Hugging Face's logo

Vchitect
/
ShotVL-3B

Image-Text-to-Text
Transformers
Safetensors
qwen2_5_vl
image-to-text
vision-language
cinematography
shotbench
conversational
text-generation-inference
Model card Files
xet
Community
1
Alexislhb commited on
Commit
a66656c
·
verified ·
1 Parent(s): ebb70ea

Upload folder using huggingface_hub

Browse files
Files changed (18) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +24 -0
  3. args.json +331 -0
  4. chat_template.json +3 -0
  5. config.json +66 -0
  6. generation_config.json +12 -0
  7. merges.txt +0 -0
  8. model-00001-of-00002.safetensors +3 -0
  9. model-00002-of-00002.safetensors +3 -0
  10. model.safetensors.index.json +831 -0
  11. preprocessor_config.json +19 -0
  12. special_tokens_map.json +31 -0
  13. tokenizer.json +3 -0
  14. tokenizer_config.json +209 -0
  15. trainer_state.json +0 -0
  16. training_args.bin +3 -0
  17. vocab.json +0 -0
  18. zero_to_fp32.py +604 -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
added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
args.json ADDED
@@ -0,0 +1,331 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model": "/mnt/petrelfs/liuhongbo/Qwen2.5-VL-3B-Instruct",
3
+ "model_type": "qwen2_5_vl",
4
+ "model_revision": null,
5
+ "task_type": "causal_lm",
6
+ "torch_dtype": "bfloat16",
7
+ "attn_impl": "flash_attn",
8
+ "num_labels": null,
9
+ "problem_type": null,
10
+ "rope_scaling": null,
11
+ "device_map": null,
12
+ "max_memory": {},
13
+ "local_repo_path": null,
14
+ "template": "qwen2_5_vl",
15
+ "system": "You are a helpful assistant.",
16
+ "max_length": 3072,
17
+ "truncation_strategy": "delete",
18
+ "max_pixels": null,
19
+ "agent_template": null,
20
+ "norm_bbox": null,
21
+ "response_prefix": null,
22
+ "padding_side": "right",
23
+ "loss_scale": "default",
24
+ "sequence_parallel_size": 1,
25
+ "use_chat_template": true,
26
+ "template_backend": "swift",
27
+ "dataset": [
28
+ "/mnt/petrelfs/liuhongbo/movie_bench/shotdeck_data/sft/img_train_v5_without_reasoning.json"
29
+ ],
30
+ "val_dataset": [],
31
+ "split_dataset_ratio": 0.01,
32
+ "data_seed": 42,
33
+ "dataset_num_proc": 1,
34
+ "dataset_shuffle": true,
35
+ "val_dataset_shuffle": false,
36
+ "streaming": false,
37
+ "interleave_prob": null,
38
+ "stopping_strategy": "first_exhausted",
39
+ "shuffle_buffer_size": 1000,
40
+ "enable_cache": false,
41
+ "download_mode": "reuse_dataset_if_exists",
42
+ "columns": {},
43
+ "strict": false,
44
+ "remove_unused_columns": true,
45
+ "model_name": [
46
+ null,
47
+ null
48
+ ],
49
+ "model_author": [
50
+ null,
51
+ null
52
+ ],
53
+ "custom_dataset_info": [],
54
+ "quant_method": null,
55
+ "quant_bits": null,
56
+ "hqq_axis": null,
57
+ "bnb_4bit_compute_dtype": "bfloat16",
58
+ "bnb_4bit_quant_type": "nf4",
59
+ "bnb_4bit_use_double_quant": true,
60
+ "bnb_4bit_quant_storage": null,
61
+ "max_new_tokens": 64,
62
+ "temperature": 0.0,
63
+ "top_k": null,
64
+ "top_p": null,
65
+ "repetition_penalty": null,
66
+ "num_beams": 1,
67
+ "stream": false,
68
+ "stop_words": [],
69
+ "logprobs": false,
70
+ "top_logprobs": null,
71
+ "ckpt_dir": null,
72
+ "load_dataset_config": null,
73
+ "lora_modules": [],
74
+ "tuner_backend": "peft",
75
+ "train_type": "full",
76
+ "adapters": [],
77
+ "external_plugins": [],
78
+ "seed": 42,
79
+ "model_kwargs": {},
80
+ "load_args": false,
81
+ "load_data_args": false,
82
+ "use_hf": false,
83
+ "hub_token": null,
84
+ "custom_register_path": [],
85
+ "ignore_args_error": false,
86
+ "use_swift_lora": false,
87
+ "output_dir": "/mnt/petrelfs/liuhongbo/ms-swift/output/main/sft_without_reasoning/v0-20250505-134456",
88
+ "overwrite_output_dir": false,
89
+ "do_train": false,
90
+ "do_eval": false,
91
+ "do_predict": false,
92
+ "eval_strategy": "steps",
93
+ "prediction_loss_only": false,
94
+ "per_device_train_batch_size": 1,
95
+ "per_device_eval_batch_size": 1,
96
+ "per_gpu_train_batch_size": null,
97
+ "per_gpu_eval_batch_size": null,
98
+ "gradient_accumulation_steps": 16,
99
+ "eval_accumulation_steps": null,
100
+ "eval_delay": 0,
101
+ "torch_empty_cache_steps": null,
102
+ "learning_rate": 1e-05,
103
+ "weight_decay": 0.1,
104
+ "adam_beta1": 0.9,
105
+ "adam_beta2": 0.95,
106
+ "adam_epsilon": 1e-08,
107
+ "max_grad_norm": 1.0,
108
+ "num_train_epochs": 1.0,
109
+ "max_steps": -1,
110
+ "lr_scheduler_type": "cosine",
111
+ "lr_scheduler_kwargs": null,
112
+ "warmup_ratio": 0.05,
113
+ "warmup_steps": 0,
114
+ "log_level": "passive",
115
+ "log_level_replica": "warning",
116
+ "log_on_each_node": true,
117
+ "logging_dir": "/mnt/petrelfs/liuhongbo/ms-swift/output/main/sft_without_reasoning/v0-20250505-134456/runs",
118
+ "logging_strategy": "steps",
119
+ "logging_first_step": true,
120
+ "logging_steps": 5,
121
+ "logging_nan_inf_filter": true,
122
+ "save_strategy": "steps",
123
+ "save_steps": 100.0,
124
+ "save_total_limit": 3,
125
+ "save_safetensors": true,
126
+ "save_on_each_node": false,
127
+ "save_only_model": false,
128
+ "restore_callback_states_from_checkpoint": false,
129
+ "no_cuda": false,
130
+ "use_cpu": false,
131
+ "use_mps_device": false,
132
+ "jit_mode_eval": false,
133
+ "use_ipex": false,
134
+ "bf16": true,
135
+ "fp16": false,
136
+ "fp16_opt_level": "O1",
137
+ "half_precision_backend": "auto",
138
+ "bf16_full_eval": false,
139
+ "fp16_full_eval": false,
140
+ "tf32": null,
141
+ "local_rank": 0,
142
+ "ddp_backend": null,
143
+ "tpu_num_cores": null,
144
+ "tpu_metrics_debug": false,
145
+ "debug": null,
146
+ "dataloader_drop_last": false,
147
+ "eval_steps": 100.0,
148
+ "dataloader_num_workers": 4,
149
+ "dataloader_prefetch_factor": null,
150
+ "past_index": -1,
151
+ "run_name": null,
152
+ "disable_tqdm": null,
153
+ "label_names": null,
154
+ "load_best_model_at_end": false,
155
+ "metric_for_best_model": "loss",
156
+ "greater_is_better": false,
157
+ "ignore_data_skip": false,
158
+ "fsdp": "",
159
+ "fsdp_min_num_params": 0,
160
+ "fsdp_config": null,
161
+ "tp_size": 0,
162
+ "fsdp_transformer_layer_cls_to_wrap": null,
163
+ "accelerator_config": {
164
+ "dispatch_batches": false
165
+ },
166
+ "deepspeed": null,
167
+ "label_smoothing_factor": 0.0,
168
+ "optim": "adamw_torch",
169
+ "optim_args": null,
170
+ "adafactor": false,
171
+ "group_by_length": false,
172
+ "length_column_name": "length",
173
+ "report_to": [
174
+ "wandb"
175
+ ],
176
+ "ddp_find_unused_parameters": null,
177
+ "ddp_bucket_cap_mb": null,
178
+ "ddp_broadcast_buffers": null,
179
+ "dataloader_pin_memory": true,
180
+ "dataloader_persistent_workers": false,
181
+ "skip_memory_metrics": true,
182
+ "use_legacy_prediction_loop": false,
183
+ "push_to_hub": false,
184
+ "resume_from_checkpoint": null,
185
+ "hub_model_id": null,
186
+ "hub_strategy": "every_save",
187
+ "hub_private_repo": null,
188
+ "hub_always_push": false,
189
+ "gradient_checkpointing": true,
190
+ "gradient_checkpointing_kwargs": null,
191
+ "include_inputs_for_metrics": false,
192
+ "include_for_metrics": [],
193
+ "eval_do_concat_batches": true,
194
+ "fp16_backend": "auto",
195
+ "evaluation_strategy": "steps",
196
+ "push_to_hub_model_id": null,
197
+ "push_to_hub_organization": null,
198
+ "push_to_hub_token": null,
199
+ "mp_parameters": "",
200
+ "auto_find_batch_size": false,
201
+ "full_determinism": false,
202
+ "torchdynamo": null,
203
+ "ray_scope": "last",
204
+ "ddp_timeout": 1800,
205
+ "torch_compile": false,
206
+ "torch_compile_backend": null,
207
+ "torch_compile_mode": null,
208
+ "dispatch_batches": null,
209
+ "split_batches": null,
210
+ "include_tokens_per_second": false,
211
+ "include_num_input_tokens_seen": false,
212
+ "neftune_noise_alpha": null,
213
+ "optim_target_modules": null,
214
+ "batch_eval_metrics": false,
215
+ "eval_on_start": false,
216
+ "use_liger_kernel": false,
217
+ "eval_use_gather_object": false,
218
+ "average_tokens_across_devices": false,
219
+ "sortish_sampler": false,
220
+ "predict_with_generate": false,
221
+ "generation_max_length": null,
222
+ "generation_num_beams": null,
223
+ "generation_config": null,
224
+ "check_model": true,
225
+ "acc_strategy": "token",
226
+ "train_dataloader_shuffle": true,
227
+ "metric_warmup_step": 0,
228
+ "fsdp_num": 1,
229
+ "acc_steps": 1,
230
+ "eval_use_evalscope": false,
231
+ "eval_datasets": [],
232
+ "eval_limit": null,
233
+ "eval_datasets_args": null,
234
+ "eval_generation_config": null,
235
+ "freeze_parameters": [
236
+ "visual",
237
+ "visual.merger"
238
+ ],
239
+ "freeze_parameters_ratio": 0.0,
240
+ "trainable_parameters": [],
241
+ "freeze_llm": false,
242
+ "freeze_vit": true,
243
+ "freeze_aligner": true,
244
+ "target_modules": [
245
+ "all-linear"
246
+ ],
247
+ "target_regex": null,
248
+ "modules_to_save": [],
249
+ "lora_rank": 8,
250
+ "lora_alpha": 32,
251
+ "lora_dropout": 0.05,
252
+ "lora_bias": "none",
253
+ "lora_dtype": null,
254
+ "lorap_lr_ratio": null,
255
+ "use_rslora": false,
256
+ "use_dora": false,
257
+ "lora_ga_batch_size": 2,
258
+ "lora_ga_iters": 2,
259
+ "lora_ga_max_length": 1024,
260
+ "lora_ga_direction": "ArB2r",
261
+ "lora_ga_scale": "stable",
262
+ "lora_ga_stable_gamma": 16,
263
+ "init_weights": true,
264
+ "fourier_n_frequency": 2000,
265
+ "fourier_scaling": 300.0,
266
+ "boft_block_size": 4,
267
+ "boft_block_num": 0,
268
+ "boft_n_butterfly_factor": 1,
269
+ "boft_dropout": 0.0,
270
+ "vera_rank": 256,
271
+ "vera_projection_prng_key": 0,
272
+ "vera_dropout": 0.0,
273
+ "vera_d_initial": 0.1,
274
+ "adapter_act": "gelu",
275
+ "adapter_length": 128,
276
+ "use_galore": false,
277
+ "galore_target_modules": null,
278
+ "galore_rank": 128,
279
+ "galore_update_proj_gap": 50,
280
+ "galore_scale": 1.0,
281
+ "galore_proj_type": "std",
282
+ "galore_optim_per_parameter": false,
283
+ "galore_with_embedding": false,
284
+ "galore_quantization": false,
285
+ "galore_proj_quant": false,
286
+ "galore_proj_bits": 4,
287
+ "galore_proj_group_size": 256,
288
+ "galore_cos_threshold": 0.4,
289
+ "galore_gamma_proj": 2,
290
+ "galore_queue_size": 5,
291
+ "adalora_target_r": 8,
292
+ "adalora_init_r": 12,
293
+ "adalora_tinit": 0,
294
+ "adalora_tfinal": 0,
295
+ "adalora_deltaT": 1,
296
+ "adalora_beta1": 0.85,
297
+ "adalora_beta2": 0.85,
298
+ "adalora_orth_reg_weight": 0.5,
299
+ "llamapro_num_new_blocks": 4,
300
+ "llamapro_num_groups": null,
301
+ "lisa_activated_layers": 0,
302
+ "lisa_step_interval": 20,
303
+ "reft_layer_key": null,
304
+ "reft_layers": null,
305
+ "reft_rank": 4,
306
+ "reft_intervention_type": "LoreftIntervention",
307
+ "reft_args": null,
308
+ "swanlab_token": null,
309
+ "swanlab_project": null,
310
+ "swanlab_workspace": null,
311
+ "swanlab_exp_name": null,
312
+ "swanlab_mode": "cloud",
313
+ "add_version": true,
314
+ "resume_only_model": false,
315
+ "create_checkpoint_symlink": false,
316
+ "packing": false,
317
+ "lazy_tokenize": true,
318
+ "loss_type": null,
319
+ "optimizer": null,
320
+ "metric": null,
321
+ "zero_hpz_partition_size": null,
322
+ "rank": 0,
323
+ "global_world_size": 4,
324
+ "local_world_size": 4,
325
+ "model_suffix": "Qwen2.5-VL-3B-Instruct",
326
+ "model_info": "ModelInfo(model_type='qwen2_5_vl', model_dir='/mnt/petrelfs/liuhongbo/Qwen2.5-VL-3B-Instruct', torch_dtype=torch.bfloat16, max_model_len=128000, quant_method=None, quant_bits=None, rope_scaling={'type': 'default', 'mrope_section': [16, 24, 24], 'rope_type': 'default'}, config=None, task_type='causal_lm', num_labels=None)",
327
+ "model_meta": "ModelMeta(model_type='qwen2_5_vl', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-VL-3B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-3B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-7B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-7B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-32B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-32B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-72B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-72B-Instruct', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-VL-3B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-3B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-7B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-7B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-32B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-32B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-72B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-72B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen2_5_vl', get_function=<function get_model_tokenizer_qwen2_5_vl at 0x7fd8f7224670>, model_arch='qwen2_vl', architectures=['Qwen2_5_VLForConditionalGeneration'], additional_saved_files=[], torch_dtype=None, is_multimodal=True, is_reward=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.49', 'qwen_vl_utils>=0.0.6', 'decord'], tags=[])",
328
+ "model_dir": "/mnt/petrelfs/liuhongbo/Qwen2.5-VL-3B-Instruct",
329
+ "hub": "<class 'swift.hub.hub.MSHub'>",
330
+ "training_args": "Seq2SeqTrainingArguments(output_dir='/mnt/petrelfs/liuhongbo/ms-swift/output/main/sft_without_reasoning/v0-20250505-134456', 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=16, 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='/mnt/petrelfs/liuhongbo/ms-swift/output/main/sft_without_reasoning/v0-20250505-134456/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=100, save_total_limit=3, 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=100, dataloader_num_workers=4, dataloader_prefetch_factor=10, past_index=-1, run_name='/mnt/petrelfs/liuhongbo/ms-swift/output/main/sft_without_reasoning/v0-20250505-134456', 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}, tp_size=0, 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=None, 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', evaluation_strategy='steps', 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=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, dispatch_batches=None, split_batches=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, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, metric_warmup_step=0, fsdp_num=1, acc_steps=1, eval_use_evalscope=False, eval_datasets=[], eval_limit=None, eval_datasets_args=None, eval_generation_config=None, train_type='full', optimizer=None, local_repo_path=None, galore_config=None)"
331
+ }
chat_template.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
3
+ }
config.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2_5_VLForConditionalGeneration"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "eos_token_id": 151645,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 2048,
10
+ "image_token_id": 151655,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 11008,
13
+ "max_position_embeddings": 128000,
14
+ "max_window_layers": 70,
15
+ "model_type": "qwen2_5_vl",
16
+ "num_attention_heads": 16,
17
+ "num_hidden_layers": 36,
18
+ "num_key_value_heads": 2,
19
+ "pad_token_id": 151643,
20
+ "rms_norm_eps": 1e-06,
21
+ "rope_scaling": {
22
+ "mrope_section": [
23
+ 16,
24
+ 24,
25
+ 24
26
+ ],
27
+ "rope_type": "default",
28
+ "type": "default"
29
+ },
30
+ "rope_theta": 1000000.0,
31
+ "sliding_window": 32768,
32
+ "tie_word_embeddings": true,
33
+ "torch_dtype": "bfloat16",
34
+ "transformers_version": "4.50.3",
35
+ "use_cache": false,
36
+ "use_sliding_window": false,
37
+ "video_token_id": 151656,
38
+ "vision_config": {
39
+ "depth": 32,
40
+ "fullatt_block_indexes": [
41
+ 7,
42
+ 15,
43
+ 23,
44
+ 31
45
+ ],
46
+ "hidden_act": "silu",
47
+ "hidden_size": 1280,
48
+ "in_channels": 3,
49
+ "in_chans": 3,
50
+ "intermediate_size": 3420,
51
+ "model_type": "qwen2_5_vl",
52
+ "num_heads": 16,
53
+ "out_hidden_size": 2048,
54
+ "patch_size": 14,
55
+ "spatial_merge_size": 2,
56
+ "spatial_patch_size": 14,
57
+ "temporal_patch_size": 2,
58
+ "tokens_per_second": 2,
59
+ "torch_dtype": "bfloat16",
60
+ "window_size": 112
61
+ },
62
+ "vision_end_token_id": 151653,
63
+ "vision_start_token_id": 151652,
64
+ "vision_token_id": 151654,
65
+ "vocab_size": 151936
66
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.05,
10
+ "temperature": 1e-06,
11
+ "transformers_version": "4.50.3"
12
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fce3b96ae987f4c8dff8ea1ea7e7bde917a118bee4e971d75c2fd769584c50c
3
+ size 4997750760
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa802c5ffa92ce415128841410096545d49702e4ec30cdf0a282b8137fd57c05
3
+ size 2511587184
model.safetensors.index.json ADDED
@@ -0,0 +1,831 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 7509245952
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
7
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
8
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
18
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
25
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
28
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
30
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
37
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
40
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
42
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
49
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
52
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
54
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
61
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
64
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
66
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
73
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
74
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
76
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
78
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
85
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
88
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
90
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
97
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
100
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
102
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
103
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
104
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
108
+ "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
109
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
110
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
112
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
113
+ "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
114
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
116
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
121
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
122
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
124
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
125
+ "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
126
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
127
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
128
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
129
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
130
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
133
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
134
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
135
+ "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
136
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
137
+ "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
138
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
139
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
140
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
141
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
142
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
143
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
144
+ "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
145
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
146
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
147
+ "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
148
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
149
+ "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
150
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
151
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
152
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
153
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
154
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
155
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
156
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
157
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
158
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
159
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
160
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
161
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
162
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
163
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
164
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
165
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
166
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
167
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
168
+ "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
169
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
170
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
171
+ "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
172
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
173
+ "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
174
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
175
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
176
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
177
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
178
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
179
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
180
+ "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
181
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
182
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
183
+ "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
184
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
185
+ "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
186
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
187
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
188
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
189
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
190
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
191
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
192
+ "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
193
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
194
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
195
+ "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
196
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
197
+ "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
198
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
199
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
200
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
201
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
202
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
203
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
204
+ "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
205
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
206
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
207
+ "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
208
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
209
+ "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
210
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
211
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
212
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
213
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
214
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
215
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
216
+ "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
217
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
218
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
219
+ "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
220
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
221
+ "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
222
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
223
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
224
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
225
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
226
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
227
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
228
+ "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
229
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
230
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
231
+ "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
232
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
233
+ "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
234
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
235
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
236
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
237
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
238
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
239
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
240
+ "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
241
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
242
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
243
+ "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
244
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
245
+ "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
246
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
247
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
248
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
249
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
250
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
251
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
252
+ "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
253
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
254
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
255
+ "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
256
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
257
+ "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
258
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
259
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
260
+ "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
261
+ "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
262
+ "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
263
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
264
+ "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
265
+ "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
266
+ "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
267
+ "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
268
+ "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
269
+ "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
270
+ "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
271
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
272
+ "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
273
+ "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
274
+ "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
275
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
276
+ "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
277
+ "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
278
+ "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
279
+ "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
280
+ "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
281
+ "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
282
+ "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
283
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
284
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
285
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
286
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
287
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
288
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
289
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
290
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
291
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
292
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
293
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
294
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
295
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
296
+ "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
297
+ "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
298
+ "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
299
+ "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
300
+ "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
301
+ "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
302
+ "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
303
+ "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
304
+ "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
305
+ "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
306
+ "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
307
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
308
+ "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
309
+ "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
310
+ "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
311
+ "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
312
+ "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
313
+ "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
314
+ "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
315
+ "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
316
+ "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
317
+ "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
318
+ "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
319
+ "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
320
+ "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
321
+ "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
322
+ "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
323
+ "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
324
+ "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
325
+ "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
326
+ "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
327
+ "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
328
+ "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
329
+ "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
330
+ "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
331
+ "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
332
+ "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
333
+ "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
334
+ "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
335
+ "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
336
+ "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
337
+ "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
338
+ "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
339
+ "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
340
+ "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
341
+ "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
342
+ "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
343
+ "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
344
+ "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
345
+ "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
346
+ "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
347
+ "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
348
+ "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
349
+ "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
350
+ "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
351
+ "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
352
+ "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
353
+ "model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
354
+ "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
355
+ "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
356
+ "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
357
+ "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
358
+ "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
359
+ "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
360
+ "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
361
+ "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
362
+ "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
363
+ "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
364
+ "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
365
+ "model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
366
+ "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
367
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
368
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
369
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
370
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
371
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
372
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
373
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
374
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
375
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
376
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
377
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
378
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
379
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
380
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
381
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
382
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
383
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
384
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
385
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
386
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
387
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
388
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
389
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
390
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
391
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
392
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
393
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
394
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
395
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
396
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
397
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
398
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
399
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
400
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
401
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
402
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
403
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
404
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
405
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
406
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
407
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
408
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
409
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
410
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
411
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
412
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
413
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
414
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
415
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
416
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
417
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
418
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
419
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
420
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
421
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
422
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
423
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
424
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
425
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
426
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
427
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
428
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
429
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
430
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
431
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
432
+ "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
433
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
434
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
435
+ "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
436
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
437
+ "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
438
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
439
+ "model.norm.weight": "model-00002-of-00002.safetensors",
440
+ "visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
441
+ "visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
442
+ "visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
443
+ "visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
444
+ "visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
445
+ "visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
446
+ "visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
447
+ "visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
448
+ "visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
449
+ "visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
450
+ "visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
451
+ "visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
452
+ "visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
453
+ "visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
454
+ "visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
455
+ "visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
456
+ "visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
457
+ "visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
458
+ "visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
459
+ "visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
460
+ "visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
461
+ "visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
462
+ "visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
463
+ "visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
464
+ "visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
465
+ "visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
466
+ "visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
467
+ "visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
468
+ "visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
469
+ "visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
470
+ "visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
471
+ "visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
472
+ "visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
473
+ "visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
474
+ "visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
475
+ "visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
476
+ "visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
477
+ "visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
478
+ "visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
479
+ "visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
480
+ "visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
481
+ "visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
482
+ "visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
483
+ "visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
484
+ "visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
485
+ "visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
486
+ "visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
487
+ "visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
488
+ "visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
489
+ "visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
490
+ "visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
491
+ "visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
492
+ "visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
493
+ "visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
494
+ "visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
495
+ "visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
496
+ "visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
497
+ "visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
498
+ "visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
499
+ "visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
500
+ "visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
501
+ "visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
502
+ "visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
503
+ "visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
504
+ "visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
505
+ "visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
506
+ "visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
507
+ "visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
508
+ "visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
509
+ "visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
510
+ "visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
511
+ "visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
512
+ "visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
513
+ "visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
514
+ "visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
515
+ "visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
516
+ "visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
517
+ "visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
518
+ "visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
519
+ "visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
520
+ "visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
521
+ "visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
522
+ "visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
523
+ "visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
524
+ "visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
525
+ "visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
526
+ "visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
527
+ "visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
528
+ "visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
529
+ "visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
530
+ "visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
531
+ "visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
532
+ "visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
533
+ "visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
534
+ "visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
535
+ "visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
536
+ "visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
537
+ "visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
538
+ "visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
539
+ "visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
540
+ "visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
541
+ "visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
542
+ "visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
543
+ "visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
544
+ "visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
545
+ "visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
546
+ "visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
547
+ "visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
548
+ "visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
549
+ "visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
550
+ "visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
551
+ "visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
552
+ "visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
553
+ "visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
554
+ "visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
555
+ "visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
556
+ "visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
557
+ "visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
558
+ "visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
559
+ "visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
560
+ "visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
561
+ "visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
562
+ "visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
563
+ "visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
564
+ "visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
565
+ "visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
566
+ "visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
567
+ "visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
568
+ "visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
569
+ "visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
570
+ "visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
571
+ "visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
572
+ "visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
573
+ "visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
574
+ "visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
575
+ "visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
576
+ "visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
577
+ "visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
578
+ "visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
579
+ "visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
580
+ "visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
581
+ "visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
582
+ "visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
583
+ "visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
584
+ "visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
585
+ "visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
586
+ "visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
587
+ "visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
588
+ "visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
589
+ "visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
590
+ "visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
591
+ "visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
592
+ "visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
593
+ "visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
594
+ "visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
595
+ "visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
596
+ "visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
597
+ "visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
598
+ "visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
599
+ "visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
600
+ "visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
601
+ "visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
602
+ "visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
603
+ "visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
604
+ "visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
605
+ "visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
606
+ "visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
607
+ "visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
608
+ "visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
609
+ "visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
610
+ "visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
611
+ "visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
612
+ "visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
613
+ "visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
614
+ "visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
615
+ "visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
616
+ "visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
617
+ "visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
618
+ "visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
619
+ "visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
620
+ "visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
621
+ "visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
622
+ "visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
623
+ "visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
624
+ "visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
625
+ "visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
626
+ "visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
627
+ "visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
628
+ "visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
629
+ "visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
630
+ "visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
631
+ "visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
632
+ "visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
633
+ "visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
634
+ "visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
635
+ "visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
636
+ "visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
637
+ "visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
638
+ "visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
639
+ "visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
640
+ "visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
641
+ "visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
642
+ "visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
643
+ "visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
644
+ "visual.blocks.24.attn.proj.bias": "model-00001-of-00002.safetensors",
645
+ "visual.blocks.24.attn.proj.weight": "model-00001-of-00002.safetensors",
646
+ "visual.blocks.24.attn.qkv.bias": "model-00001-of-00002.safetensors",
647
+ "visual.blocks.24.attn.qkv.weight": "model-00001-of-00002.safetensors",
648
+ "visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
649
+ "visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
650
+ "visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
651
+ "visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
652
+ "visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
653
+ "visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
654
+ "visual.blocks.24.norm1.weight": "model-00001-of-00002.safetensors",
655
+ "visual.blocks.24.norm2.weight": "model-00001-of-00002.safetensors",
656
+ "visual.blocks.25.attn.proj.bias": "model-00001-of-00002.safetensors",
657
+ "visual.blocks.25.attn.proj.weight": "model-00001-of-00002.safetensors",
658
+ "visual.blocks.25.attn.qkv.bias": "model-00001-of-00002.safetensors",
659
+ "visual.blocks.25.attn.qkv.weight": "model-00001-of-00002.safetensors",
660
+ "visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
661
+ "visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
662
+ "visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
663
+ "visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
664
+ "visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
665
+ "visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
666
+ "visual.blocks.25.norm1.weight": "model-00001-of-00002.safetensors",
667
+ "visual.blocks.25.norm2.weight": "model-00001-of-00002.safetensors",
668
+ "visual.blocks.26.attn.proj.bias": "model-00001-of-00002.safetensors",
669
+ "visual.blocks.26.attn.proj.weight": "model-00001-of-00002.safetensors",
670
+ "visual.blocks.26.attn.qkv.bias": "model-00001-of-00002.safetensors",
671
+ "visual.blocks.26.attn.qkv.weight": "model-00001-of-00002.safetensors",
672
+ "visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
673
+ "visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
674
+ "visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
675
+ "visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
676
+ "visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
677
+ "visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
678
+ "visual.blocks.26.norm1.weight": "model-00001-of-00002.safetensors",
679
+ "visual.blocks.26.norm2.weight": "model-00001-of-00002.safetensors",
680
+ "visual.blocks.27.attn.proj.bias": "model-00001-of-00002.safetensors",
681
+ "visual.blocks.27.attn.proj.weight": "model-00001-of-00002.safetensors",
682
+ "visual.blocks.27.attn.qkv.bias": "model-00001-of-00002.safetensors",
683
+ "visual.blocks.27.attn.qkv.weight": "model-00001-of-00002.safetensors",
684
+ "visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
685
+ "visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
686
+ "visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
687
+ "visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
688
+ "visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
689
+ "visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
690
+ "visual.blocks.27.norm1.weight": "model-00001-of-00002.safetensors",
691
+ "visual.blocks.27.norm2.weight": "model-00001-of-00002.safetensors",
692
+ "visual.blocks.28.attn.proj.bias": "model-00001-of-00002.safetensors",
693
+ "visual.blocks.28.attn.proj.weight": "model-00001-of-00002.safetensors",
694
+ "visual.blocks.28.attn.qkv.bias": "model-00001-of-00002.safetensors",
695
+ "visual.blocks.28.attn.qkv.weight": "model-00001-of-00002.safetensors",
696
+ "visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
697
+ "visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
698
+ "visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
699
+ "visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
700
+ "visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
701
+ "visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
702
+ "visual.blocks.28.norm1.weight": "model-00001-of-00002.safetensors",
703
+ "visual.blocks.28.norm2.weight": "model-00001-of-00002.safetensors",
704
+ "visual.blocks.29.attn.proj.bias": "model-00001-of-00002.safetensors",
705
+ "visual.blocks.29.attn.proj.weight": "model-00001-of-00002.safetensors",
706
+ "visual.blocks.29.attn.qkv.bias": "model-00001-of-00002.safetensors",
707
+ "visual.blocks.29.attn.qkv.weight": "model-00001-of-00002.safetensors",
708
+ "visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
709
+ "visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
710
+ "visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
711
+ "visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
712
+ "visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
713
+ "visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
714
+ "visual.blocks.29.norm1.weight": "model-00001-of-00002.safetensors",
715
+ "visual.blocks.29.norm2.weight": "model-00001-of-00002.safetensors",
716
+ "visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
717
+ "visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
718
+ "visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
719
+ "visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
720
+ "visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
721
+ "visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
722
+ "visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
723
+ "visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
724
+ "visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
725
+ "visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
726
+ "visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
727
+ "visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
728
+ "visual.blocks.30.attn.proj.bias": "model-00001-of-00002.safetensors",
729
+ "visual.blocks.30.attn.proj.weight": "model-00001-of-00002.safetensors",
730
+ "visual.blocks.30.attn.qkv.bias": "model-00001-of-00002.safetensors",
731
+ "visual.blocks.30.attn.qkv.weight": "model-00001-of-00002.safetensors",
732
+ "visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
733
+ "visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
734
+ "visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
735
+ "visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
736
+ "visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
737
+ "visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
738
+ "visual.blocks.30.norm1.weight": "model-00001-of-00002.safetensors",
739
+ "visual.blocks.30.norm2.weight": "model-00001-of-00002.safetensors",
740
+ "visual.blocks.31.attn.proj.bias": "model-00001-of-00002.safetensors",
741
+ "visual.blocks.31.attn.proj.weight": "model-00001-of-00002.safetensors",
742
+ "visual.blocks.31.attn.qkv.bias": "model-00001-of-00002.safetensors",
743
+ "visual.blocks.31.attn.qkv.weight": "model-00001-of-00002.safetensors",
744
+ "visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
745
+ "visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
746
+ "visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
747
+ "visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
748
+ "visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
749
+ "visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
750
+ "visual.blocks.31.norm1.weight": "model-00001-of-00002.safetensors",
751
+ "visual.blocks.31.norm2.weight": "model-00001-of-00002.safetensors",
752
+ "visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
753
+ "visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
754
+ "visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
755
+ "visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
756
+ "visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
757
+ "visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
758
+ "visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
759
+ "visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
760
+ "visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
761
+ "visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
762
+ "visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
763
+ "visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
764
+ "visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
765
+ "visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
766
+ "visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
767
+ "visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
768
+ "visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
769
+ "visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
770
+ "visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
771
+ "visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
772
+ "visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
773
+ "visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
774
+ "visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
775
+ "visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
776
+ "visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
777
+ "visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
778
+ "visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
779
+ "visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
780
+ "visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
781
+ "visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
782
+ "visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
783
+ "visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
784
+ "visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
785
+ "visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
786
+ "visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
787
+ "visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
788
+ "visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
789
+ "visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
790
+ "visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
791
+ "visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
792
+ "visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
793
+ "visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
794
+ "visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
795
+ "visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
796
+ "visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
797
+ "visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
798
+ "visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
799
+ "visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
800
+ "visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
801
+ "visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
802
+ "visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
803
+ "visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
804
+ "visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
805
+ "visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
806
+ "visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
807
+ "visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
808
+ "visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
809
+ "visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
810
+ "visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
811
+ "visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
812
+ "visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
813
+ "visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
814
+ "visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
815
+ "visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
816
+ "visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
817
+ "visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
818
+ "visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
819
+ "visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
820
+ "visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
821
+ "visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
822
+ "visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
823
+ "visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
824
+ "visual.merger.ln_q.weight": "model-00001-of-00002.safetensors",
825
+ "visual.merger.mlp.0.bias": "model-00001-of-00002.safetensors",
826
+ "visual.merger.mlp.0.weight": "model-00001-of-00002.safetensors",
827
+ "visual.merger.mlp.2.bias": "model-00001-of-00002.safetensors",
828
+ "visual.merger.mlp.2.weight": "model-00001-of-00002.safetensors",
829
+ "visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors"
830
+ }
831
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "min_pixels": 3136,
3
+ "max_pixels": 12845056,
4
+ "patch_size": 14,
5
+ "temporal_patch_size": 2,
6
+ "merge_size": 2,
7
+ "image_mean": [
8
+ 0.48145466,
9
+ 0.4578275,
10
+ 0.40821073
11
+ ],
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "image_processor_type": "Qwen2VLImageProcessor",
18
+ "processor_class": "Qwen2_5_VLProcessor"
19
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
tokenizer_config.json ADDED
@@ -0,0 +1,209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|im_end|>",
201
+ "errors": "replace",
202
+ "extra_special_tokens": {},
203
+ "model_max_length": 131072,
204
+ "pad_token": "<|endoftext|>",
205
+ "processor_class": "Qwen2_5_VLProcessor",
206
+ "split_special_tokens": false,
207
+ "tokenizer_class": "Qwen2Tokenizer",
208
+ "unk_token": null
209
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29d9c1908e4acaf41cb93e7a17780b33063c66d384fd432f19a72809463639c7
3
+ size 9976
vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
zero_to_fp32.py ADDED
@@ -0,0 +1,604 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #!/usr/bin/env python
2
+
3
+ # Copyright (c) Microsoft Corporation.
4
+ # SPDX-License-Identifier: Apache-2.0
5
+
6
+ # DeepSpeed Team
7
+
8
+ # This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
9
+ # copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
10
+ # the future. Once extracted, the weights don't require DeepSpeed and can be used in any
11
+ # application.
12
+ #
13
+ # example: python zero_to_fp32.py . pytorch_model.bin
14
+
15
+ import argparse
16
+ import torch
17
+ import glob
18
+ import math
19
+ import os
20
+ import re
21
+ from collections import OrderedDict
22
+ from dataclasses import dataclass
23
+
24
+ # while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
25
+ # DeepSpeed data structures it has to be available in the current python environment.
26
+ from deepspeed.utils import logger
27
+ from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
28
+ FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
29
+ FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
30
+
31
+
32
+ @dataclass
33
+ class zero_model_state:
34
+ buffers: dict()
35
+ param_shapes: dict()
36
+ shared_params: list
37
+ ds_version: int
38
+ frozen_param_shapes: dict()
39
+ frozen_param_fragments: dict()
40
+
41
+
42
+ debug = 0
43
+
44
+ # load to cpu
45
+ device = torch.device('cpu')
46
+
47
+
48
+ def atoi(text):
49
+ return int(text) if text.isdigit() else text
50
+
51
+
52
+ def natural_keys(text):
53
+ '''
54
+ alist.sort(key=natural_keys) sorts in human order
55
+ http://nedbatchelder.com/blog/200712/human_sorting.html
56
+ (See Toothy's implementation in the comments)
57
+ '''
58
+ return [atoi(c) for c in re.split(r'(\d+)', text)]
59
+
60
+
61
+ def get_model_state_file(checkpoint_dir, zero_stage):
62
+ if not os.path.isdir(checkpoint_dir):
63
+ raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
64
+
65
+ # there should be only one file
66
+ if zero_stage <= 2:
67
+ file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
68
+ elif zero_stage == 3:
69
+ file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
70
+
71
+ if not os.path.exists(file):
72
+ raise FileNotFoundError(f"can't find model states file at '{file}'")
73
+
74
+ return file
75
+
76
+
77
+ def get_checkpoint_files(checkpoint_dir, glob_pattern):
78
+ # XXX: need to test that this simple glob rule works for multi-node setup too
79
+ ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
80
+
81
+ if len(ckpt_files) == 0:
82
+ raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
83
+
84
+ return ckpt_files
85
+
86
+
87
+ def get_optim_files(checkpoint_dir):
88
+ return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
89
+
90
+
91
+ def get_model_state_files(checkpoint_dir):
92
+ return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
93
+
94
+
95
+ def parse_model_states(files):
96
+ zero_model_states = []
97
+ for file in files:
98
+ state_dict = torch.load(file, map_location=device)
99
+
100
+ if BUFFER_NAMES not in state_dict:
101
+ raise ValueError(f"{file} is not a model state checkpoint")
102
+ buffer_names = state_dict[BUFFER_NAMES]
103
+ if debug:
104
+ print("Found buffers:", buffer_names)
105
+
106
+ # recover just the buffers while restoring them to fp32 if they were saved in fp16
107
+ buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
108
+ param_shapes = state_dict[PARAM_SHAPES]
109
+
110
+ # collect parameters that are included in param_shapes
111
+ param_names = []
112
+ for s in param_shapes:
113
+ for name in s.keys():
114
+ param_names.append(name)
115
+
116
+ # update with frozen parameters
117
+ frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
118
+ if frozen_param_shapes is not None:
119
+ if debug:
120
+ print(f"Found frozen_param_shapes: {frozen_param_shapes}")
121
+ param_names += list(frozen_param_shapes.keys())
122
+
123
+ # handle shared params
124
+ shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
125
+
126
+ ds_version = state_dict.get(DS_VERSION, None)
127
+
128
+ frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
129
+
130
+ z_model_state = zero_model_state(buffers=buffers,
131
+ param_shapes=param_shapes,
132
+ shared_params=shared_params,
133
+ ds_version=ds_version,
134
+ frozen_param_shapes=frozen_param_shapes,
135
+ frozen_param_fragments=frozen_param_fragments)
136
+ zero_model_states.append(z_model_state)
137
+
138
+ return zero_model_states
139
+
140
+
141
+ def parse_optim_states(files, ds_checkpoint_dir):
142
+
143
+ total_files = len(files)
144
+ state_dicts = []
145
+ for f in files:
146
+ state_dict = torch.load(f, map_location=device)
147
+ # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
148
+ # and also handle the case where it was already removed by another helper script
149
+ state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
150
+ state_dicts.append(state_dict)
151
+
152
+ if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
153
+ raise ValueError(f"{files[0]} is not a zero checkpoint")
154
+ zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
155
+ world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
156
+
157
+ # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
158
+ # parameters can be different from data parallelism for non-expert parameters. So we can just
159
+ # use the max of the partition_count to get the dp world_size.
160
+
161
+ if type(world_size) is list:
162
+ world_size = max(world_size)
163
+
164
+ if world_size != total_files:
165
+ raise ValueError(
166
+ f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
167
+ "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
168
+ )
169
+
170
+ # the groups are named differently in each stage
171
+ if zero_stage <= 2:
172
+ fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
173
+ elif zero_stage == 3:
174
+ fp32_groups_key = FP32_FLAT_GROUPS
175
+ else:
176
+ raise ValueError(f"unknown zero stage {zero_stage}")
177
+
178
+ if zero_stage <= 2:
179
+ fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
180
+ elif zero_stage == 3:
181
+ # if there is more than one param group, there will be multiple flattened tensors - one
182
+ # flattened tensor per group - for simplicity merge them into a single tensor
183
+ #
184
+ # XXX: could make the script more memory efficient for when there are multiple groups - it
185
+ # will require matching the sub-lists of param_shapes for each param group flattened tensor
186
+
187
+ fp32_flat_groups = [
188
+ torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
189
+ ]
190
+
191
+ return zero_stage, world_size, fp32_flat_groups
192
+
193
+
194
+ def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
195
+ """
196
+ Returns fp32 state_dict reconstructed from ds checkpoint
197
+
198
+ Args:
199
+ - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
200
+
201
+ """
202
+ print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
203
+
204
+ optim_files = get_optim_files(ds_checkpoint_dir)
205
+ zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
206
+ print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
207
+
208
+ model_files = get_model_state_files(ds_checkpoint_dir)
209
+
210
+ zero_model_states = parse_model_states(model_files)
211
+ print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
212
+
213
+ if zero_stage <= 2:
214
+ return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
215
+ exclude_frozen_parameters)
216
+ elif zero_stage == 3:
217
+ return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
218
+ exclude_frozen_parameters)
219
+
220
+
221
+ def _zero2_merge_frozen_params(state_dict, zero_model_states):
222
+ if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
223
+ return
224
+
225
+ frozen_param_shapes = zero_model_states[0].frozen_param_shapes
226
+ frozen_param_fragments = zero_model_states[0].frozen_param_fragments
227
+
228
+ if debug:
229
+ num_elem = sum(s.numel() for s in frozen_param_shapes.values())
230
+ print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
231
+
232
+ wanted_params = len(frozen_param_shapes)
233
+ wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
234
+ avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
235
+ print(f'Frozen params: Have {avail_numel} numels to process.')
236
+ print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
237
+
238
+ total_params = 0
239
+ total_numel = 0
240
+ for name, shape in frozen_param_shapes.items():
241
+ total_params += 1
242
+ unpartitioned_numel = shape.numel()
243
+ total_numel += unpartitioned_numel
244
+
245
+ state_dict[name] = frozen_param_fragments[name]
246
+
247
+ if debug:
248
+ print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
249
+
250
+ print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
251
+
252
+
253
+ def _has_callable(obj, fn):
254
+ attr = getattr(obj, fn, None)
255
+ return callable(attr)
256
+
257
+
258
+ def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
259
+ param_shapes = zero_model_states[0].param_shapes
260
+
261
+ # Reconstruction protocol:
262
+ #
263
+ # XXX: document this
264
+
265
+ if debug:
266
+ for i in range(world_size):
267
+ for j in range(len(fp32_flat_groups[0])):
268
+ print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
269
+
270
+ # XXX: memory usage doubles here (zero2)
271
+ num_param_groups = len(fp32_flat_groups[0])
272
+ merged_single_partition_of_fp32_groups = []
273
+ for i in range(num_param_groups):
274
+ merged_partitions = [sd[i] for sd in fp32_flat_groups]
275
+ full_single_fp32_vector = torch.cat(merged_partitions, 0)
276
+ merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
277
+ avail_numel = sum(
278
+ [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
279
+
280
+ if debug:
281
+ wanted_params = sum([len(shapes) for shapes in param_shapes])
282
+ wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
283
+ # not asserting if there is a mismatch due to possible padding
284
+ print(f"Have {avail_numel} numels to process.")
285
+ print(f"Need {wanted_numel} numels in {wanted_params} params.")
286
+
287
+ # params
288
+ # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
289
+ # out-of-core computing solution
290
+ total_numel = 0
291
+ total_params = 0
292
+ for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
293
+ offset = 0
294
+ avail_numel = full_single_fp32_vector.numel()
295
+ for name, shape in shapes.items():
296
+
297
+ unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
298
+ total_numel += unpartitioned_numel
299
+ total_params += 1
300
+
301
+ if debug:
302
+ print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
303
+ state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
304
+ offset += unpartitioned_numel
305
+
306
+ # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
307
+ # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
308
+ # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
309
+ # live optimizer object, so we are checking that the numbers are within the right range
310
+ align_to = 2 * world_size
311
+
312
+ def zero2_align(x):
313
+ return align_to * math.ceil(x / align_to)
314
+
315
+ if debug:
316
+ print(f"original offset={offset}, avail_numel={avail_numel}")
317
+
318
+ offset = zero2_align(offset)
319
+ avail_numel = zero2_align(avail_numel)
320
+
321
+ if debug:
322
+ print(f"aligned offset={offset}, avail_numel={avail_numel}")
323
+
324
+ # Sanity check
325
+ if offset != avail_numel:
326
+ raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
327
+
328
+ print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
329
+
330
+
331
+ def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
332
+ exclude_frozen_parameters):
333
+ state_dict = OrderedDict()
334
+
335
+ # buffers
336
+ buffers = zero_model_states[0].buffers
337
+ state_dict.update(buffers)
338
+ if debug:
339
+ print(f"added {len(buffers)} buffers")
340
+
341
+ if not exclude_frozen_parameters:
342
+ _zero2_merge_frozen_params(state_dict, zero_model_states)
343
+
344
+ _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
345
+
346
+ # recover shared parameters
347
+ for pair in zero_model_states[0].shared_params:
348
+ if pair[1] in state_dict:
349
+ state_dict[pair[0]] = state_dict[pair[1]]
350
+
351
+ return state_dict
352
+
353
+
354
+ def zero3_partitioned_param_info(unpartitioned_numel, world_size):
355
+ remainder = unpartitioned_numel % world_size
356
+ padding_numel = (world_size - remainder) if remainder else 0
357
+ partitioned_numel = math.ceil(unpartitioned_numel / world_size)
358
+ return partitioned_numel, padding_numel
359
+
360
+
361
+ def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
362
+ if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
363
+ return
364
+
365
+ if debug:
366
+ for i in range(world_size):
367
+ num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
368
+ print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
369
+
370
+ frozen_param_shapes = zero_model_states[0].frozen_param_shapes
371
+ wanted_params = len(frozen_param_shapes)
372
+ wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
373
+ avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
374
+ print(f'Frozen params: Have {avail_numel} numels to process.')
375
+ print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
376
+
377
+ total_params = 0
378
+ total_numel = 0
379
+ for name, shape in zero_model_states[0].frozen_param_shapes.items():
380
+ total_params += 1
381
+ unpartitioned_numel = shape.numel()
382
+ total_numel += unpartitioned_numel
383
+
384
+ param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
385
+ state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
386
+
387
+ partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
388
+
389
+ if debug:
390
+ print(
391
+ f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
392
+ )
393
+
394
+ print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
395
+
396
+
397
+ def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
398
+ param_shapes = zero_model_states[0].param_shapes
399
+ avail_numel = fp32_flat_groups[0].numel() * world_size
400
+ # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
401
+ # param, re-consolidating each param, while dealing with padding if any
402
+
403
+ # merge list of dicts, preserving order
404
+ param_shapes = {k: v for d in param_shapes for k, v in d.items()}
405
+
406
+ if debug:
407
+ for i in range(world_size):
408
+ print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
409
+
410
+ wanted_params = len(param_shapes)
411
+ wanted_numel = sum(shape.numel() for shape in param_shapes.values())
412
+ # not asserting if there is a mismatch due to possible padding
413
+ avail_numel = fp32_flat_groups[0].numel() * world_size
414
+ print(f"Trainable params: Have {avail_numel} numels to process.")
415
+ print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
416
+
417
+ # params
418
+ # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
419
+ # out-of-core computing solution
420
+ offset = 0
421
+ total_numel = 0
422
+ total_params = 0
423
+ for name, shape in param_shapes.items():
424
+
425
+ unpartitioned_numel = shape.numel()
426
+ total_numel += unpartitioned_numel
427
+ total_params += 1
428
+
429
+ partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
430
+
431
+ if debug:
432
+ print(
433
+ f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
434
+ )
435
+
436
+ # XXX: memory usage doubles here
437
+ state_dict[name] = torch.cat(
438
+ tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
439
+ 0).narrow(0, 0, unpartitioned_numel).view(shape)
440
+ offset += partitioned_numel
441
+
442
+ offset *= world_size
443
+
444
+ # Sanity check
445
+ if offset != avail_numel:
446
+ raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
447
+
448
+ print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
449
+
450
+
451
+ def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
452
+ exclude_frozen_parameters):
453
+ state_dict = OrderedDict()
454
+
455
+ # buffers
456
+ buffers = zero_model_states[0].buffers
457
+ state_dict.update(buffers)
458
+ if debug:
459
+ print(f"added {len(buffers)} buffers")
460
+
461
+ if not exclude_frozen_parameters:
462
+ _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
463
+
464
+ _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
465
+
466
+ # recover shared parameters
467
+ for pair in zero_model_states[0].shared_params:
468
+ if pair[1] in state_dict:
469
+ state_dict[pair[0]] = state_dict[pair[1]]
470
+
471
+ return state_dict
472
+
473
+
474
+ def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
475
+ """
476
+ Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
477
+ ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
478
+ via a model hub.
479
+
480
+ Args:
481
+ - ``checkpoint_dir``: path to the desired checkpoint folder
482
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
483
+ - ``exclude_frozen_parameters``: exclude frozen parameters
484
+
485
+ Returns:
486
+ - pytorch ``state_dict``
487
+
488
+ Note: this approach may not work if your application doesn't have sufficient free CPU memory and
489
+ you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
490
+ the checkpoint.
491
+
492
+ A typical usage might be ::
493
+
494
+ from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
495
+ # do the training and checkpoint saving
496
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
497
+ model = model.cpu() # move to cpu
498
+ model.load_state_dict(state_dict)
499
+ # submit to model hub or save the model to share with others
500
+
501
+ In this example the ``model`` will no longer be usable in the deepspeed context of the same
502
+ application. i.e. you will need to re-initialize the deepspeed engine, since
503
+ ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
504
+
505
+ If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
506
+
507
+ """
508
+ if tag is None:
509
+ latest_path = os.path.join(checkpoint_dir, 'latest')
510
+ if os.path.isfile(latest_path):
511
+ with open(latest_path, 'r') as fd:
512
+ tag = fd.read().strip()
513
+ else:
514
+ raise ValueError(f"Unable to find 'latest' file at {latest_path}")
515
+
516
+ ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
517
+
518
+ if not os.path.isdir(ds_checkpoint_dir):
519
+ raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
520
+
521
+ return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
522
+
523
+
524
+ def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None, exclude_frozen_parameters=False):
525
+ """
526
+ Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
527
+ loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
528
+
529
+ Args:
530
+ - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
531
+ - ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
532
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
533
+ - ``exclude_frozen_parameters``: exclude frozen parameters
534
+ """
535
+
536
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
537
+ print(f"Saving fp32 state dict to {output_file}")
538
+ torch.save(state_dict, output_file)
539
+
540
+
541
+ def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
542
+ """
543
+ 1. Put the provided model to cpu
544
+ 2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
545
+ 3. Load it into the provided model
546
+
547
+ Args:
548
+ - ``model``: the model object to update
549
+ - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
550
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
551
+
552
+ Returns:
553
+ - ``model`: modified model
554
+
555
+ Make sure you have plenty of CPU memory available before you call this function. If you don't
556
+ have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
557
+ conveniently placed for you in the checkpoint folder.
558
+
559
+ A typical usage might be ::
560
+
561
+ from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
562
+ model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
563
+ # submit to model hub or save the model to share with others
564
+
565
+ Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
566
+ of the same application. i.e. you will need to re-initialize the deepspeed engine, since
567
+ ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
568
+
569
+ """
570
+ logger.info(f"Extracting fp32 weights")
571
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
572
+
573
+ logger.info(f"Overwriting model with fp32 weights")
574
+ model = model.cpu()
575
+ model.load_state_dict(state_dict, strict=False)
576
+
577
+ return model
578
+
579
+
580
+ if __name__ == "__main__":
581
+
582
+ parser = argparse.ArgumentParser()
583
+ parser.add_argument("checkpoint_dir",
584
+ type=str,
585
+ help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
586
+ parser.add_argument(
587
+ "output_file",
588
+ type=str,
589
+ help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
590
+ parser.add_argument("-t",
591
+ "--tag",
592
+ type=str,
593
+ default=None,
594
+ help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
595
+ parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
596
+ parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
597
+ args = parser.parse_args()
598
+
599
+ debug = args.debug
600
+
601
+ convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
602
+ args.output_file,
603
+ tag=args.tag,
604
+ exclude_frozen_parameters=args.exclude_frozen_parameters)