetensors",
141
+ "model.layers.19.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
142
+ "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
143
+ "model.layers.19.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
144
+ "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
145
+ "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
146
+ "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
147
+ "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
148
+ "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
149
+ "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
150
+ "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
151
+ "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
152
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00014.safetensors",
153
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
154
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
155
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
156
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
157
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
158
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
159
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
160
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
161
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
162
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
163
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
164
+ "model.layers.20.input_layernorm.weight": "model-00005-of-00014.safetensors",
165
+ "model.layers.20.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
166
+ "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
167
+ "model.layers.20.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
168
+ "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
169
+ "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
170
+ "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
171
+ "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
172
+ "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
173
+ "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
174
+ "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
175
+ "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
176
+ "model.layers.21.input_layernorm.weight": "model-00005-of-00014.safetensors",
177
+ "model.layers.21.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
178
+ "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
179
+ "model.layers.21.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
180
+ "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
181
+ "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
182
+ "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
183
+ "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
184
+ "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
185
+ "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
186
+ "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
187
+ "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
188
+ "model.layers.22.input_layernorm.weight": "model-00005-of-00014.safetensors",
189
+ "model.layers.22.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
190
+ "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
191
+ "model.layers.22.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
192
+ "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
193
+ "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
194
+ "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
195
+ "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
196
+ "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
197
+ "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
198
+ "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
199
+ "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
200
+ "model.layers.23.input_layernorm.weight": "model-00006-of-00014.safetensors",
201
+ "model.layers.23.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
202
+ "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
203
+ "model.layers.23.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
204
+ "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
205
+ "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
206
+ "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
207
+ "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
208
+ "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
209
+ "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
210
+ "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
211
+ "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
212
+ "model.layers.24.input_layernorm.weight": "model-00006-of-00014.safetensors",
213
+ "model.layers.24.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
214
+ "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
215
+ "model.layers.24.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
216
+ "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
217
+ "model.layers.24.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
218
+ "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
219
+ "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
220
+ "model.layers.24.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
221
+ "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
222
+ "model.layers.24.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
223
+ "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
224
+ "model.layers.25.input_layernorm.weight": "model-00006-of-00014.safetensors",
225
+ "model.layers.25.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
226
+ "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
227
+ "model.layers.25.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
228
+ "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
229
+ "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
230
+ "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
231
+ "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
232
+ "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
233
+ "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
234
+ "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
235
+ "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
236
+ "model.layers.26.input_layernorm.weight": "model-00006-of-00014.safetensors",
237
+ "model.layers.26.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
238
+ "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
239
+ "model.layers.26.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
240
+ "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
241
+ "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
242
+ "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
243
+ "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
244
+ "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
245
+ "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
246
+ "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
247
+ "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
248
+ "model.layers.27.input_layernorm.weight": "model-00006-of-00014.safetensors",
249
+ "model.layers.27.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
250
+ "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
251
+ "model.layers.27.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
252
+ "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
253
+ "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
254
+ "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
255
+ "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
256
+ "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
257
+ "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
258
+ "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
259
+ "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
260
+ "model.layers.28.input_layernorm.weight": "model-00007-of-00014.safetensors",
261
+ "model.layers.28.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
262
+ "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
263
+ "model.layers.28.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
264
+ "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
265
+ "model.layers.28.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
266
+ "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
267
+ "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
268
+ "model.layers.28.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
269
+ "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
270
+ "model.layers.28.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
271
+ "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
272
+ "model.layers.29.input_layernorm.weight": "model-00007-of-00014.safetensors",
273
+ "model.layers.29.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
274
+ "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
275
+ "model.layers.29.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
276
+ "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
277
+ "model.layers.29.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
278
+ "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
279
+ "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
280
+ "model.layers.29.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
281
+ "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
282
+ "model.layers.29.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
283
+ "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
284
+ "model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors",
285
+ "model.layers.3.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
286
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
287
+ "model.layers.3.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
288
+ "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
289
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
290
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
291
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
292
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
293
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
294
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
295
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
296
+ "model.layers.30.input_layernorm.weight": "model-00007-of-00014.safetensors",
297
+ "model.layers.30.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
298
+ "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
299
+ "model.layers.30.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
300
+ "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
301
+ "model.layers.30.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
302
+ "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
303
+ "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
304
+ "model.layers.30.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
305
+ "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
306
+ "model.layers.30.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
307
+ "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
308
+ "model.layers.31.input_layernorm.weight": "model-00007-of-00014.safetensors",
309
+ "model.layers.31.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
310
+ "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
311
+ "model.layers.31.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
312
+ "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
313
+ "model.layers.31.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
314
+ "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
315
+ "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
316
+ "model.layers.31.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
317
+ "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
318
+ "model.layers.31.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
319
+ "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
320
+ "model.layers.32.input_layernorm.weight": "model-00007-of-00014.safetensors",
321
+ "model.layers.32.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
322
+ "model.layers.32.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
323
+ "model.layers.32.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
324
+ "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
325
+ "model.layers.32.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
326
+ "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
327
+ "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
328
+ "model.layers.32.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
329
+ "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
330
+ "model.layers.32.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
331
+ "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
332
+ "model.layers.33.input_layernorm.weight": "model-00008-of-00014.safetensors",
333
+ "model.layers.33.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
334
+ "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
335
+ "model.layers.33.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
336
+ "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
337
+ "model.layers.33.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
338
+ "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
339
+ "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
340
+ "model.layers.33.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
341
+ "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
342
+ "model.layers.33.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
343
+ "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
344
+ "model.layers.34.input_layernorm.weight": "model-00008-of-00014.safetensors",
345
+ "model.layers.34.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
346
+ "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
347
+ "model.layers.34.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
348
+ "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
349
+ "model.layers.34.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
350
+ "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
351
+ "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
352
+ "model.layers.34.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
353
+ "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
354
+ "model.layers.34.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
355
+ "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
356
+ "model.layers.35.input_layernorm.weight": "model-00008-of-00014.safetensors",
357
+ "model.layers.35.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
358
+ "model.layers.35.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
359
+ "model.layers.35.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
360
+ "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
361
+ "model.layers.35.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
362
+ "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
363
+ "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
364
+ "model.layers.35.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
365
+ "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
366
+ "model.layers.35.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
367
+ "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
368
+ "model.layers.36.input_layernorm.weight": "model-00008-of-00014.safetensors",
369
+ "model.layers.36.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
370
+ "model.layers.36.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
371
+ "model.layers.36.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
372
+ "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
373
+ "model.layers.36.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
374
+ "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
375
+ "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
376
+ "model.layers.36.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
377
+ "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
378
+ "model.layers.36.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
379
+ "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
380
+ "model.layers.37.input_layernorm.weight": "model-00008-of-00014.safetensors",
381
+ "model.layers.37.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
382
+ "model.layers.37.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
383
+ "model.layers.37.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
384
+ "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
385
+ "model.layers.37.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
386
+ "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
387
+ "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
388
+ "model.layers.37.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
389
+ "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
390
+ "model.layers.37.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
391
+ "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
392
+ "model.layers.38.input_layernorm.weight": "model-00009-of-00014.safetensors",
393
+ "model.layers.38.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
394
+ "model.layers.38.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
395
+ "model.layers.38.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
396
+ "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
397
+ "model.layers.38.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
398
+ "model.layers.38.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
399
+ "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
400
+ "model.layers.38.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
401
+ "model.layers.38.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
402
+ "model.layers.38.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
403
+ "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
404
+ "model.layers.39.input_layernorm.weight": "model-00009-of-00014.safetensors",
405
+ "model.layers.39.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
406
+ "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
407
+ "model.layers.39.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
408
+ "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
409
+ "model.layers.39.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
410
+ "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
411
+ "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
412
+ "model.layers.39.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
413
+ "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
414
+ "model.layers.39.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
415
+ "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
416
+ "model.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors",
417
+ "model.layers.4.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
418
+ "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
419
+ "model.layers.4.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
420
+ "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
421
+ "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
422
+ "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
423
+ "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
424
+ "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
425
+ "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
426
+ "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
427
+ "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
428
+ "model.layers.40.input_layernorm.weight": "model-00009-of-00014.safetensors",
429
+ "model.layers.40.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
430
+ "model.layers.40.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
431
+ "model.layers.40.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
432
+ "model.layers.40.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
433
+ "model.layers.40.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
434
+ "model.layers.40.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
435
+ "model.layers.40.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
436
+ "model.layers.40.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
437
+ "model.layers.40.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
438
+ "model.layers.40.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
439
+ "model.layers.40.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
440
+ "model.layers.41.input_layernorm.weight": "model-00009-of-00014.safetensors",
441
+ "model.layers.41.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
442
+ "model.layers.41.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
443
+ "model.layers.41.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
444
+ "model.layers.41.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
445
+ "model.layers.41.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
446
+ "model.layers.41.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
447
+ "model.layers.41.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
448
+ "model.layers.41.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
449
+ "model.layers.41.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
450
+ "model.layers.41.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
451
+ "model.layers.41.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
452
+ "model.layers.42.input_layernorm.weight": "model-00009-of-00014.safetensors",
453
+ "model.layers.42.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
454
+ "model.layers.42.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
455
+ "model.layers.42.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
456
+ "model.layers.42.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
457
+ "model.layers.42.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
458
+ "model.layers.42.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
459
+ "model.layers.42.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
460
+ "model.layers.42.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
461
+ "model.layers.42.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
462
+ "model.layers.42.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
463
+ "model.layers.42.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
464
+ "model.layers.43.input_layernorm.weight": "model-00010-of-00014.safetensors",
465
+ "model.layers.43.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
466
+ "model.layers.43.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
467
+ "model.layers.43.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
468
+ "model.layers.43.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
469
+ "model.layers.43.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
470
+ "model.layers.43.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
471
+ "model.layers.43.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
472
+ "model.layers.43.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
473
+ "model.layers.43.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
474
+ "model.layers.43.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
475
+ "model.layers.43.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
476
+ "model.layers.44.input_layernorm.weight": "model-00010-of-00014.safetensors",
477
+ "model.layers.44.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
478
+ "model.layers.44.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
479
+ "model.layers.44.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
480
+ "model.layers.44.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
481
+ "model.layers.44.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
482
+ "model.layers.44.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
483
+ "model.layers.44.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
484
+ "model.layers.44.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
485
+ "model.layers.44.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
486
+ "model.layers.44.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
487
+ "model.layers.44.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
488
+ "model.layers.45.input_layernorm.weight": "model-00010-of-00014.safetensors",
489
+ "model.layers.45.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
490
+ "model.layers.45.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
491
+ "model.layers.45.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
492
+ "model.layers.45.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
493
+ "model.layers.45.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
494
+ "model.layers.45.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
495
+ "model.layers.45.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
496
+ "model.layers.45.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
497
+ "model.layers.45.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
498
+ "model.layers.45.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
499
+ "model.layers.45.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
500
+ "model.layers.46.input_layernorm.weight": "model-00010-of-00014.safetensors",
501
+ "model.layers.46.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
502
+ "model.layers.46.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
503
+ "model.layers.46.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
504
+ "model.layers.46.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
505
+ "model.layers.46.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
506
+ "model.layers.46.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
507
+ "model.layers.46.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
508
+ "model.layers.46.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
509
+ "model.layers.46.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
510
+ "model.layers.46.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
511
+ "model.layers.46.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
512
+ "model.layers.47.input_layernorm.weight": "model-00010-of-00014.safetensors",
513
+ "model.layers.47.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
514
+ "model.layers.47.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
515
+ "model.layers.47.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
516
+ "model.layers.47.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
517
+ "model.layers.47.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
518
+ "model.layers.47.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
519
+ "model.layers.47.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
520
+ "model.layers.47.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
521
+ "model.layers.47.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
522
+ "model.layers.47.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
523
+ "model.layers.47.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
524
+ "model.layers.48.input_layernorm.weight": "model-00011-of-00014.safetensors",
525
+ "model.layers.48.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
526
+ "model.layers.48.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
527
+ "model.layers.48.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
528
+ "model.layers.48.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
529
+ "model.layers.48.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
530
+ "model.layers.48.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
531
+ "model.layers.48.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
532
+ "model.layers.48.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
533
+ "model.layers.48.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
534
+ "model.layers.48.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
535
+ "model.layers.48.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
536
+ "model.layers.49.input_layernorm.weight": "model-00011-of-00014.safetensors",
537
+ "model.layers.49.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
538
+ "model.layers.49.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
539
+ "model.layers.49.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
540
+ "model.layers.49.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
541
+ "model.layers.49.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
542
+ "model.layers.49.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
543
+ "model.layers.49.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
544
+ "model.layers.49.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
545
+ "model.layers.49.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
546
+ "model.layers.49.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
547
+ "model.layers.49.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
548
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00014.safetensors",
549
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
550
+ "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
551
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
552
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
553
+ "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
554
+ "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
555
+ "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
556
+ "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
557
+ "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
558
+ "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
559
+ "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
560
+ "model.layers.50.input_layernorm.weight": "model-00011-of-00014.safetensors",
561
+ "model.layers.50.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
562
+ "model.layers.50.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
563
+ "model.layers.50.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
564
+ "model.layers.50.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
565
+ "model.layers.50.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
566
+ "model.layers.50.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
567
+ "model.layers.50.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
568
+ "model.layers.50.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
569
+ "model.layers.50.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
570
+ "model.layers.50.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
571
+ "model.layers.50.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
572
+ "model.layers.51.input_layernorm.weight": "model-00011-of-00014.safetensors",
573
+ "model.layers.51.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
574
+ "model.layers.51.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
575
+ "model.layers.51.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
576
+ "model.layers.51.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
577
+ "model.layers.51.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
578
+ "model.layers.51.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
579
+ "model.layers.51.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
580
+ "model.layers.51.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
581
+ "model.layers.51.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
582
+ "model.layers.51.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
583
+ "model.layers.51.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
584
+ "model.layers.52.input_layernorm.weight": "model-00011-of-00014.safetensors",
585
+ "model.layers.52.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
586
+ "model.layers.52.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
587
+ "model.layers.52.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
588
+ "model.layers.52.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
589
+ "model.layers.52.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
590
+ "model.layers.52.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
591
+ "model.layers.52.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
592
+ "model.layers.52.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
593
+ "model.layers.52.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
594
+ "model.layers.52.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
595
+ "model.layers.52.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
596
+ "model.layers.53.input_layernorm.weight": "model-00012-of-00014.safetensors",
597
+ "model.layers.53.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
598
+ "model.layers.53.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
599
+ "model.layers.53.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
600
+ "model.layers.53.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
601
+ "model.layers.53.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
602
+ "model.layers.53.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
603
+ "model.layers.53.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
604
+ "model.layers.53.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
605
+ "model.layers.53.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
606
+ "model.layers.53.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
607
+ "model.layers.53.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
608
+ "model.layers.54.input_layernorm.weight": "model-00012-of-00014.safetensors",
609
+ "model.layers.54.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
610
+ "model.layers.54.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
611
+ "model.layers.54.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
612
+ "model.layers.54.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
613
+ "model.layers.54.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
614
+ "model.layers.54.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
615
+ "model.layers.54.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
616
+ "model.layers.54.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
617
+ "model.layers.54.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
618
+ "model.layers.54.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
619
+ "model.layers.54.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
620
+ "model.layers.55.input_layernorm.weight": "model-00012-of-00014.safetensors",
621
+ "model.layers.55.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
622
+ "model.layers.55.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
623
+ "model.layers.55.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
624
+ "model.layers.55.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
625
+ "model.layers.55.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
626
+ "model.layers.55.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
627
+ "model.layers.55.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
628
+ "model.layers.55.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
629
+ "model.layers.55.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
630
+ "model.layers.55.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
631
+ "model.layers.55.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
632
+ "model.layers.56.input_layernorm.weight": "model-00012-of-00014.safetensors",
633
+ "model.layers.56.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
634
+ "model.layers.56.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
635
+ "model.layers.56.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
636
+ "model.layers.56.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
637
+ "model.layers.56.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
638
+ "model.layers.56.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
639
+ "model.layers.56.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
640
+ "model.layers.56.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
641
+ "model.layers.56.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
642
+ "model.layers.56.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
643
+ "model.layers.56.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
644
+ "model.layers.57.input_layernorm.weight": "model-00012-of-00014.safetensors",
645
+ "model.layers.57.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
646
+ "model.layers.57.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
647
+ "model.layers.57.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
648
+ "model.layers.57.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
649
+ "model.layers.57.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
650
+ "model.layers.57.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
651
+ "model.layers.57.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
652
+ "model.layers.57.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
653
+ "model.layers.57.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
654
+ "model.layers.57.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
655
+ "model.layers.57.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
656
+ "model.layers.58.input_layernorm.weight": "model-00013-of-00014.safetensors",
657
+ "model.layers.58.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
658
+ "model.layers.58.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
659
+ "model.layers.58.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
660
+ "model.layers.58.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
661
+ "model.layers.58.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
662
+ "model.layers.58.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
663
+ "model.layers.58.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
664
+ "model.layers.58.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
665
+ "model.layers.58.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
666
+ "model.layers.58.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
667
+ "model.layers.58.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
668
+ "model.layers.59.input_layernorm.weight": "model-00013-of-00014.safetensors",
669
+ "model.layers.59.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
670
+ "model.layers.59.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
671
+ "model.layers.59.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
672
+ "model.layers.59.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
673
+ "model.layers.59.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
674
+ "model.layers.59.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
675
+ "model.layers.59.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
676
+ "model.layers.59.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
677
+ "model.layers.59.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
678
+ "model.layers.59.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
679
+ "model.layers.59.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
680
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00014.safetensors",
681
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
682
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
683
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
684
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
685
+ "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
686
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
687
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
688
+ "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
689
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
690
+ "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
691
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
692
+ "model.layers.60.input_layernorm.weight": "model-00013-of-00014.safetensors",
693
+ "model.layers.60.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
694
+ "model.layers.60.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
695
+ "model.layers.60.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
696
+ "model.layers.60.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
697
+ "model.layers.60.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
698
+ "model.layers.60.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
699
+ "model.layers.60.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
700
+ "model.layers.60.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
701
+ "model.layers.60.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
702
+ "model.layers.60.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
703
+ "model.layers.60.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
704
+ "model.layers.61.input_layernorm.weight": "model-00013-of-00014.safetensors",
705
+ "model.layers.61.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
706
+ "model.layers.61.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
707
+ "model.layers.61.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
708
+ "model.layers.61.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
709
+ "model.layers.61.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
710
+ "model.layers.61.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
711
+ "model.layers.61.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
712
+ "model.layers.61.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
713
+ "model.layers.61.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
714
+ "model.layers.61.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
715
+ "model.layers.61.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
716
+ "model.layers.62.input_layernorm.weight": "model-00013-of-00014.safetensors",
717
+ "model.layers.62.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
718
+ "model.layers.62.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
719
+ "model.layers.62.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
720
+ "model.layers.62.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
721
+ "model.layers.62.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
722
+ "model.layers.62.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
723
+ "model.layers.62.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
724
+ "model.layers.62.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
725
+ "model.layers.62.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
726
+ "model.layers.62.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
727
+ "model.layers.62.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
728
+ "model.layers.63.input_layernorm.weight": "model-00014-of-00014.safetensors",
729
+ "model.layers.63.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
730
+ "model.layers.63.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
731
+ "model.layers.63.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
732
+ "model.layers.63.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
733
+ "model.layers.63.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
734
+ "model.layers.63.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
735
+ "model.layers.63.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
736
+ "model.layers.63.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
737
+ "model.layers.63.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
738
+ "model.layers.63.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
739
+ "model.layers.63.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
740
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00014.safetensors",
741
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
742
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
743
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
744
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
745
+ "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
746
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
747
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
748
+ "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
749
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
750
+ "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
751
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
752
+ "model.layers.8.input_layernorm.weight": "model-00003-of-00014.safetensors",
753
+ "model.layers.8.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
754
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
755
+ "model.layers.8.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
756
+ "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
757
+ "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
758
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
759
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
760
+ "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
761
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
762
+ "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
763
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
764
+ "model.layers.9.input_layernorm.weight": "model-00003-of-00014.safetensors",
765
+ "model.layers.9.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
766
+ "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
767
+ "model.layers.9.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
768
+ "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
769
+ "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
770
+ "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
771
+ "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
772
+ "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
773
+ "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
774
+ "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
775
+ "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
776
+ "model.norm.weight": "model-00014-of-00014.safetensors"
777
+ }
778
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
3
+ size 11422778
tokenizer_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<｜begin▁of▁sentence｜>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "<｜end▁of▁sentence｜>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "legacy": true,
22
+ "model_max_length": 16384,
23
+ "pad_token": {
24
+ "__type": "AddedToken",
25
+ "content": "<｜end▁of▁sentence｜>",
26
+ "lstrip": false,
27
+ "normalized": true,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ "sp_model_kwargs": {},
32
+ "unk_token": null,
33
+ "tokenizer_class": "LlamaTokenizerFast",
34
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\\n'}}{% endif %}"
35
+ }