Hugging Face's logo

andyc03
/
Qwen2-VL-PRISM-DPO

Image-Text-to-Text
Transformers
Safetensors
qwen2_vl
conversational
text-generation-inference
Model card Files
xet
Community
1
andyc03 commited on
Commit
720cf6f
·
verified ·
1 Parent(s): 63a950c

update files

Browse files
Files changed (19) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +24 -0
  3. args.json +334 -0
  4. chat_template.jinja +7 -0
  5. config.json +98 -0
  6. generation_config.json +13 -0
  7. merges.txt +0 -0
  8. model-00001-of-00004.safetensors +3 -0
  9. model-00002-of-00004.safetensors +3 -0
  10. model-00003-of-00004.safetensors +3 -0
  11. model-00004-of-00004.safetensors +3 -0
  12. model.safetensors.index.json +737 -0
  13. preprocessor_config.json +19 -0
  14. rng_state.pth +3 -0
  15. special_tokens_map.json +26 -0
  16. tokenizer.json +3 -0
  17. tokenizer_config.json +203 -0
  18. video_preprocessor_config.json +86 -0
  19. vocab.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|/CAPTION|>": 151660,
3
+ "<|/OUTPUT|>": 151664,
4
+ "<|/PROBLEM|>": 151658,
5
+ "<|/REASONING|>": 151662,
6
+ "<|CAPTION|>": 151659,
7
+ "<|OUTPUT|>": 151663,
8
+ "<|PROBLEM|>": 151657,
9
+ "<|REASONING|>": 151661,
10
+ "<|box_end|>": 151649,
11
+ "<|box_start|>": 151648,
12
+ "<|endoftext|>": 151643,
13
+ "<|im_end|>": 151645,
14
+ "<|im_start|>": 151644,
15
+ "<|image_pad|>": 151655,
16
+ "<|object_ref_end|>": 151647,
17
+ "<|object_ref_start|>": 151646,
18
+ "<|quad_end|>": 151651,
19
+ "<|quad_start|>": 151650,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
args.json ADDED
@@ -0,0 +1,334 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "output_dir": "/home/nanxi/MLLM_safeguard/dataset/output/checkpoint-205-merged/v1-20250629-033245",
3
+ "overwrite_output_dir": false,
4
+ "do_train": false,
5
+ "do_eval": false,
6
+ "do_predict": false,
7
+ "eval_strategy": "steps",
8
+ "prediction_loss_only": false,
9
+ "per_device_train_batch_size": 3,
10
+ "per_device_eval_batch_size": 1,
11
+ "per_gpu_train_batch_size": null,
12
+ "per_gpu_eval_batch_size": null,
13
+ "gradient_accumulation_steps": 32,
14
+ "eval_accumulation_steps": null,
15
+ "eval_delay": 0,
16
+ "torch_empty_cache_steps": null,
17
+ "learning_rate": 1e-05,
18
+ "weight_decay": 0.1,
19
+ "adam_beta1": 0.9,
20
+ "adam_beta2": 0.95,
21
+ "adam_epsilon": 1e-08,
22
+ "max_grad_norm": 1.0,
23
+ "num_train_epochs": 5.0,
24
+ "max_steps": -1,
25
+ "lr_scheduler_type": "cosine",
26
+ "lr_scheduler_kwargs": null,
27
+ "warmup_ratio": 0.0,
28
+ "warmup_steps": 0,
29
+ "log_level": "passive",
30
+ "log_level_replica": "warning",
31
+ "log_on_each_node": true,
32
+ "logging_dir": "/home/nanxi/MLLM_safeguard/dataset/output/checkpoint-205-merged/v1-20250629-033245/runs",
33
+ "logging_strategy": "steps",
34
+ "logging_first_step": true,
35
+ "logging_steps": 5,
36
+ "logging_nan_inf_filter": true,
37
+ "save_strategy": "steps",
38
+ "save_steps": 30.0,
39
+ "save_total_limit": 3,
40
+ "save_safetensors": true,
41
+ "save_on_each_node": false,
42
+ "save_only_model": false,
43
+ "restore_callback_states_from_checkpoint": false,
44
+ "no_cuda": false,
45
+ "use_cpu": false,
46
+ "use_mps_device": false,
47
+ "seed": 42,
48
+ "data_seed": 42,
49
+ "jit_mode_eval": false,
50
+ "use_ipex": false,
51
+ "bf16": true,
52
+ "fp16": false,
53
+ "fp16_opt_level": "O1",
54
+ "half_precision_backend": "auto",
55
+ "bf16_full_eval": false,
56
+ "fp16_full_eval": false,
57
+ "tf32": null,
58
+ "local_rank": -1,
59
+ "ddp_backend": null,
60
+ "tpu_num_cores": null,
61
+ "tpu_metrics_debug": false,
62
+ "debug": null,
63
+ "dataloader_drop_last": false,
64
+ "eval_steps": 15.0,
65
+ "dataloader_num_workers": null,
66
+ "dataloader_prefetch_factor": null,
67
+ "past_index": -1,
68
+ "run_name": "/home/nanxi/MLLM_safeguard/dataset/output/checkpoint-205-merged/v1-20250629-033245",
69
+ "disable_tqdm": null,
70
+ "remove_unused_columns": true,
71
+ "label_names": null,
72
+ "load_best_model_at_end": false,
73
+ "metric_for_best_model": "loss",
74
+ "greater_is_better": false,
75
+ "ignore_data_skip": false,
76
+ "fsdp": "",
77
+ "fsdp_min_num_params": 0,
78
+ "fsdp_config": null,
79
+ "fsdp_transformer_layer_cls_to_wrap": null,
80
+ "accelerator_config": {
81
+ "dispatch_batches": false
82
+ },
83
+ "deepspeed": null,
84
+ "label_smoothing_factor": 0.0,
85
+ "optim": "adamw_torch",
86
+ "optim_args": null,
87
+ "adafactor": false,
88
+ "group_by_length": false,
89
+ "length_column_name": "length",
90
+ "report_to": [
91
+ "tensorboard"
92
+ ],
93
+ "ddp_find_unused_parameters": null,
94
+ "ddp_bucket_cap_mb": null,
95
+ "ddp_broadcast_buffers": null,
96
+ "dataloader_pin_memory": true,
97
+ "dataloader_persistent_workers": false,
98
+ "skip_memory_metrics": true,
99
+ "use_legacy_prediction_loop": false,
100
+ "push_to_hub": false,
101
+ "resume_from_checkpoint": null,
102
+ "hub_model_id": null,
103
+ "hub_strategy": "every_save",
104
+ "hub_token": null,
105
+ "hub_private_repo": null,
106
+ "hub_always_push": false,
107
+ "gradient_checkpointing": true,
108
+ "gradient_checkpointing_kwargs": null,
109
+ "include_inputs_for_metrics": false,
110
+ "include_for_metrics": [],
111
+ "eval_do_concat_batches": true,
112
+ "fp16_backend": "auto",
113
+ "push_to_hub_model_id": null,
114
+ "push_to_hub_organization": null,
115
+ "push_to_hub_token": null,
116
+ "mp_parameters": "",
117
+ "auto_find_batch_size": false,
118
+ "full_determinism": false,
119
+ "torchdynamo": null,
120
+ "ray_scope": "last",
121
+ "ddp_timeout": 18000000,
122
+ "torch_compile": false,
123
+ "torch_compile_backend": null,
124
+ "torch_compile_mode": null,
125
+ "include_tokens_per_second": false,
126
+ "include_num_input_tokens_seen": false,
127
+ "neftune_noise_alpha": null,
128
+ "optim_target_modules": null,
129
+ "batch_eval_metrics": false,
130
+ "eval_on_start": false,
131
+ "use_liger_kernel": false,
132
+ "eval_use_gather_object": false,
133
+ "average_tokens_across_devices": false,
134
+ "sortish_sampler": false,
135
+ "predict_with_generate": false,
136
+ "generation_max_length": null,
137
+ "generation_num_beams": null,
138
+ "generation_config": null,
139
+ "vit_gradient_checkpointing": null,
140
+ "check_model": true,
141
+ "acc_strategy": "token",
142
+ "train_dataloader_shuffle": true,
143
+ "max_epochs": null,
144
+ "aligner_lr": null,
145
+ "vit_lr": null,
146
+ "optimizer": null,
147
+ "use_logits_to_keep": null,
148
+ "channels": null,
149
+ "metric_warmup_step": 0,
150
+ "fsdp_num": 1,
151
+ "acc_steps": 1,
152
+ "eval_use_evalscope": false,
153
+ "eval_datasets": [],
154
+ "eval_limit": null,
155
+ "eval_datasets_args": null,
156
+ "eval_generation_config": null,
157
+ "model": "/home/nanxi/MLLM_safeguard/dataset/output/v24-20250628-053154/checkpoint-205-merged",
158
+ "model_type": "qwen2_vl",
159
+ "model_revision": null,
160
+ "task_type": "causal_lm",
161
+ "torch_dtype": "bfloat16",
162
+ "attn_impl": null,
163
+ "num_labels": null,
164
+ "problem_type": null,
165
+ "rope_scaling": null,
166
+ "device_map": null,
167
+ "max_memory": {},
168
+ "local_repo_path": null,
169
+ "init_strategy": null,
170
+ "template": "qwen2_vl",
171
+ "system": null,
172
+ "max_length": null,
173
+ "truncation_strategy": "delete",
174
+ "max_pixels": 302112,
175
+ "agent_template": null,
176
+ "norm_bbox": null,
177
+ "use_chat_template": true,
178
+ "padding_free": false,
179
+ "padding_side": "right",
180
+ "loss_scale": "default",
181
+ "sequence_parallel_size": 1,
182
+ "response_prefix": null,
183
+ "template_backend": "swift",
184
+ "dataset": [
185
+ "/home/nanxi/DATASETS/SafeVL-CoT/SafeVL-CoT_swift_added.json"
186
+ ],
187
+ "val_dataset": [],
188
+ "split_dataset_ratio": 0.01,
189
+ "dataset_num_proc": 1,
190
+ "load_from_cache_file": true,
191
+ "dataset_shuffle": true,
192
+ "val_dataset_shuffle": false,
193
+ "streaming": false,
194
+ "interleave_prob": null,
195
+ "stopping_strategy": "first_exhausted",
196
+ "shuffle_buffer_size": 1000,
197
+ "download_mode": "reuse_dataset_if_exists",
198
+ "columns": {},
199
+ "strict": false,
200
+ "model_name": null,
201
+ "model_author": [
202
+ "lnx"
203
+ ],
204
+ "custom_dataset_info": [],
205
+ "quant_method": null,
206
+ "quant_bits": null,
207
+ "hqq_axis": null,
208
+ "bnb_4bit_compute_dtype": "bfloat16",
209
+ "bnb_4bit_quant_type": "nf4",
210
+ "bnb_4bit_use_double_quant": true,
211
+ "bnb_4bit_quant_storage": null,
212
+ "max_new_tokens": 64,
213
+ "temperature": 0.0,
214
+ "top_k": null,
215
+ "top_p": null,
216
+ "repetition_penalty": null,
217
+ "num_beams": 1,
218
+ "stream": false,
219
+ "stop_words": [],
220
+ "logprobs": false,
221
+ "top_logprobs": null,
222
+ "ckpt_dir": "/home/nanxi/MLLM_safeguard/dataset/output/v24-20250628-053154/checkpoint-205-merged",
223
+ "lora_modules": [],
224
+ "tuner_backend": "peft",
225
+ "train_type": "full",
226
+ "adapters": [],
227
+ "external_plugins": [],
228
+ "model_kwargs": {},
229
+ "load_args": false,
230
+ "load_data_args": false,
231
+ "packing": false,
232
+ "packing_cache": null,
233
+ "custom_register_path": [],
234
+ "use_hf": false,
235
+ "ignore_args_error": false,
236
+ "use_swift_lora": false,
237
+ "freeze_parameters": [
238
+ "model.visual",
239
+ "model.visual.merger"
240
+ ],
241
+ "freeze_parameters_regex": null,
242
+ "freeze_parameters_ratio": 0.0,
243
+ "trainable_parameters": [],
244
+ "trainable_parameters_regex": null,
245
+ "freeze_llm": false,
246
+ "freeze_vit": true,
247
+ "freeze_aligner": true,
248
+ "target_modules": [
249
+ "all-linear"
250
+ ],
251
+ "target_regex": null,
252
+ "modules_to_save": [],
253
+ "lora_rank": 8,
254
+ "lora_alpha": 32,
255
+ "lora_dropout": 0.05,
256
+ "lora_bias": "none",
257
+ "lora_dtype": null,
258
+ "lorap_lr_ratio": null,
259
+ "use_rslora": false,
260
+ "use_dora": false,
261
+ "lora_ga_batch_size": 2,
262
+ "lora_ga_iters": 2,
263
+ "lora_ga_max_length": 1024,
264
+ "lora_ga_direction": "ArB2r",
265
+ "lora_ga_scale": "stable",
266
+ "lora_ga_stable_gamma": 16,
267
+ "init_weights": true,
268
+ "fourier_n_frequency": 2000,
269
+ "fourier_scaling": 300.0,
270
+ "boft_block_size": 4,
271
+ "boft_block_num": 0,
272
+ "boft_n_butterfly_factor": 1,
273
+ "boft_dropout": 0.0,
274
+ "vera_rank": 256,
275
+ "vera_projection_prng_key": 0,
276
+ "vera_dropout": 0.0,
277
+ "vera_d_initial": 0.1,
278
+ "adapter_act": "gelu",
279
+ "adapter_length": 128,
280
+ "use_galore": false,
281
+ "galore_target_modules": null,
282
+ "galore_rank": 128,
283
+ "galore_update_proj_gap": 50,
284
+ "galore_scale": 1.0,
285
+ "galore_proj_type": "std",
286
+ "galore_optim_per_parameter": false,
287
+ "galore_with_embedding": false,
288
+ "galore_quantization": false,
289
+ "galore_proj_quant": false,
290
+ "galore_proj_bits": 4,
291
+ "galore_proj_group_size": 256,
292
+ "galore_cos_threshold": 0.4,
293
+ "galore_gamma_proj": 2,
294
+ "galore_queue_size": 5,
295
+ "adalora_target_r": 8,
296
+ "adalora_init_r": 12,
297
+ "adalora_tinit": 0,
298
+ "adalora_tfinal": 0,
299
+ "adalora_deltaT": 1,
300
+ "adalora_beta1": 0.85,
301
+ "adalora_beta2": 0.85,
302
+ "adalora_orth_reg_weight": 0.5,
303
+ "llamapro_num_new_blocks": 4,
304
+ "llamapro_num_groups": null,
305
+ "lisa_activated_layers": 0,
306
+ "lisa_step_interval": 20,
307
+ "reft_layer_key": null,
308
+ "reft_layers": null,
309
+ "reft_rank": 4,
310
+ "reft_intervention_type": "LoreftIntervention",
311
+ "reft_args": null,
312
+ "swanlab_token": null,
313
+ "swanlab_project": null,
314
+ "swanlab_workspace": null,
315
+ "swanlab_exp_name": null,
316
+ "swanlab_mode": "cloud",
317
+ "add_version": true,
318
+ "resume_only_model": false,
319
+ "create_checkpoint_symlink": false,
320
+ "lazy_tokenize": true,
321
+ "loss_type": null,
322
+ "metric": null,
323
+ "zero_hpz_partition_size": null,
324
+ "rank": -1,
325
+ "global_world_size": 1,
326
+ "local_world_size": 1,
327
+ "model_suffix": "checkpoint-205-merged",
328
+ "model_info": "ModelInfo(model_type='qwen2_vl', model_dir='/home/nanxi/MLLM_safeguard/dataset/output/v24-20250628-053154/checkpoint-205-merged', torch_dtype=torch.bfloat16, max_model_len=32768, quant_method=None, quant_bits=None, rope_scaling={'mrope_section': [16, 24, 24], 'rope_type': 'default', 'type': 'default'}, config=None, task_type='causal_lm', num_labels=None)",
329
+ "model_meta": "ModelMeta(model_type='qwen2_vl', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2-VL-2B-Instruct', hf_model_id='Qwen/Qwen2-VL-2B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-VL-7B-Instruct', hf_model_id='Qwen/Qwen2-VL-7B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-VL-72B-Instruct', hf_model_id='Qwen/Qwen2-VL-72B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-VL-2B', hf_model_id='Qwen/Qwen2-VL-2B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-VL-7B', hf_model_id='Qwen/Qwen2-VL-7B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-VL-72B', hf_model_id='Qwen/Qwen2-VL-72B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-VL-2B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2-VL-2B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-VL-7B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2-VL-7B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-VL-72B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2-VL-72B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-VL-2B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2-VL-2B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-VL-7B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2-VL-7B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-VL-72B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2-VL-72B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-VL-2B-Instruct-AWQ', hf_model_id='Qwen/Qwen2-VL-2B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-VL-7B-Instruct-AWQ', hf_model_id='Qwen/Qwen2-VL-7B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-VL-72B-Instruct-AWQ', hf_model_id='Qwen/Qwen2-VL-72B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='bytedance-research/UI-TARS-2B-SFT', hf_model_id='bytedance-research/UI-TARS-2B-SFT', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='bytedance-research/UI-TARS-7B-SFT', hf_model_id='bytedance-research/UI-TARS-7B-SFT', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='bytedance-research/UI-TARS-7B-DPO', hf_model_id='bytedance-research/UI-TARS-7B-DPO', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='bytedance-research/UI-TARS-72B-SFT', hf_model_id='bytedance-research/UI-TARS-72B-SFT', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='bytedance-research/UI-TARS-72B-DPO', hf_model_id='bytedance-research/UI-TARS-72B-DPO', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='allenai/olmOCR-7B-0225-preview', hf_model_id='allenai/olmOCR-7B-0225-preview', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen2_vl', get_function=<function get_model_tokenizer_qwen2_vl at 0x7ff85250ad40>, model_arch='qwen2_vl', architectures=['Qwen2VLForConditionalGeneration'], additional_saved_files=[], torch_dtype=None, is_multimodal=True, is_reward=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.45', 'qwen_vl_utils>=0.0.6', 'decord'], tags=['vision', 'video'])",
330
+ "model_dir": "/home/nanxi/MLLM_safeguard/dataset/output/v24-20250628-053154/checkpoint-205-merged",
331
+ "hub": "<class 'swift.hub.hub.MSHub'>",
332
+ "evaluation_strategy": "steps",
333
+ "training_args": "Seq2SeqTrainingArguments(output_dir='/home/nanxi/MLLM_safeguard/dataset/output/checkpoint-205-merged/v1-20250629-033245', 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=3, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=32, 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=5.0, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.0, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/home/nanxi/MLLM_safeguard/dataset/output/checkpoint-205-merged/v1-20250629-033245/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=30, 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=15, dataloader_num_workers=1, dataloader_prefetch_factor=10, past_index=-1, run_name='/home/nanxi/MLLM_safeguard/dataset/output/checkpoint-205-merged/v1-20250629-033245', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), deepspeed=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=['tensorboard'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=None, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=18000000, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, include_tokens_per_second=None, include_num_input_tokens_seen=None, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, eval_use_gather_object=False, average_tokens_across_devices=None, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=None, vit_gradient_checkpointing=True, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, aligner_lr=None, vit_lr=None, optimizer=None, use_logits_to_keep=None, channels=None, 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', local_repo_path=None, galore_config=None)"
334
+ }
chat_template.jinja ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {% 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
2
+ You are a helpful assistant.<|im_end|>
3
+ {% endif %}<|im_start|>{{ message['role'] }}
4
+ {% if message['content'] is string %}{{ message['content'] }}<|im_end|>
5
+ {% 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|>
6
+ {% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
7
+ {% endif %}
config.json ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2VLForConditionalGeneration"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "eos_token_id": 151645,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 3584,
10
+ "image_token_id": 151655,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 18944,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 28,
15
+ "model_type": "qwen2_vl",
16
+ "num_attention_heads": 28,
17
+ "num_hidden_layers": 28,
18
+ "num_key_value_heads": 4,
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
+ "text_config": {
33
+ "architectures": [
34
+ "Qwen2VLForConditionalGeneration"
35
+ ],
36
+ "attention_dropout": 0.0,
37
+ "bos_token_id": 151643,
38
+ "eos_token_id": 151645,
39
+ "hidden_act": "silu",
40
+ "hidden_size": 3584,
41
+ "image_token_id": null,
42
+ "initializer_range": 0.02,
43
+ "intermediate_size": 18944,
44
+ "max_position_embeddings": 32768,
45
+ "max_window_layers": 28,
46
+ "model_type": "qwen2_vl_text",
47
+ "num_attention_heads": 28,
48
+ "num_hidden_layers": 28,
49
+ "num_key_value_heads": 4,
50
+ "rms_norm_eps": 1e-06,
51
+ "rope_scaling": {
52
+ "mrope_section": [
53
+ 16,
54
+ 24,
55
+ 24
56
+ ],
57
+ "rope_type": "default",
58
+ "type": "default"
59
+ },
60
+ "rope_theta": 1000000.0,
61
+ "sliding_window": 32768,
62
+ "torch_dtype": "bfloat16",
63
+ "use_cache": true,
64
+ "use_sliding_window": false,
65
+ "video_token_id": null,
66
+ "vision_end_token_id": 151653,
67
+ "vision_start_token_id": 151652,
68
+ "vision_token_id": 151654,
69
+ "vocab_size": 152064
70
+ },
71
+ "tie_word_embeddings": false,
72
+ "torch_dtype": "bfloat16",
73
+ "transformers_version": "4.52.4",
74
+ "use_cache": false,
75
+ "use_sliding_window": false,
76
+ "video_token_id": 151656,
77
+ "vision_config": {
78
+ "depth": 32,
79
+ "embed_dim": 1280,
80
+ "hidden_act": "quick_gelu",
81
+ "hidden_size": 3584,
82
+ "in_channels": 3,
83
+ "in_chans": 3,
84
+ "initializer_range": 0.02,
85
+ "mlp_ratio": 4,
86
+ "model_type": "qwen2_vl",
87
+ "num_heads": 16,
88
+ "patch_size": 14,
89
+ "spatial_merge_size": 2,
90
+ "spatial_patch_size": 14,
91
+ "temporal_patch_size": 2,
92
+ "torch_dtype": "bfloat16"
93
+ },
94
+ "vision_end_token_id": 151653,
95
+ "vision_start_token_id": 151652,
96
+ "vision_token_id": 151654,
97
+ "vocab_size": 152064
98
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "temperature": 0.01,
10
+ "top_k": 1,
11
+ "top_p": 0.001,
12
+ "transformers_version": "4.52.4"
13
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca6a0ab8ac476cfc7d5cce12e356470bd79380f124a54302114f28083720bec7
3
+ size 4966659944
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54e1daf83bad087ea87bb34960cccf37d977d26a188e7bcc41fd97cc9dc0dcb1
3
+ size 4991495816
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11e7f7210acf7e93f7b7308d368e730911d9d21bd4621711ef32489d2e1a380e
3
+ size 4932751040
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5494a1fc29a6aee7f176f7b039c6425db00161b316f490e10856bfd555f4824d
3
+ size 1691924384
model.safetensors.index.json ADDED
@@ -0,0 +1,737 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16582751232
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
17
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
19
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
26
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
27
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
28
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
29
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
30
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
31
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
32
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
38
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
41
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
43
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
50
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
53
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
55
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
62
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
65
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
67
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
74
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
77
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
79
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
86
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
89
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
91
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
98
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
101
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
103
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
105
+ "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
106
+ "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
107
+ "model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
108
+ "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
109
+ "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
110
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
113
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
115
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
117
+ "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
118
+ "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
119
+ "model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
120
+ "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
121
+ "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
122
+ "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
123
+ "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
124
+ "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
125
+ "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
126
+ "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
127
+ "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
128
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
131
+ "model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
132
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
133
+ "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
134
+ "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
135
+ "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
136
+ "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
137
+ "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
138
+ "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
139
+ "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
140
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
146
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
149
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
151
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
153
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
154
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
155
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
156
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
157
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
158
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
159
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
160
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
161
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
162
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
163
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
164
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
170
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
173
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
175
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
182
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
185
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
187
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
194
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
197
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
199
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
206
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
209
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
211
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
216
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
217
+ "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
218
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
219
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
220
+ "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
221
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
222
+ "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
223
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
224
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
230
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
233
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
234
+ "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
235
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
236
+ "model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
237
+ "model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
238
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
241
+ "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
242
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
243
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
244
+ "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
245
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
246
+ "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
247
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
248
+ "model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
249
+ "model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
250
+ "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
251
+ "model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
252
+ "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
253
+ "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
254
+ "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
255
+ "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
256
+ "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
257
+ "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
258
+ "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
259
+ "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
260
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
261
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
266
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
267
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
269
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
270
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
271
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
272
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
278
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
279
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
281
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
282
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
283
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
284
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
285
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
286
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
287
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
288
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
289
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
290
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
291
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
292
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
293
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
294
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
295
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
296
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
297
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
298
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
299
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
300
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
301
+ "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
302
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
303
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
304
+ "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
305
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
306
+ "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
307
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
308
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
309
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
310
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
311
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
312
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
313
+ "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
314
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
315
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
316
+ "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
317
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
318
+ "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
319
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
320
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
321
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
322
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
323
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
324
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
325
+ "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
326
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
327
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
328
+ "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
329
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
330
+ "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
331
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
332
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
333
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
334
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
335
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
336
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
337
+ "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
338
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
339
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
340
+ "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
341
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
342
+ "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
343
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
344
+ "model.norm.weight": "model-00004-of-00004.safetensors",
345
+ "visual.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors",
346
+ "visual.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
347
+ "visual.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
348
+ "visual.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
349
+ "visual.blocks.0.mlp.fc1.bias": "model-00001-of-00004.safetensors",
350
+ "visual.blocks.0.mlp.fc1.weight": "model-00001-of-00004.safetensors",
351
+ "visual.blocks.0.mlp.fc2.bias": "model-00001-of-00004.safetensors",
352
+ "visual.blocks.0.mlp.fc2.weight": "model-00001-of-00004.safetensors",
353
+ "visual.blocks.0.norm1.bias": "model-00001-of-00004.safetensors",
354
+ "visual.blocks.0.norm1.weight": "model-00001-of-00004.safetensors",
355
+ "visual.blocks.0.norm2.bias": "model-00001-of-00004.safetensors",
356
+ "visual.blocks.0.norm2.weight": "model-00001-of-00004.safetensors",
357
+ "visual.blocks.1.attn.proj.bias": "model-00001-of-00004.safetensors",
358
+ "visual.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors",
359
+ "visual.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
360
+ "visual.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
361
+ "visual.blocks.1.mlp.fc1.bias": "model-00001-of-00004.safetensors",
362
+ "visual.blocks.1.mlp.fc1.weight": "model-00001-of-00004.safetensors",
363
+ "visual.blocks.1.mlp.fc2.bias": "model-00001-of-00004.safetensors",
364
+ "visual.blocks.1.mlp.fc2.weight": "model-00001-of-00004.safetensors",
365
+ "visual.blocks.1.norm1.bias": "model-00001-of-00004.safetensors",
366
+ "visual.blocks.1.norm1.weight": "model-00001-of-00004.safetensors",
367
+ "visual.blocks.1.norm2.bias": "model-00001-of-00004.safetensors",
368
+ "visual.blocks.1.norm2.weight": "model-00001-of-00004.safetensors",
369
+ "visual.blocks.10.attn.proj.bias": "model-00001-of-00004.safetensors",
370
+ "visual.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors",
371
+ "visual.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
372
+ "visual.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
373
+ "visual.blocks.10.mlp.fc1.bias": "model-00001-of-00004.safetensors",
374
+ "visual.blocks.10.mlp.fc1.weight": "model-00001-of-00004.safetensors",
375
+ "visual.blocks.10.mlp.fc2.bias": "model-00001-of-00004.safetensors",
376
+ "visual.blocks.10.mlp.fc2.weight": "model-00001-of-00004.safetensors",
377
+ "visual.blocks.10.norm1.bias": "model-00001-of-00004.safetensors",
378
+ "visual.blocks.10.norm1.weight": "model-00001-of-00004.safetensors",
379
+ "visual.blocks.10.norm2.bias": "model-00001-of-00004.safetensors",
380
+ "visual.blocks.10.norm2.weight": "model-00001-of-00004.safetensors",
381
+ "visual.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors",
382
+ "visual.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors",
383
+ "visual.blocks.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
384
+ "visual.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
385
+ "visual.blocks.11.mlp.fc1.bias": "model-00001-of-00004.safetensors",
386
+ "visual.blocks.11.mlp.fc1.weight": "model-00001-of-00004.safetensors",
387
+ "visual.blocks.11.mlp.fc2.bias": "model-00001-of-00004.safetensors",
388
+ "visual.blocks.11.mlp.fc2.weight": "model-00001-of-00004.safetensors",
389
+ "visual.blocks.11.norm1.bias": "model-00001-of-00004.safetensors",
390
+ "visual.blocks.11.norm1.weight": "model-00001-of-00004.safetensors",
391
+ "visual.blocks.11.norm2.bias": "model-00001-of-00004.safetensors",
392
+ "visual.blocks.11.norm2.weight": "model-00001-of-00004.safetensors",
393
+ "visual.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors",
394
+ "visual.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors",
395
+ "visual.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
396
+ "visual.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
397
+ "visual.blocks.12.mlp.fc1.bias": "model-00001-of-00004.safetensors",
398
+ "visual.blocks.12.mlp.fc1.weight": "model-00001-of-00004.safetensors",
399
+ "visual.blocks.12.mlp.fc2.bias": "model-00001-of-00004.safetensors",
400
+ "visual.blocks.12.mlp.fc2.weight": "model-00001-of-00004.safetensors",
401
+ "visual.blocks.12.norm1.bias": "model-00001-of-00004.safetensors",
402
+ "visual.blocks.12.norm1.weight": "model-00001-of-00004.safetensors",
403
+ "visual.blocks.12.norm2.bias": "model-00001-of-00004.safetensors",
404
+ "visual.blocks.12.norm2.weight": "model-00001-of-00004.safetensors",
405
+ "visual.blocks.13.attn.proj.bias": "model-00001-of-00004.safetensors",
406
+ "visual.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors",
407
+ "visual.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
408
+ "visual.blocks.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
409
+ "visual.blocks.13.mlp.fc1.bias": "model-00001-of-00004.safetensors",
410
+ "visual.blocks.13.mlp.fc1.weight": "model-00001-of-00004.safetensors",
411
+ "visual.blocks.13.mlp.fc2.bias": "model-00001-of-00004.safetensors",
412
+ "visual.blocks.13.mlp.fc2.weight": "model-00001-of-00004.safetensors",
413
+ "visual.blocks.13.norm1.bias": "model-00001-of-00004.safetensors",
414
+ "visual.blocks.13.norm1.weight": "model-00001-of-00004.safetensors",
415
+ "visual.blocks.13.norm2.bias": "model-00001-of-00004.safetensors",
416
+ "visual.blocks.13.norm2.weight": "model-00001-of-00004.safetensors",
417
+ "visual.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors",
418
+ "visual.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors",
419
+ "visual.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
420
+ "visual.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
421
+ "visual.blocks.14.mlp.fc1.bias": "model-00001-of-00004.safetensors",
422
+ "visual.blocks.14.mlp.fc1.weight": "model-00001-of-00004.safetensors",
423
+ "visual.blocks.14.mlp.fc2.bias": "model-00001-of-00004.safetensors",
424
+ "visual.blocks.14.mlp.fc2.weight": "model-00001-of-00004.safetensors",
425
+ "visual.blocks.14.norm1.bias": "model-00001-of-00004.safetensors",
426
+ "visual.blocks.14.norm1.weight": "model-00001-of-00004.safetensors",
427
+ "visual.blocks.14.norm2.bias": "model-00001-of-00004.safetensors",
428
+ "visual.blocks.14.norm2.weight": "model-00001-of-00004.safetensors",
429
+ "visual.blocks.15.attn.proj.bias": "model-00001-of-00004.safetensors",
430
+ "visual.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors",
431
+ "visual.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
432
+ "visual.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
433
+ "visual.blocks.15.mlp.fc1.bias": "model-00001-of-00004.safetensors",
434
+ "visual.blocks.15.mlp.fc1.weight": "model-00001-of-00004.safetensors",
435
+ "visual.blocks.15.mlp.fc2.bias": "model-00001-of-00004.safetensors",
436
+ "visual.blocks.15.mlp.fc2.weight": "model-00001-of-00004.safetensors",
437
+ "visual.blocks.15.norm1.bias": "model-00001-of-00004.safetensors",
438
+ "visual.blocks.15.norm1.weight": "model-00001-of-00004.safetensors",
439
+ "visual.blocks.15.norm2.bias": "model-00001-of-00004.safetensors",
440
+ "visual.blocks.15.norm2.weight": "model-00001-of-00004.safetensors",
441
+ "visual.blocks.16.attn.proj.bias": "model-00001-of-00004.safetensors",
442
+ "visual.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors",
443
+ "visual.blocks.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
444
+ "visual.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
445
+ "visual.blocks.16.mlp.fc1.bias": "model-00001-of-00004.safetensors",
446
+ "visual.blocks.16.mlp.fc1.weight": "model-00001-of-00004.safetensors",
447
+ "visual.blocks.16.mlp.fc2.bias": "model-00001-of-00004.safetensors",
448
+ "visual.blocks.16.mlp.fc2.weight": "model-00001-of-00004.safetensors",
449
+ "visual.blocks.16.norm1.bias": "model-00001-of-00004.safetensors",
450
+ "visual.blocks.16.norm1.weight": "model-00001-of-00004.safetensors",
451
+ "visual.blocks.16.norm2.bias": "model-00001-of-00004.safetensors",
452
+ "visual.blocks.16.norm2.weight": "model-00001-of-00004.safetensors",
453
+ "visual.blocks.17.attn.proj.bias": "model-00001-of-00004.safetensors",
454
+ "visual.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors",
455
+ "visual.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
456
+ "visual.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
457
+ "visual.blocks.17.mlp.fc1.bias": "model-00001-of-00004.safetensors",
458
+ "visual.blocks.17.mlp.fc1.weight": "model-00001-of-00004.safetensors",
459
+ "visual.blocks.17.mlp.fc2.bias": "model-00001-of-00004.safetensors",
460
+ "visual.blocks.17.mlp.fc2.weight": "model-00001-of-00004.safetensors",
461
+ "visual.blocks.17.norm1.bias": "model-00001-of-00004.safetensors",
462
+ "visual.blocks.17.norm1.weight": "model-00001-of-00004.safetensors",
463
+ "visual.blocks.17.norm2.bias": "model-00001-of-00004.safetensors",
464
+ "visual.blocks.17.norm2.weight": "model-00001-of-00004.safetensors",
465
+ "visual.blocks.18.attn.proj.bias": "model-00001-of-00004.safetensors",
466
+ "visual.blocks.18.attn.proj.weight": "model-00001-of-00004.safetensors",
467
+ "visual.blocks.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
468
+ "visual.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
469
+ "visual.blocks.18.mlp.fc1.bias": "model-00001-of-00004.safetensors",
470
+ "visual.blocks.18.mlp.fc1.weight": "model-00001-of-00004.safetensors",
471
+ "visual.blocks.18.mlp.fc2.bias": "model-00001-of-00004.safetensors",
472
+ "visual.blocks.18.mlp.fc2.weight": "model-00001-of-00004.safetensors",
473
+ "visual.blocks.18.norm1.bias": "model-00001-of-00004.safetensors",
474
+ "visual.blocks.18.norm1.weight": "model-00001-of-00004.safetensors",
475
+ "visual.blocks.18.norm2.bias": "model-00001-of-00004.safetensors",
476
+ "visual.blocks.18.norm2.weight": "model-00001-of-00004.safetensors",
477
+ "visual.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors",
478
+ "visual.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors",
479
+ "visual.blocks.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
480
+ "visual.blocks.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
481
+ "visual.blocks.19.mlp.fc1.bias": "model-00001-of-00004.safetensors",
482
+ "visual.blocks.19.mlp.fc1.weight": "model-00001-of-00004.safetensors",
483
+ "visual.blocks.19.mlp.fc2.bias": "model-00001-of-00004.safetensors",
484
+ "visual.blocks.19.mlp.fc2.weight": "model-00001-of-00004.safetensors",
485
+ "visual.blocks.19.norm1.bias": "model-00001-of-00004.safetensors",
486
+ "visual.blocks.19.norm1.weight": "model-00001-of-00004.safetensors",
487
+ "visual.blocks.19.norm2.bias": "model-00001-of-00004.safetensors",
488
+ "visual.blocks.19.norm2.weight": "model-00001-of-00004.safetensors",
489
+ "visual.blocks.2.attn.proj.bias": "model-00001-of-00004.safetensors",
490
+ "visual.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors",
491
+ "visual.blocks.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
492
+ "visual.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
493
+ "visual.blocks.2.mlp.fc1.bias": "model-00001-of-00004.safetensors",
494
+ "visual.blocks.2.mlp.fc1.weight": "model-00001-of-00004.safetensors",
495
+ "visual.blocks.2.mlp.fc2.bias": "model-00001-of-00004.safetensors",
496
+ "visual.blocks.2.mlp.fc2.weight": "model-00001-of-00004.safetensors",
497
+ "visual.blocks.2.norm1.bias": "model-00001-of-00004.safetensors",
498
+ "visual.blocks.2.norm1.weight": "model-00001-of-00004.safetensors",
499
+ "visual.blocks.2.norm2.bias": "model-00001-of-00004.safetensors",
500
+ "visual.blocks.2.norm2.weight": "model-00001-of-00004.safetensors",
501
+ "visual.blocks.20.attn.proj.bias": "model-00001-of-00004.safetensors",
502
+ "visual.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors",
503
+ "visual.blocks.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
504
+ "visual.blocks.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
505
+ "visual.blocks.20.mlp.fc1.bias": "model-00001-of-00004.safetensors",
506
+ "visual.blocks.20.mlp.fc1.weight": "model-00001-of-00004.safetensors",
507
+ "visual.blocks.20.mlp.fc2.bias": "model-00001-of-00004.safetensors",
508
+ "visual.blocks.20.mlp.fc2.weight": "model-00001-of-00004.safetensors",
509
+ "visual.blocks.20.norm1.bias": "model-00001-of-00004.safetensors",
510
+ "visual.blocks.20.norm1.weight": "model-00001-of-00004.safetensors",
511
+ "visual.blocks.20.norm2.bias": "model-00001-of-00004.safetensors",
512
+ "visual.blocks.20.norm2.weight": "model-00001-of-00004.safetensors",
513
+ "visual.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors",
514
+ "visual.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors",
515
+ "visual.blocks.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
516
+ "visual.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
517
+ "visual.blocks.21.mlp.fc1.bias": "model-00001-of-00004.safetensors",
518
+ "visual.blocks.21.mlp.fc1.weight": "model-00001-of-00004.safetensors",
519
+ "visual.blocks.21.mlp.fc2.bias": "model-00001-of-00004.safetensors",
520
+ "visual.blocks.21.mlp.fc2.weight": "model-00001-of-00004.safetensors",
521
+ "visual.blocks.21.norm1.bias": "model-00001-of-00004.safetensors",
522
+ "visual.blocks.21.norm1.weight": "model-00001-of-00004.safetensors",
523
+ "visual.blocks.21.norm2.bias": "model-00001-of-00004.safetensors",
524
+ "visual.blocks.21.norm2.weight": "model-00001-of-00004.safetensors",
525
+ "visual.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors",
526
+ "visual.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors",
527
+ "visual.blocks.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
528
+ "visual.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
529
+ "visual.blocks.22.mlp.fc1.bias": "model-00001-of-00004.safetensors",
530
+ "visual.blocks.22.mlp.fc1.weight": "model-00001-of-00004.safetensors",
531
+ "visual.blocks.22.mlp.fc2.bias": "model-00001-of-00004.safetensors",
532
+ "visual.blocks.22.mlp.fc2.weight": "model-00001-of-00004.safetensors",
533
+ "visual.blocks.22.norm1.bias": "model-00001-of-00004.safetensors",
534
+ "visual.blocks.22.norm1.weight": "model-00001-of-00004.safetensors",
535
+ "visual.blocks.22.norm2.bias": "model-00001-of-00004.safetensors",
536
+ "visual.blocks.22.norm2.weight": "model-00001-of-00004.safetensors",
537
+ "visual.blocks.23.attn.proj.bias": "model-00001-of-00004.safetensors",
538
+ "visual.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors",
539
+ "visual.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
540
+ "visual.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
541
+ "visual.blocks.23.mlp.fc1.bias": "model-00001-of-00004.safetensors",
542
+ "visual.blocks.23.mlp.fc1.weight": "model-00001-of-00004.safetensors",
543
+ "visual.blocks.23.mlp.fc2.bias": "model-00001-of-00004.safetensors",
544
+ "visual.blocks.23.mlp.fc2.weight": "model-00001-of-00004.safetensors",
545
+ "visual.blocks.23.norm1.bias": "model-00001-of-00004.safetensors",
546
+ "visual.blocks.23.norm1.weight": "model-00001-of-00004.safetensors",
547
+ "visual.blocks.23.norm2.bias": "model-00001-of-00004.safetensors",
548
+ "visual.blocks.23.norm2.weight": "model-00001-of-00004.safetensors",
549
+ "visual.blocks.24.attn.proj.bias": "model-00001-of-00004.safetensors",
550
+ "visual.blocks.24.attn.proj.weight": "model-00001-of-00004.safetensors",
551
+ "visual.blocks.24.attn.qkv.bias": "model-00001-of-00004.safetensors",
552
+ "visual.blocks.24.attn.qkv.weight": "model-00001-of-00004.safetensors",
553
+ "visual.blocks.24.mlp.fc1.bias": "model-00001-of-00004.safetensors",
554
+ "visual.blocks.24.mlp.fc1.weight": "model-00001-of-00004.safetensors",
555
+ "visual.blocks.24.mlp.fc2.bias": "model-00001-of-00004.safetensors",
556
+ "visual.blocks.24.mlp.fc2.weight": "model-00001-of-00004.safetensors",
557
+ "visual.blocks.24.norm1.bias": "model-00001-of-00004.safetensors",
558
+ "visual.blocks.24.norm1.weight": "model-00001-of-00004.safetensors",
559
+ "visual.blocks.24.norm2.bias": "model-00001-of-00004.safetensors",
560
+ "visual.blocks.24.norm2.weight": "model-00001-of-00004.safetensors",
561
+ "visual.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors",
562
+ "visual.blocks.25.attn.proj.weight": "model-00001-of-00004.safetensors",
563
+ "visual.blocks.25.attn.qkv.bias": "model-00001-of-00004.safetensors",
564
+ "visual.blocks.25.attn.qkv.weight": "model-00001-of-00004.safetensors",
565
+ "visual.blocks.25.mlp.fc1.bias": "model-00001-of-00004.safetensors",
566
+ "visual.blocks.25.mlp.fc1.weight": "model-00001-of-00004.safetensors",
567
+ "visual.blocks.25.mlp.fc2.bias": "model-00001-of-00004.safetensors",
568
+ "visual.blocks.25.mlp.fc2.weight": "model-00001-of-00004.safetensors",
569
+ "visual.blocks.25.norm1.bias": "model-00001-of-00004.safetensors",
570
+ "visual.blocks.25.norm1.weight": "model-00001-of-00004.safetensors",
571
+ "visual.blocks.25.norm2.bias": "model-00001-of-00004.safetensors",
572
+ "visual.blocks.25.norm2.weight": "model-00001-of-00004.safetensors",
573
+ "visual.blocks.26.attn.proj.bias": "model-00001-of-00004.safetensors",
574
+ "visual.blocks.26.attn.proj.weight": "model-00001-of-00004.safetensors",
575
+ "visual.blocks.26.attn.qkv.bias": "model-00001-of-00004.safetensors",
576
+ "visual.blocks.26.attn.qkv.weight": "model-00001-of-00004.safetensors",
577
+ "visual.blocks.26.mlp.fc1.bias": "model-00001-of-00004.safetensors",
578
+ "visual.blocks.26.mlp.fc1.weight": "model-00001-of-00004.safetensors",
579
+ "visual.blocks.26.mlp.fc2.bias": "model-00001-of-00004.safetensors",
580
+ "visual.blocks.26.mlp.fc2.weight": "model-00001-of-00004.safetensors",
581
+ "visual.blocks.26.norm1.bias": "model-00001-of-00004.safetensors",
582
+ "visual.blocks.26.norm1.weight": "model-00001-of-00004.safetensors",
583
+ "visual.blocks.26.norm2.bias": "model-00001-of-00004.safetensors",
584
+ "visual.blocks.26.norm2.weight": "model-00001-of-00004.safetensors",
585
+ "visual.blocks.27.attn.proj.bias": "model-00001-of-00004.safetensors",
586
+ "visual.blocks.27.attn.proj.weight": "model-00001-of-00004.safetensors",
587
+ "visual.blocks.27.attn.qkv.bias": "model-00001-of-00004.safetensors",
588
+ "visual.blocks.27.attn.qkv.weight": "model-00001-of-00004.safetensors",
589
+ "visual.blocks.27.mlp.fc1.bias": "model-00001-of-00004.safetensors",
590
+ "visual.blocks.27.mlp.fc1.weight": "model-00001-of-00004.safetensors",
591
+ "visual.blocks.27.mlp.fc2.bias": "model-00001-of-00004.safetensors",
592
+ "visual.blocks.27.mlp.fc2.weight": "model-00001-of-00004.safetensors",
593
+ "visual.blocks.27.norm1.bias": "model-00001-of-00004.safetensors",
594
+ "visual.blocks.27.norm1.weight": "model-00001-of-00004.safetensors",
595
+ "visual.blocks.27.norm2.bias": "model-00001-of-00004.safetensors",
596
+ "visual.blocks.27.norm2.weight": "model-00001-of-00004.safetensors",
597
+ "visual.blocks.28.attn.proj.bias": "model-00001-of-00004.safetensors",
598
+ "visual.blocks.28.attn.proj.weight": "model-00001-of-00004.safetensors",
599
+ "visual.blocks.28.attn.qkv.bias": "model-00001-of-00004.safetensors",
600
+ "visual.blocks.28.attn.qkv.weight": "model-00001-of-00004.safetensors",
601
+ "visual.blocks.28.mlp.fc1.bias": "model-00001-of-00004.safetensors",
602
+ "visual.blocks.28.mlp.fc1.weight": "model-00001-of-00004.safetensors",
603
+ "visual.blocks.28.mlp.fc2.bias": "model-00001-of-00004.safetensors",
604
+ "visual.blocks.28.mlp.fc2.weight": "model-00001-of-00004.safetensors",
605
+ "visual.blocks.28.norm1.bias": "model-00001-of-00004.safetensors",
606
+ "visual.blocks.28.norm1.weight": "model-00001-of-00004.safetensors",
607
+ "visual.blocks.28.norm2.bias": "model-00001-of-00004.safetensors",
608
+ "visual.blocks.28.norm2.weight": "model-00001-of-00004.safetensors",
609
+ "visual.blocks.29.attn.proj.bias": "model-00001-of-00004.safetensors",
610
+ "visual.blocks.29.attn.proj.weight": "model-00001-of-00004.safetensors",
611
+ "visual.blocks.29.attn.qkv.bias": "model-00001-of-00004.safetensors",
612
+ "visual.blocks.29.attn.qkv.weight": "model-00001-of-00004.safetensors",
613
+ "visual.blocks.29.mlp.fc1.bias": "model-00001-of-00004.safetensors",
614
+ "visual.blocks.29.mlp.fc1.weight": "model-00001-of-00004.safetensors",
615
+ "visual.blocks.29.mlp.fc2.bias": "model-00001-of-00004.safetensors",
616
+ "visual.blocks.29.mlp.fc2.weight": "model-00001-of-00004.safetensors",
617
+ "visual.blocks.29.norm1.bias": "model-00001-of-00004.safetensors",
618
+ "visual.blocks.29.norm1.weight": "model-00001-of-00004.safetensors",
619
+ "visual.blocks.29.norm2.bias": "model-00001-of-00004.safetensors",
620
+ "visual.blocks.29.norm2.weight": "model-00001-of-00004.safetensors",
621
+ "visual.blocks.3.attn.proj.bias": "model-00001-of-00004.safetensors",
622
+ "visual.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors",
623
+ "visual.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
624
+ "visual.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
625
+ "visual.blocks.3.mlp.fc1.bias": "model-00001-of-00004.safetensors",
626
+ "visual.blocks.3.mlp.fc1.weight": "model-00001-of-00004.safetensors",
627
+ "visual.blocks.3.mlp.fc2.bias": "model-00001-of-00004.safetensors",
628
+ "visual.blocks.3.mlp.fc2.weight": "model-00001-of-00004.safetensors",
629
+ "visual.blocks.3.norm1.bias": "model-00001-of-00004.safetensors",
630
+ "visual.blocks.3.norm1.weight": "model-00001-of-00004.safetensors",
631
+ "visual.blocks.3.norm2.bias": "model-00001-of-00004.safetensors",
632
+ "visual.blocks.3.norm2.weight": "model-00001-of-00004.safetensors",
633
+ "visual.blocks.30.attn.proj.bias": "model-00001-of-00004.safetensors",
634
+ "visual.blocks.30.attn.proj.weight": "model-00001-of-00004.safetensors",
635
+ "visual.blocks.30.attn.qkv.bias": "model-00001-of-00004.safetensors",
636
+ "visual.blocks.30.attn.qkv.weight": "model-00001-of-00004.safetensors",
637
+ "visual.blocks.30.mlp.fc1.bias": "model-00001-of-00004.safetensors",
638
+ "visual.blocks.30.mlp.fc1.weight": "model-00001-of-00004.safetensors",
639
+ "visual.blocks.30.mlp.fc2.bias": "model-00001-of-00004.safetensors",
640
+ "visual.blocks.30.mlp.fc2.weight": "model-00001-of-00004.safetensors",
641
+ "visual.blocks.30.norm1.bias": "model-00001-of-00004.safetensors",
642
+ "visual.blocks.30.norm1.weight": "model-00001-of-00004.safetensors",
643
+ "visual.blocks.30.norm2.bias": "model-00001-of-00004.safetensors",
644
+ "visual.blocks.30.norm2.weight": "model-00001-of-00004.safetensors",
645
+ "visual.blocks.31.attn.proj.bias": "model-00001-of-00004.safetensors",
646
+ "visual.blocks.31.attn.proj.weight": "model-00001-of-00004.safetensors",
647
+ "visual.blocks.31.attn.qkv.bias": "model-00001-of-00004.safetensors",
648
+ "visual.blocks.31.attn.qkv.weight": "model-00001-of-00004.safetensors",
649
+ "visual.blocks.31.mlp.fc1.bias": "model-00001-of-00004.safetensors",
650
+ "visual.blocks.31.mlp.fc1.weight": "model-00001-of-00004.safetensors",
651
+ "visual.blocks.31.mlp.fc2.bias": "model-00001-of-00004.safetensors",
652
+ "visual.blocks.31.mlp.fc2.weight": "model-00001-of-00004.safetensors",
653
+ "visual.blocks.31.norm1.bias": "model-00001-of-00004.safetensors",
654
+ "visual.blocks.31.norm1.weight": "model-00001-of-00004.safetensors",
655
+ "visual.blocks.31.norm2.bias": "model-00001-of-00004.safetensors",
656
+ "visual.blocks.31.norm2.weight": "model-00001-of-00004.safetensors",
657
+ "visual.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors",
658
+ "visual.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors",
659
+ "visual.blocks.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
660
+ "visual.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
661
+ "visual.blocks.4.mlp.fc1.bias": "model-00001-of-00004.safetensors",
662
+ "visual.blocks.4.mlp.fc1.weight": "model-00001-of-00004.safetensors",
663
+ "visual.blocks.4.mlp.fc2.bias": "model-00001-of-00004.safetensors",
664
+ "visual.blocks.4.mlp.fc2.weight": "model-00001-of-00004.safetensors",
665
+ "visual.blocks.4.norm1.bias": "model-00001-of-00004.safetensors",
666
+ "visual.blocks.4.norm1.weight": "model-00001-of-00004.safetensors",
667
+ "visual.blocks.4.norm2.bias": "model-00001-of-00004.safetensors",
668
+ "visual.blocks.4.norm2.weight": "model-00001-of-00004.safetensors",
669
+ "visual.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors",
670
+ "visual.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors",
671
+ "visual.blocks.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
672
+ "visual.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
673
+ "visual.blocks.5.mlp.fc1.bias": "model-00001-of-00004.safetensors",
674
+ "visual.blocks.5.mlp.fc1.weight": "model-00001-of-00004.safetensors",
675
+ "visual.blocks.5.mlp.fc2.bias": "model-00001-of-00004.safetensors",
676
+ "visual.blocks.5.mlp.fc2.weight": "model-00001-of-00004.safetensors",
677
+ "visual.blocks.5.norm1.bias": "model-00001-of-00004.safetensors",
678
+ "visual.blocks.5.norm1.weight": "model-00001-of-00004.safetensors",
679
+ "visual.blocks.5.norm2.bias": "model-00001-of-00004.safetensors",
680
+ "visual.blocks.5.norm2.weight": "model-00001-of-00004.safetensors",
681
+ "visual.blocks.6.attn.proj.bias": "model-00001-of-00004.safetensors",
682
+ "visual.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors",
683
+ "visual.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
684
+ "visual.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
685
+ "visual.blocks.6.mlp.fc1.bias": "model-00001-of-00004.safetensors",
686
+ "visual.blocks.6.mlp.fc1.weight": "model-00001-of-00004.safetensors",
687
+ "visual.blocks.6.mlp.fc2.bias": "model-00001-of-00004.safetensors",
688
+ "visual.blocks.6.mlp.fc2.weight": "model-00001-of-00004.safetensors",
689
+ "visual.blocks.6.norm1.bias": "model-00001-of-00004.safetensors",
690
+ "visual.blocks.6.norm1.weight": "model-00001-of-00004.safetensors",
691
+ "visual.blocks.6.norm2.bias": "model-00001-of-00004.safetensors",
692
+ "visual.blocks.6.norm2.weight": "model-00001-of-00004.safetensors",
693
+ "visual.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors",
694
+ "visual.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors",
695
+ "visual.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
696
+ "visual.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
697
+ "visual.blocks.7.mlp.fc1.bias": "model-00001-of-00004.safetensors",
698
+ "visual.blocks.7.mlp.fc1.weight": "model-00001-of-00004.safetensors",
699
+ "visual.blocks.7.mlp.fc2.bias": "model-00001-of-00004.safetensors",
700
+ "visual.blocks.7.mlp.fc2.weight": "model-00001-of-00004.safetensors",
701
+ "visual.blocks.7.norm1.bias": "model-00001-of-00004.safetensors",
702
+ "visual.blocks.7.norm1.weight": "model-00001-of-00004.safetensors",
703
+ "visual.blocks.7.norm2.bias": "model-00001-of-00004.safetensors",
704
+ "visual.blocks.7.norm2.weight": "model-00001-of-00004.safetensors",
705
+ "visual.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors",
706
+ "visual.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors",
707
+ "visual.blocks.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
708
+ "visual.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
709
+ "visual.blocks.8.mlp.fc1.bias": "model-00001-of-00004.safetensors",
710
+ "visual.blocks.8.mlp.fc1.weight": "model-00001-of-00004.safetensors",
711
+ "visual.blocks.8.mlp.fc2.bias": "model-00001-of-00004.safetensors",
712
+ "visual.blocks.8.mlp.fc2.weight": "model-00001-of-00004.safetensors",
713
+ "visual.blocks.8.norm1.bias": "model-00001-of-00004.safetensors",
714
+ "visual.blocks.8.norm1.weight": "model-00001-of-00004.safetensors",
715
+ "visual.blocks.8.norm2.bias": "model-00001-of-00004.safetensors",
716
+ "visual.blocks.8.norm2.weight": "model-00001-of-00004.safetensors",
717
+ "visual.blocks.9.attn.proj.bias": "model-00001-of-00004.safetensors",
718
+ "visual.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors",
719
+ "visual.blocks.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
720
+ "visual.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
721
+ "visual.blocks.9.mlp.fc1.bias": "model-00001-of-00004.safetensors",
722
+ "visual.blocks.9.mlp.fc1.weight": "model-00001-of-00004.safetensors",
723
+ "visual.blocks.9.mlp.fc2.bias": "model-00001-of-00004.safetensors",
724
+ "visual.blocks.9.mlp.fc2.weight": "model-00001-of-00004.safetensors",
725
+ "visual.blocks.9.norm1.bias": "model-00001-of-00004.safetensors",
726
+ "visual.blocks.9.norm1.weight": "model-00001-of-00004.safetensors",
727
+ "visual.blocks.9.norm2.bias": "model-00001-of-00004.safetensors",
728
+ "visual.blocks.9.norm2.weight": "model-00001-of-00004.safetensors",
729
+ "visual.merger.ln_q.bias": "model-00001-of-00004.safetensors",
730
+ "visual.merger.ln_q.weight": "model-00001-of-00004.safetensors",
731
+ "visual.merger.mlp.0.bias": "model-00001-of-00004.safetensors",
732
+ "visual.merger.mlp.0.weight": "model-00001-of-00004.safetensors",
733
+ "visual.merger.mlp.2.bias": "model-00001-of-00004.safetensors",
734
+ "visual.merger.mlp.2.weight": "model-00001-of-00004.safetensors",
735
+ "visual.patch_embed.proj.weight": "model-00001-of-00004.safetensors"
736
+ }
737
+ }
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": "Qwen2VLProcessor"
19
+ }
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ee51cbb5c5343cdaf9eb0e09d6969a52927117d55281de01777929090f4a664
3
+ size 14645
special_tokens_map.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|PROBLEM|>",
4
+ "<|/PROBLEM|>",
5
+ "<|CAPTION|>",
6
+ "<|/CAPTION|>",
7
+ "<|REASONING|>",
8
+ "<|/REASONING|>",
9
+ "<|OUTPUT|>",
10
+ "<|/OUTPUT|>"
11
+ ],
12
+ "eos_token": {
13
+ "content": "<|im_end|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "pad_token": {
20
+ "content": "<|endoftext|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ }
26
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:574df5ded264d77110fc157ae6957073e00e898e58ef20b648172a88851031df
3
+ size 11421881
tokenizer_config.json ADDED
@@ -0,0 +1,203 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "151646": {
29
+ "content": "<|object_ref_start|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "151647": {
37
+ "content": "<|object_ref_end|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "151648": {
45
+ "content": "<|box_start|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "151649": {
53
+ "content": "<|box_end|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "151650": {
61
+ "content": "<|quad_start|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "151651": {
69
+ "content": "<|quad_end|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "151652": {
77
+ "content": "<|vision_start|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "151653": {
85
+ "content": "<|vision_end|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "151654": {
93
+ "content": "<|vision_pad|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "151655": {
101
+ "content": "<|image_pad|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "151656": {
109
+ "content": "<|video_pad|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "151657": {
117
+ "content": "<|PROBLEM|>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "151658": {
125
+ "content": "<|/PROBLEM|>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "151659": {
133
+ "content": "<|CAPTION|>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "151660": {
141
+ "content": "<|/CAPTION|>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "151661": {
149
+ "content": "<|REASONING|>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "151662": {
157
+ "content": "<|/REASONING|>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "151663": {
165
+ "content": "<|OUTPUT|>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "151664": {
173
+ "content": "<|/OUTPUT|>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ }
180
+ },
181
+ "additional_special_tokens": [
182
+ "<|PROBLEM|>",
183
+ "<|/PROBLEM|>",
184
+ "<|CAPTION|>",
185
+ "<|/CAPTION|>",
186
+ "<|REASONING|>",
187
+ "<|/REASONING|>",
188
+ "<|OUTPUT|>",
189
+ "<|/OUTPUT|>"
190
+ ],
191
+ "bos_token": null,
192
+ "clean_up_tokenization_spaces": false,
193
+ "eos_token": "<|im_end|>",
194
+ "errors": "replace",
195
+ "extra_special_tokens": {},
196
+ "model_max_length": 32768,
197
+ "pad_token": "<|endoftext|>",
198
+ "padding_side": "left",
199
+ "processor_class": "Qwen2VLProcessor",
200
+ "split_special_tokens": false,
201
+ "tokenizer_class": "Qwen2Tokenizer",
202
+ "unk_token": null
203
+ }
video_preprocessor_config.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_valid_kwargs_names": [
3
+ "do_convert_rgb",
4
+ "do_resize",
5
+ "size",
6
+ "size_divisor",
7
+ "default_to_square",
8
+ "resample",
9
+ "do_rescale",
10
+ "rescale_factor",
11
+ "do_normalize",
12
+ "image_mean",
13
+ "image_std",
14
+ "do_pad",
15
+ "do_center_crop",
16
+ "crop_size",
17
+ "data_format",
18
+ "input_data_format",
19
+ "device",
20
+ "min_pixels",
21
+ "max_pixels",
22
+ "patch_size",
23
+ "temporal_patch_size",
24
+ "merge_size"
25
+ ],
26
+ "crop_size": null,
27
+ "data_format": "channels_first",
28
+ "default_to_square": true,
29
+ "device": null,
30
+ "do_center_crop": null,
31
+ "do_convert_rgb": true,
32
+ "do_normalize": true,
33
+ "do_pad": null,
34
+ "do_rescale": true,
35
+ "do_resize": true,
36
+ "image_mean": [
37
+ 0.48145466,
38
+ 0.4578275,
39
+ 0.40821073
40
+ ],
41
+ "image_processor_type": "Qwen2VLImageProcessor",
42
+ "image_std": [
43
+ 0.26862954,
44
+ 0.26130258,
45
+ 0.27577711
46
+ ],
47
+ "input_data_format": null,
48
+ "max_pixels": 12845056,
49
+ "merge_size": 2,
50
+ "min_pixels": 3136,
51
+ "model_valid_processing_keys": [
52
+ "do_convert_rgb",
53
+ "do_resize",
54
+ "size",
55
+ "size_divisor",
56
+ "default_to_square",
57
+ "resample",
58
+ "do_rescale",
59
+ "rescale_factor",
60
+ "do_normalize",
61
+ "image_mean",
62
+ "image_std",
63
+ "do_pad",
64
+ "do_center_crop",
65
+ "crop_size",
66
+ "data_format",
67
+ "input_data_format",
68
+ "device",
69
+ "min_pixels",
70
+ "max_pixels",
71
+ "patch_size",
72
+ "temporal_patch_size",
73
+ "merge_size"
74
+ ],
75
+ "patch_size": 14,
76
+ "processor_class": "Qwen2VLProcessor",
77
+ "resample": 3,
78
+ "rescale_factor": 0.00392156862745098,
79
+ "size": {
80
+ "longest_edge": 12845056,
81
+ "shortest_edge": 3136
82
+ },
83
+ "size_divisor": null,
84
+ "temporal_patch_size": 2,
85
+ "video_processor_type": "Qwen2VLVideoProcessor"
86
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff