Hugging Face's logo

ndhieu2oo3
/
Doc2Bit-VL-8B

Image-to-Text
Safetensors
English
Vietnamese
qwen2_5_vl
vision-language
document-ai
vlm
ocr
Model card Files
xet
 Community
rabbit commited on
Commit
10e013e
·
1 Parent(s): 00a2227

Initial upload Doc2Bit-VL-7B (LFS)

Browse files
Files changed (21) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +24 -0
  3. args.json +330 -0
  4. chat_template.jinja +7 -0
  5. config.json +136 -0
  6. generation_config.json +6 -0
  7. merges.txt +0 -0
  8. model-00001-of-00007.safetensors +3 -0
  9. model-00002-of-00007.safetensors +3 -0
  10. model-00003-of-00007.safetensors +3 -0
  11. model-00004-of-00007.safetensors +3 -0
  12. model-00005-of-00007.safetensors +3 -0
  13. model-00006-of-00007.safetensors +3 -0
  14. model-00007-of-00007.safetensors +3 -0
  15. model.safetensors.index.json +737 -0
  16. preprocessor_config.json +36 -0
  17. special_tokens_map.json +31 -0
  18. tokenizer.json +3 -0
  19. tokenizer_config.json +209 -0
  20. video_preprocessor_config.json +45 -0
  21. 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
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
args.json ADDED
@@ -0,0 +1,330 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model": "./MODEL/vision_matters_7b",
3
+ "model_type": "qwen2_5_vl",
4
+ "model_revision": null,
5
+ "task_type": "causal_lm",
6
+ "torch_dtype": "float32",
7
+ "attn_impl": null,
8
+ "num_labels": null,
9
+ "problem_type": null,
10
+ "rope_scaling": null,
11
+ "device_map": null,
12
+ "max_memory": {},
13
+ "local_repo_path": null,
14
+ "template": "qwen2_5_vl",
15
+ "system": null,
16
+ "max_length": 4092,
17
+ "truncation_strategy": "delete",
18
+ "max_pixels": null,
19
+ "tools_prompt": "react_en",
20
+ "norm_bbox": null,
21
+ "response_prefix": null,
22
+ "padding_side": "right",
23
+ "loss_scale": "default",
24
+ "sequence_parallel_size": 1,
25
+ "use_chat_template": true,
26
+ "template_backend": "swift",
27
+ "dataset": [
28
+ "./DATA/20250618_data_noibo_4541/train_1col_22151_vm_format.json",
29
+ "./DATA/20250711_data_gen_5317/labels_1col_16885_converted.json",
30
+ "./DATA/20250718_data_gtgt_eng_127/hd-gtgt-eng-train-1col-880_converted.json",
31
+ "./DATA/20250813_FF_8/train_1col_84_vm_format.json",
32
+ "./DATA/20250804_viet_receipt_2034/viet_receipt_2f_3976.json",
33
+ "./DATA/20250804_viet_receipt_2034/viet_receipt_2033.json",
34
+ "./DATA/20250806_GROUP_IMAGE_TABLE_GHTK/group_image_table_ghtk_singleform_3991.json"
35
+ ],
36
+ "val_dataset": [],
37
+ "split_dataset_ratio": 0.01,
38
+ "data_seed": 42,
39
+ "dataset_num_proc": 1,
40
+ "streaming": false,
41
+ "enable_cache": false,
42
+ "download_mode": "reuse_dataset_if_exists",
43
+ "columns": {},
44
+ "strict": false,
45
+ "remove_unused_columns": true,
46
+ "model_name": [
47
+ null,
48
+ null
49
+ ],
50
+ "model_author": [
51
+ null,
52
+ null
53
+ ],
54
+ "custom_dataset_info": [],
55
+ "quant_method": null,
56
+ "quant_bits": null,
57
+ "hqq_axis": null,
58
+ "bnb_4bit_compute_dtype": "float32",
59
+ "bnb_4bit_quant_type": "nf4",
60
+ "bnb_4bit_use_double_quant": true,
61
+ "bnb_4bit_quant_storage": null,
62
+ "max_new_tokens": 64,
63
+ "temperature": 0.0,
64
+ "top_k": null,
65
+ "top_p": null,
66
+ "repetition_penalty": null,
67
+ "num_beams": 1,
68
+ "stream": false,
69
+ "stop_words": [],
70
+ "logprobs": false,
71
+ "top_logprobs": null,
72
+ "ckpt_dir": null,
73
+ "load_dataset_config": null,
74
+ "lora_modules": [],
75
+ "tuner_backend": "peft",
76
+ "train_type": "lora",
77
+ "adapters": [],
78
+ "external_plugins": [],
79
+ "seed": 42,
80
+ "model_kwargs": {},
81
+ "load_args": false,
82
+ "load_data_args": false,
83
+ "use_hf": false,
84
+ "hub_token": null,
85
+ "custom_register_path": [],
86
+ "ignore_args_error": false,
87
+ "use_swift_lora": false,
88
+ "output_dir": "/root/notebooks/hieund244/Vision-Matters/20250908_train_50k_allinone/v0-20250908-063809",
89
+ "overwrite_output_dir": false,
90
+ "do_train": false,
91
+ "do_eval": false,
92
+ "do_predict": false,
93
+ "eval_strategy": "steps",
94
+ "prediction_loss_only": false,
95
+ "per_device_train_batch_size": 1,
96
+ "per_device_eval_batch_size": 1,
97
+ "per_gpu_train_batch_size": null,
98
+ "per_gpu_eval_batch_size": null,
99
+ "gradient_accumulation_steps": 2,
100
+ "eval_accumulation_steps": null,
101
+ "eval_delay": 0,
102
+ "torch_empty_cache_steps": null,
103
+ "learning_rate": 0.0001,
104
+ "weight_decay": 0.1,
105
+ "adam_beta1": 0.9,
106
+ "adam_beta2": 0.95,
107
+ "adam_epsilon": 1e-08,
108
+ "max_grad_norm": 1.0,
109
+ "num_train_epochs": 1.0,
110
+ "max_steps": -1,
111
+ "lr_scheduler_type": "cosine",
112
+ "lr_scheduler_kwargs": null,
113
+ "warmup_ratio": 0.0,
114
+ "warmup_steps": 0,
115
+ "log_level": "passive",
116
+ "log_level_replica": "warning",
117
+ "log_on_each_node": true,
118
+ "logging_dir": "/root/notebooks/hieund244/Vision-Matters/20250908_train_50k_allinone/v0-20250908-063809/runs",
119
+ "logging_strategy": "steps",
120
+ "logging_first_step": true,
121
+ "logging_steps": 5,
122
+ "logging_nan_inf_filter": true,
123
+ "save_strategy": "steps",
124
+ "save_steps": 500,
125
+ "save_total_limit": null,
126
+ "save_safetensors": true,
127
+ "save_on_each_node": false,
128
+ "save_only_model": false,
129
+ "restore_callback_states_from_checkpoint": false,
130
+ "no_cuda": false,
131
+ "use_cpu": false,
132
+ "use_mps_device": false,
133
+ "jit_mode_eval": false,
134
+ "use_ipex": false,
135
+ "bf16": false,
136
+ "fp16": true,
137
+ "fp16_opt_level": "O1",
138
+ "half_precision_backend": "auto",
139
+ "bf16_full_eval": false,
140
+ "fp16_full_eval": false,
141
+ "tf32": null,
142
+ "local_rank": -1,
143
+ "ddp_backend": null,
144
+ "tpu_num_cores": null,
145
+ "tpu_metrics_debug": false,
146
+ "debug": null,
147
+ "dataloader_drop_last": false,
148
+ "eval_steps": 500,
149
+ "dataloader_num_workers": 0,
150
+ "dataloader_prefetch_factor": null,
151
+ "past_index": -1,
152
+ "run_name": null,
153
+ "disable_tqdm": null,
154
+ "label_names": null,
155
+ "load_best_model_at_end": false,
156
+ "metric_for_best_model": "loss",
157
+ "greater_is_better": false,
158
+ "ignore_data_skip": false,
159
+ "fsdp": "",
160
+ "fsdp_min_num_params": 0,
161
+ "fsdp_config": null,
162
+ "fsdp_transformer_layer_cls_to_wrap": null,
163
+ "accelerator_config": {
164
+ "dispatch_batches": false
165
+ },
166
+ "deepspeed": null,
167
+ "label_smoothing_factor": 0.0,
168
+ "optim": "adamw_torch",
169
+ "optim_args": null,
170
+ "adafactor": false,
171
+ "group_by_length": false,
172
+ "length_column_name": "length",
173
+ "report_to": [
174
+ "tensorboard"
175
+ ],
176
+ "ddp_find_unused_parameters": null,
177
+ "ddp_bucket_cap_mb": null,
178
+ "ddp_broadcast_buffers": null,
179
+ "dataloader_pin_memory": true,
180
+ "dataloader_persistent_workers": false,
181
+ "skip_memory_metrics": true,
182
+ "use_legacy_prediction_loop": false,
183
+ "push_to_hub": false,
184
+ "resume_from_checkpoint": null,
185
+ "hub_model_id": null,
186
+ "hub_strategy": "every_save",
187
+ "hub_private_repo": null,
188
+ "hub_always_push": false,
189
+ "gradient_checkpointing": true,
190
+ "gradient_checkpointing_kwargs": null,
191
+ "include_inputs_for_metrics": false,
192
+ "include_for_metrics": [],
193
+ "eval_do_concat_batches": true,
194
+ "fp16_backend": "auto",
195
+ "push_to_hub_model_id": null,
196
+ "push_to_hub_organization": null,
197
+ "push_to_hub_token": null,
198
+ "mp_parameters": "",
199
+ "auto_find_batch_size": false,
200
+ "full_determinism": false,
201
+ "torchdynamo": null,
202
+ "ray_scope": "last",
203
+ "ddp_timeout": 1800,
204
+ "torch_compile": false,
205
+ "torch_compile_backend": null,
206
+ "torch_compile_mode": null,
207
+ "include_tokens_per_second": false,
208
+ "include_num_input_tokens_seen": false,
209
+ "neftune_noise_alpha": null,
210
+ "optim_target_modules": null,
211
+ "batch_eval_metrics": false,
212
+ "eval_on_start": false,
213
+ "use_liger_kernel": false,
214
+ "eval_use_gather_object": false,
215
+ "average_tokens_across_devices": false,
216
+ "sortish_sampler": false,
217
+ "predict_with_generate": false,
218
+ "generation_max_length": null,
219
+ "generation_num_beams": null,
220
+ "generation_config": null,
221
+ "check_model": true,
222
+ "acc_strategy": "token",
223
+ "train_sampler_random": true,
224
+ "metric_warmup_step": 0,
225
+ "fsdp_num": 1,
226
+ "acc_steps": 1,
227
+ "eval_use_evalscope": false,
228
+ "eval_datasets": [],
229
+ "eval_limit": null,
230
+ "eval_datasets_args": null,
231
+ "eval_generation_config": null,
232
+ "freeze_parameters": [
233
+ "visual",
234
+ "visual.merger"
235
+ ],
236
+ "freeze_parameters_ratio": 0.0,
237
+ "trainable_parameters": [],
238
+ "freeze_llm": false,
239
+ "freeze_vit": true,
240
+ "freeze_aligner": true,
241
+ "target_modules": [
242
+ "all-linear"
243
+ ],
244
+ "target_regex": null,
245
+ "modules_to_save": [],
246
+ "lora_rank": 8,
247
+ "lora_alpha": 32,
248
+ "lora_dropout": 0.05,
249
+ "lora_bias": "none",
250
+ "lora_dtype": null,
251
+ "lorap_lr_ratio": null,
252
+ "use_rslora": false,
253
+ "use_dora": false,
254
+ "lora_ga_batch_size": 2,
255
+ "lora_ga_iters": 2,
256
+ "lora_ga_max_length": 1024,
257
+ "lora_ga_direction": "ArB2r",
258
+ "lora_ga_scale": "stable",
259
+ "lora_ga_stable_gamma": 16,
260
+ "init_weights": true,
261
+ "fourier_n_frequency": 2000,
262
+ "fourier_scaling": 300.0,
263
+ "boft_block_size": 4,
264
+ "boft_block_num": 0,
265
+ "boft_n_butterfly_factor": 1,
266
+ "boft_dropout": 0.0,
267
+ "vera_rank": 256,
268
+ "vera_projection_prng_key": 0,
269
+ "vera_dropout": 0.0,
270
+ "vera_d_initial": 0.1,
271
+ "adapter_act": "gelu",
272
+ "adapter_length": 128,
273
+ "use_galore": false,
274
+ "galore_target_modules": null,
275
+ "galore_rank": 128,
276
+ "galore_update_proj_gap": 50,
277
+ "galore_scale": 1.0,
278
+ "galore_proj_type": "std",
279
+ "galore_optim_per_parameter": false,
280
+ "galore_with_embedding": false,
281
+ "galore_quantization": false,
282
+ "galore_proj_quant": false,
283
+ "galore_proj_bits": 4,
284
+ "galore_proj_group_size": 256,
285
+ "galore_cos_threshold": 0.4,
286
+ "galore_gamma_proj": 2,
287
+ "galore_queue_size": 5,
288
+ "adalora_target_r": 8,
289
+ "adalora_init_r": 12,
290
+ "adalora_tinit": 0,
291
+ "adalora_tfinal": 0,
292
+ "adalora_deltaT": 1,
293
+ "adalora_beta1": 0.85,
294
+ "adalora_beta2": 0.85,
295
+ "adalora_orth_reg_weight": 0.5,
296
+ "llamapro_num_new_blocks": 4,
297
+ "llamapro_num_groups": null,
298
+ "lisa_activated_layers": 0,
299
+ "lisa_step_interval": 20,
300
+ "reft_layer_key": null,
301
+ "reft_layers": null,
302
+ "reft_rank": 4,
303
+ "reft_intervention_type": "LoreftIntervention",
304
+ "reft_args": null,
305
+ "use_liger": false,
306
+ "swanlab_token": null,
307
+ "swanlab_project": null,
308
+ "swanlab_workspace": null,
309
+ "swanlab_exp_name": null,
310
+ "swanlab_mode": "cloud",
311
+ "add_version": true,
312
+ "resume_only_model": false,
313
+ "create_checkpoint_symlink": false,
314
+ "packing": false,
315
+ "lazy_tokenize": true,
316
+ "loss_type": null,
317
+ "optimizer": null,
318
+ "metric": null,
319
+ "zero_hpz_partition_size": null,
320
+ "rank": -1,
321
+ "global_world_size": 1,
322
+ "local_world_size": 1,
323
+ "model_suffix": "vision_matters_7b",
324
+ "model_info": "ModelInfo(model_type='qwen2_5_vl', model_dir='/root/notebooks/hieund244/Vision-Matters/MODEL/vision_matters_7b', torch_dtype=torch.float32, max_model_len=128000, 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)",
325
+ "model_meta": "ModelMeta(model_type='qwen2_5_vl', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-VL-3B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-3B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-7B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-7B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-32B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-32B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-72B-Instruct', hf_model_id='Qwen/Qwen2.5-VL-72B-Instruct', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2.5-VL-3B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-3B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-7B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-7B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2.5-VL-72B-Instruct-AWQ', hf_model_id='Qwen/Qwen2.5-VL-72B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen2_5_vl', get_function=<function get_model_tokenizer_qwen2_5_vl at 0x7ffdbe45c790>, model_arch='qwen2_vl', architectures=['Qwen2_5_VLForConditionalGeneration'], additional_saved_files=[], torch_dtype=None, is_multimodal=True, is_reward=False, task_type=None, ignore_patterns=[], requires=['transformers>=4.49', 'qwen_vl_utils>=0.0.6', 'decord'], tags=['vision', 'video'])",
326
+ "model_dir": "/root/notebooks/hieund244/Vision-Matters/MODEL/vision_matters_7b",
327
+ "hub": "<class 'swift.hub.hub.MSHub'>",
328
+ "evaluation_strategy": "steps",
329
+ "training_args": "Seq2SeqTrainingArguments(output_dir='/root/notebooks/hieund244/Vision-Matters/20250908_train_50k_allinone/v0-20250908-063809', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=<IntervalStrategy.STEPS: 'steps'>, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=2, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=0.0001, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=1.0, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.0, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/root/notebooks/hieund244/Vision-Matters/20250908_train_50k_allinone/v0-20250908-063809/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=500, save_total_limit=None, 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=False, fp16=True, 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=500, dataloader_num_workers=0, dataloader_prefetch_factor=None, past_index=-1, run_name='/root/notebooks/hieund244/Vision-Matters/20250908_train_50k_allinone/v0-20250908-063809', 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=1800, 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, check_model=True, acc_strategy='token', train_sampler_random=True, metric_warmup_step=0, fsdp_num=1, acc_steps=1, eval_use_evalscope=False, eval_datasets=[], eval_limit=None, eval_datasets_args=None, eval_generation_config=None, train_type='lora', optimizer=None, local_repo_path=None, galore_config=None)"
330
+ }
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 +1,136 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2_5_VLForConditionalGeneration"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "eos_token_id": 151645,
7
+ "hidden_act": "silu",
8
+ "hidden_size": 3584,
9
+ "image_token_id": 151655,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 18944,
12
+ "max_position_embeddings": 128000,
13
+ "max_window_layers": 28,
14
+ "model_type": "qwen2_5_vl",
15
+ "num_attention_heads": 28,
16
+ "num_hidden_layers": 28,
17
+ "num_key_value_heads": 4,
18
+ "pad_token_id": 151643,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_scaling": {
21
+ "mrope_section": [
22
+ 16,
23
+ 24,
24
+ 24
25
+ ],
26
+ "rope_type": "default",
27
+ "type": "default"
28
+ },
29
+ "rope_theta": 1000000.0,
30
+ "sliding_window": 32768,
31
+ "text_config": {
32
+ "architectures": [
33
+ "Qwen2_5_VLForConditionalGeneration"
34
+ ],
35
+ "attention_dropout": 0.0,
36
+ "eos_token_id": 151645,
37
+ "hidden_act": "silu",
38
+ "hidden_size": 3584,
39
+ "image_token_id": null,
40
+ "initializer_range": 0.02,
41
+ "intermediate_size": 18944,
42
+ "layer_types": [
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention",
51
+ "full_attention",
52
+ "full_attention",
53
+ "full_attention",
54
+ "full_attention",
55
+ "full_attention",
56
+ "full_attention",
57
+ "full_attention",
58
+ "full_attention",
59
+ "full_attention",
60
+ "full_attention",
61
+ "full_attention",
62
+ "full_attention",
63
+ "full_attention",
64
+ "full_attention",
65
+ "full_attention",
66
+ "full_attention",
67
+ "full_attention",
68
+ "full_attention",
69
+ "full_attention",
70
+ "full_attention"
71
+ ],
72
+ "max_position_embeddings": 128000,
73
+ "max_window_layers": 28,
74
+ "model_type": "qwen2_5_vl_text",
75
+ "num_attention_heads": 28,
76
+ "num_hidden_layers": 28,
77
+ "num_key_value_heads": 4,
78
+ "pad_token_id": 151643,
79
+ "rms_norm_eps": 1e-06,
80
+ "rope_scaling": {
81
+ "mrope_section": [
82
+ 16,
83
+ 24,
84
+ 24
85
+ ],
86
+ "rope_type": "default",
87
+ "type": "default"
88
+ },
89
+ "rope_theta": 1000000.0,
90
+ "sliding_window": null,
91
+ "torch_dtype": "float32",
92
+ "use_cache": true,
93
+ "use_sliding_window": false,
94
+ "video_token_id": null,
95
+ "vision_end_token_id": 151653,
96
+ "vision_start_token_id": 151652,
97
+ "vision_token_id": 151654,
98
+ "vocab_size": 152064
99
+ },
100
+ "tie_word_embeddings": false,
101
+ "torch_dtype": "float32",
102
+ "transformers_version": "4.55.0.dev0",
103
+ "use_cache": true,
104
+ "use_sliding_window": false,
105
+ "video_token_id": 151656,
106
+ "vision_config": {
107
+ "depth": 32,
108
+ "fullatt_block_indexes": [
109
+ 7,
110
+ 15,
111
+ 23,
112
+ 31
113
+ ],
114
+ "hidden_act": "silu",
115
+ "hidden_size": 1280,
116
+ "in_channels": 3,
117
+ "in_chans": 3,
118
+ "initializer_range": 0.02,
119
+ "intermediate_size": 3420,
120
+ "model_type": "qwen2_5_vl",
121
+ "num_heads": 16,
122
+ "out_hidden_size": 3584,
123
+ "pad_token_id": 151643,
124
+ "patch_size": 14,
125
+ "spatial_merge_size": 2,
126
+ "spatial_patch_size": 14,
127
+ "temporal_patch_size": 2,
128
+ "tokens_per_second": 2,
129
+ "torch_dtype": "float32",
130
+ "window_size": 112
131
+ },
132
+ "vision_end_token_id": 151653,
133
+ "vision_start_token_id": 151652,
134
+ "vision_token_id": 151654,
135
+ "vocab_size": 152064
136
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": 151645,
4
+ "pad_token_id": 151643,
5
+ "transformers_version": "4.55.0.dev0"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36fa92b82452da892adfa951220fc7ce480cb720df5020056d5a1d2150fa6870
3
+ size 4952311608
model-00002-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cff405eba1c75f4a5d5f78bf4f642a74e5a9bb6c0ea52d5ae021c78a78ca9ad
3
+ size 4984124272
model-00003-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a4b47b3bab1c90f3c4e6bd383c002a999e981a598e2f445e5e3cab803e7a161
3
+ size 4932743936
model-00004-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cdca7ed9a5d7b51c3123146c1e1ab78502d5a82d5d1fb6337ef1bbb5454d66b
3
+ size 4998852296
model-00005-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c184b1d3cca040ea80c9d546cc3345e5f3a32bb2d84da3f8af43d09176072e4d
3
+ size 4984124336
model-00006-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7af8e85e1f54f3382739b278d870b49ccdffda087aa8ff7f8b93880fda3b9554
3
+ size 4932743992
model-00007-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcbd028f3e59a23f38657319627efc1057c19e64638507e87871b1dc38b289f6
3
+ size 3383846800
model.safetensors.index.json ADDED
@@ -0,0 +1,737 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 8292166656,
4
+ "total_size": 33168666624
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "model-00007-of-00007.safetensors",
8
+ "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model-00002-of-00007.safetensors",
10
+ "model.layers.0.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
11
+ "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
12
+ "model.layers.0.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
13
+ "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
14
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
15
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
16
+ "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
17
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
18
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
19
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
20
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
21
+ "model.layers.1.input_layernorm.weight": "model-00002-of-00007.safetensors",
22
+ "model.layers.1.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
23
+ "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
24
+ "model.layers.1.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
25
+ "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
26
+ "model.layers.1.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
27
+ "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
28
+ "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
29
+ "model.layers.1.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
30
+ "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
31
+ "model.layers.1.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
32
+ "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
33
+ "model.layers.10.input_layernorm.weight": "model-00004-of-00007.safetensors",
34
+ "model.layers.10.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
35
+ "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
36
+ "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
37
+ "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
38
+ "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
39
+ "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
40
+ "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
41
+ "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
42
+ "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
43
+ "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
44
+ "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
45
+ "model.layers.11.input_layernorm.weight": "model-00004-of-00007.safetensors",
46
+ "model.layers.11.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
47
+ "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
48
+ "model.layers.11.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
49
+ "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
50
+ "model.layers.11.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
51
+ "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
52
+ "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
53
+ "model.layers.11.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
54
+ "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
55
+ "model.layers.11.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
56
+ "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
57
+ "model.layers.12.input_layernorm.weight": "model-00004-of-00007.safetensors",
58
+ "model.layers.12.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
59
+ "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
60
+ "model.layers.12.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
61
+ "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
62
+ "model.layers.12.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
63
+ "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
64
+ "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
65
+ "model.layers.12.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
66
+ "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
67
+ "model.layers.12.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
68
+ "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
69
+ "model.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors",
70
+ "model.layers.13.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
71
+ "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
72
+ "model.layers.13.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
73
+ "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
74
+ "model.layers.13.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
75
+ "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
76
+ "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
77
+ "model.layers.13.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
78
+ "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
79
+ "model.layers.13.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
80
+ "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
81
+ "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
82
+ "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
83
+ "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
84
+ "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
85
+ "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
86
+ "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
87
+ "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
88
+ "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
89
+ "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
90
+ "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
91
+ "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
92
+ "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
93
+ "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
94
+ "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
95
+ "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
96
+ "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
97
+ "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
98
+ "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
99
+ "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
100
+ "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
101
+ "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
102
+ "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
103
+ "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
104
+ "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
105
+ "model.layers.16.input_layernorm.weight": "model-00005-of-00007.safetensors",
106
+ "model.layers.16.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
107
+ "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
108
+ "model.layers.16.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
109
+ "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
110
+ "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
111
+ "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
112
+ "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
113
+ "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
114
+ "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
115
+ "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
116
+ "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
117
+ "model.layers.17.input_layernorm.weight": "model-00005-of-00007.safetensors",
118
+ "model.layers.17.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
119
+ "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
120
+ "model.layers.17.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
121
+ "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
122
+ "model.layers.17.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
123
+ "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
124
+ "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
125
+ "model.layers.17.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
126
+ "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
127
+ "model.layers.17.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
128
+ "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
129
+ "model.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors",
130
+ "model.layers.18.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
131
+ "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
132
+ "model.layers.18.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
133
+ "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
134
+ "model.layers.18.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
135
+ "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
136
+ "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
137
+ "model.layers.18.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
138
+ "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
139
+ "model.layers.18.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
140
+ "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
141
+ "model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
142
+ "model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
143
+ "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
144
+ "model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
145
+ "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
146
+ "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
147
+ "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
148
+ "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
149
+ "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
150
+ "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
151
+ "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
152
+ "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
153
+ "model.layers.2.input_layernorm.weight": "model-00002-of-00007.safetensors",
154
+ "model.layers.2.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
155
+ "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
156
+ "model.layers.2.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
157
+ "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
158
+ "model.layers.2.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
159
+ "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
160
+ "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
161
+ "model.layers.2.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
162
+ "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
163
+ "model.layers.2.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
164
+ "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
165
+ "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
166
+ "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
167
+ "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
168
+ "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
169
+ "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
170
+ "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
171
+ "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
172
+ "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
173
+ "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
174
+ "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
175
+ "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
176
+ "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
177
+ "model.layers.21.input_layernorm.weight": "model-00006-of-00007.safetensors",
178
+ "model.layers.21.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
179
+ "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
180
+ "model.layers.21.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
181
+ "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
182
+ "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
183
+ "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
184
+ "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
185
+ "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
186
+ "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
187
+ "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
188
+ "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
189
+ "model.layers.22.input_layernorm.weight": "model-00006-of-00007.safetensors",
190
+ "model.layers.22.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
191
+ "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
192
+ "model.layers.22.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
193
+ "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
194
+ "model.layers.22.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
195
+ "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
196
+ "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
197
+ "model.layers.22.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
198
+ "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
199
+ "model.layers.22.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
200
+ "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
201
+ "model.layers.23.input_layernorm.weight": "model-00006-of-00007.safetensors",
202
+ "model.layers.23.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
203
+ "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
204
+ "model.layers.23.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
205
+ "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
206
+ "model.layers.23.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
207
+ "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
208
+ "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
209
+ "model.layers.23.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
210
+ "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
211
+ "model.layers.23.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
212
+ "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
213
+ "model.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
214
+ "model.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
215
+ "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
216
+ "model.layers.24.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
217
+ "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
218
+ "model.layers.24.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
219
+ "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
220
+ "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
221
+ "model.layers.24.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
222
+ "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
223
+ "model.layers.24.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
224
+ "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
225
+ "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
226
+ "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
227
+ "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
228
+ "model.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
229
+ "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
230
+ "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
231
+ "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
232
+ "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
233
+ "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
234
+ "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
235
+ "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
236
+ "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
237
+ "model.layers.26.input_layernorm.weight": "model-00007-of-00007.safetensors",
238
+ "model.layers.26.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
239
+ "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
240
+ "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
241
+ "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
242
+ "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
243
+ "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
244
+ "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
245
+ "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
246
+ "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
247
+ "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
248
+ "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
249
+ "model.layers.27.input_layernorm.weight": "model-00007-of-00007.safetensors",
250
+ "model.layers.27.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
251
+ "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
252
+ "model.layers.27.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
253
+ "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
254
+ "model.layers.27.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
255
+ "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
256
+ "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
257
+ "model.layers.27.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
258
+ "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
259
+ "model.layers.27.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
260
+ "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
261
+ "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
262
+ "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
263
+ "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
264
+ "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
265
+ "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
266
+ "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
267
+ "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
268
+ "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
269
+ "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
270
+ "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
271
+ "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
272
+ "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
273
+ "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
274
+ "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
275
+ "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
276
+ "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
277
+ "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
278
+ "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
279
+ "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
280
+ "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
281
+ "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
282
+ "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
283
+ "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
284
+ "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
285
+ "model.layers.5.input_layernorm.weight": "model-00003-of-00007.safetensors",
286
+ "model.layers.5.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
287
+ "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
288
+ "model.layers.5.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
289
+ "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
290
+ "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
291
+ "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
292
+ "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
293
+ "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
294
+ "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
295
+ "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
296
+ "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
297
+ "model.layers.6.input_layernorm.weight": "model-00003-of-00007.safetensors",
298
+ "model.layers.6.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
299
+ "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
300
+ "model.layers.6.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
301
+ "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
302
+ "model.layers.6.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
303
+ "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
304
+ "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
305
+ "model.layers.6.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
306
+ "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
307
+ "model.layers.6.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
308
+ "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
309
+ "model.layers.7.input_layernorm.weight": "model-00003-of-00007.safetensors",
310
+ "model.layers.7.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
311
+ "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
312
+ "model.layers.7.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
313
+ "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
314
+ "model.layers.7.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
315
+ "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
316
+ "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
317
+ "model.layers.7.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
318
+ "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
319
+ "model.layers.7.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
320
+ "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
321
+ "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
322
+ "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
323
+ "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
324
+ "model.layers.8.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
325
+ "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
326
+ "model.layers.8.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
327
+ "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
328
+ "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
329
+ "model.layers.8.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
330
+ "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
331
+ "model.layers.8.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
332
+ "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
333
+ "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
334
+ "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
335
+ "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
336
+ "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
337
+ "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
338
+ "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
339
+ "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
340
+ "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
341
+ "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
342
+ "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
343
+ "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
344
+ "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
345
+ "model.norm.weight": "model-00007-of-00007.safetensors",
346
+ "visual.blocks.0.attn.proj.bias": "model-00001-of-00007.safetensors",
347
+ "visual.blocks.0.attn.proj.weight": "model-00001-of-00007.safetensors",
348
+ "visual.blocks.0.attn.qkv.bias": "model-00001-of-00007.safetensors",
349
+ "visual.blocks.0.attn.qkv.weight": "model-00001-of-00007.safetensors",
350
+ "visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
351
+ "visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
352
+ "visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
353
+ "visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
354
+ "visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
355
+ "visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
356
+ "visual.blocks.0.norm1.weight": "model-00001-of-00007.safetensors",
357
+ "visual.blocks.0.norm2.weight": "model-00001-of-00007.safetensors",
358
+ "visual.blocks.1.attn.proj.bias": "model-00001-of-00007.safetensors",
359
+ "visual.blocks.1.attn.proj.weight": "model-00001-of-00007.safetensors",
360
+ "visual.blocks.1.attn.qkv.bias": "model-00001-of-00007.safetensors",
361
+ "visual.blocks.1.attn.qkv.weight": "model-00001-of-00007.safetensors",
362
+ "visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
363
+ "visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
364
+ "visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
365
+ "visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
366
+ "visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
367
+ "visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
368
+ "visual.blocks.1.norm1.weight": "model-00001-of-00007.safetensors",
369
+ "visual.blocks.1.norm2.weight": "model-00001-of-00007.safetensors",
370
+ "visual.blocks.10.attn.proj.bias": "model-00001-of-00007.safetensors",
371
+ "visual.blocks.10.attn.proj.weight": "model-00001-of-00007.safetensors",
372
+ "visual.blocks.10.attn.qkv.bias": "model-00001-of-00007.safetensors",
373
+ "visual.blocks.10.attn.qkv.weight": "model-00001-of-00007.safetensors",
374
+ "visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
375
+ "visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
376
+ "visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
377
+ "visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
378
+ "visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
379
+ "visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
380
+ "visual.blocks.10.norm1.weight": "model-00001-of-00007.safetensors",
381
+ "visual.blocks.10.norm2.weight": "model-00001-of-00007.safetensors",
382
+ "visual.blocks.11.attn.proj.bias": "model-00001-of-00007.safetensors",
383
+ "visual.blocks.11.attn.proj.weight": "model-00001-of-00007.safetensors",
384
+ "visual.blocks.11.attn.qkv.bias": "model-00001-of-00007.safetensors",
385
+ "visual.blocks.11.attn.qkv.weight": "model-00001-of-00007.safetensors",
386
+ "visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
387
+ "visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
388
+ "visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
389
+ "visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
390
+ "visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
391
+ "visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
392
+ "visual.blocks.11.norm1.weight": "model-00001-of-00007.safetensors",
393
+ "visual.blocks.11.norm2.weight": "model-00001-of-00007.safetensors",
394
+ "visual.blocks.12.attn.proj.bias": "model-00001-of-00007.safetensors",
395
+ "visual.blocks.12.attn.proj.weight": "model-00001-of-00007.safetensors",
396
+ "visual.blocks.12.attn.qkv.bias": "model-00001-of-00007.safetensors",
397
+ "visual.blocks.12.attn.qkv.weight": "model-00001-of-00007.safetensors",
398
+ "visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
399
+ "visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
400
+ "visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
401
+ "visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
402
+ "visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
403
+ "visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
404
+ "visual.blocks.12.norm1.weight": "model-00001-of-00007.safetensors",
405
+ "visual.blocks.12.norm2.weight": "model-00001-of-00007.safetensors",
406
+ "visual.blocks.13.attn.proj.bias": "model-00001-of-00007.safetensors",
407
+ "visual.blocks.13.attn.proj.weight": "model-00001-of-00007.safetensors",
408
+ "visual.blocks.13.attn.qkv.bias": "model-00001-of-00007.safetensors",
409
+ "visual.blocks.13.attn.qkv.weight": "model-00001-of-00007.safetensors",
410
+ "visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
411
+ "visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
412
+ "visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
413
+ "visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
414
+ "visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
415
+ "visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
416
+ "visual.blocks.13.norm1.weight": "model-00001-of-00007.safetensors",
417
+ "visual.blocks.13.norm2.weight": "model-00001-of-00007.safetensors",
418
+ "visual.blocks.14.attn.proj.bias": "model-00001-of-00007.safetensors",
419
+ "visual.blocks.14.attn.proj.weight": "model-00001-of-00007.safetensors",
420
+ "visual.blocks.14.attn.qkv.bias": "model-00001-of-00007.safetensors",
421
+ "visual.blocks.14.attn.qkv.weight": "model-00001-of-00007.safetensors",
422
+ "visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
423
+ "visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
424
+ "visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
425
+ "visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
426
+ "visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
427
+ "visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
428
+ "visual.blocks.14.norm1.weight": "model-00001-of-00007.safetensors",
429
+ "visual.blocks.14.norm2.weight": "model-00001-of-00007.safetensors",
430
+ "visual.blocks.15.attn.proj.bias": "model-00001-of-00007.safetensors",
431
+ "visual.blocks.15.attn.proj.weight": "model-00001-of-00007.safetensors",
432
+ "visual.blocks.15.attn.qkv.bias": "model-00001-of-00007.safetensors",
433
+ "visual.blocks.15.attn.qkv.weight": "model-00001-of-00007.safetensors",
434
+ "visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
435
+ "visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
436
+ "visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
437
+ "visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
438
+ "visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
439
+ "visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
440
+ "visual.blocks.15.norm1.weight": "model-00001-of-00007.safetensors",
441
+ "visual.blocks.15.norm2.weight": "model-00001-of-00007.safetensors",
442
+ "visual.blocks.16.attn.proj.bias": "model-00001-of-00007.safetensors",
443
+ "visual.blocks.16.attn.proj.weight": "model-00001-of-00007.safetensors",
444
+ "visual.blocks.16.attn.qkv.bias": "model-00001-of-00007.safetensors",
445
+ "visual.blocks.16.attn.qkv.weight": "model-00001-of-00007.safetensors",
446
+ "visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
447
+ "visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
448
+ "visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
449
+ "visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
450
+ "visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
451
+ "visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
452
+ "visual.blocks.16.norm1.weight": "model-00001-of-00007.safetensors",
453
+ "visual.blocks.16.norm2.weight": "model-00001-of-00007.safetensors",
454
+ "visual.blocks.17.attn.proj.bias": "model-00001-of-00007.safetensors",
455
+ "visual.blocks.17.attn.proj.weight": "model-00001-of-00007.safetensors",
456
+ "visual.blocks.17.attn.qkv.bias": "model-00001-of-00007.safetensors",
457
+ "visual.blocks.17.attn.qkv.weight": "model-00001-of-00007.safetensors",
458
+ "visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
459
+ "visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
460
+ "visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
461
+ "visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
462
+ "visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
463
+ "visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
464
+ "visual.blocks.17.norm1.weight": "model-00001-of-00007.safetensors",
465
+ "visual.blocks.17.norm2.weight": "model-00001-of-00007.safetensors",
466
+ "visual.blocks.18.attn.proj.bias": "model-00001-of-00007.safetensors",
467
+ "visual.blocks.18.attn.proj.weight": "model-00001-of-00007.safetensors",
468
+ "visual.blocks.18.attn.qkv.bias": "model-00001-of-00007.safetensors",
469
+ "visual.blocks.18.attn.qkv.weight": "model-00001-of-00007.safetensors",
470
+ "visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
471
+ "visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
472
+ "visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
473
+ "visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
474
+ "visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
475
+ "visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
476
+ "visual.blocks.18.norm1.weight": "model-00001-of-00007.safetensors",
477
+ "visual.blocks.18.norm2.weight": "model-00001-of-00007.safetensors",
478
+ "visual.blocks.19.attn.proj.bias": "model-00001-of-00007.safetensors",
479
+ "visual.blocks.19.attn.proj.weight": "model-00001-of-00007.safetensors",
480
+ "visual.blocks.19.attn.qkv.bias": "model-00001-of-00007.safetensors",
481
+ "visual.blocks.19.attn.qkv.weight": "model-00001-of-00007.safetensors",
482
+ "visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
483
+ "visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
484
+ "visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
485
+ "visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
486
+ "visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
487
+ "visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
488
+ "visual.blocks.19.norm1.weight": "model-00001-of-00007.safetensors",
489
+ "visual.blocks.19.norm2.weight": "model-00001-of-00007.safetensors",
490
+ "visual.blocks.2.attn.proj.bias": "model-00001-of-00007.safetensors",
491
+ "visual.blocks.2.attn.proj.weight": "model-00001-of-00007.safetensors",
492
+ "visual.blocks.2.attn.qkv.bias": "model-00001-of-00007.safetensors",
493
+ "visual.blocks.2.attn.qkv.weight": "model-00001-of-00007.safetensors",
494
+ "visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
495
+ "visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
496
+ "visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
497
+ "visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
498
+ "visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
499
+ "visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
500
+ "visual.blocks.2.norm1.weight": "model-00001-of-00007.safetensors",
501
+ "visual.blocks.2.norm2.weight": "model-00001-of-00007.safetensors",
502
+ "visual.blocks.20.attn.proj.bias": "model-00001-of-00007.safetensors",
503
+ "visual.blocks.20.attn.proj.weight": "model-00001-of-00007.safetensors",
504
+ "visual.blocks.20.attn.qkv.bias": "model-00001-of-00007.safetensors",
505
+ "visual.blocks.20.attn.qkv.weight": "model-00001-of-00007.safetensors",
506
+ "visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
507
+ "visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
508
+ "visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
509
+ "visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
510
+ "visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
511
+ "visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
512
+ "visual.blocks.20.norm1.weight": "model-00001-of-00007.safetensors",
513
+ "visual.blocks.20.norm2.weight": "model-00001-of-00007.safetensors",
514
+ "visual.blocks.21.attn.proj.bias": "model-00001-of-00007.safetensors",
515
+ "visual.blocks.21.attn.proj.weight": "model-00001-of-00007.safetensors",
516
+ "visual.blocks.21.attn.qkv.bias": "model-00001-of-00007.safetensors",
517
+ "visual.blocks.21.attn.qkv.weight": "model-00001-of-00007.safetensors",
518
+ "visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
519
+ "visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
520
+ "visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
521
+ "visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
522
+ "visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
523
+ "visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
524
+ "visual.blocks.21.norm1.weight": "model-00001-of-00007.safetensors",
525
+ "visual.blocks.21.norm2.weight": "model-00001-of-00007.safetensors",
526
+ "visual.blocks.22.attn.proj.bias": "model-00001-of-00007.safetensors",
527
+ "visual.blocks.22.attn.proj.weight": "model-00001-of-00007.safetensors",
528
+ "visual.blocks.22.attn.qkv.bias": "model-00001-of-00007.safetensors",
529
+ "visual.blocks.22.attn.qkv.weight": "model-00001-of-00007.safetensors",
530
+ "visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
531
+ "visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
532
+ "visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
533
+ "visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
534
+ "visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
535
+ "visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
536
+ "visual.blocks.22.norm1.weight": "model-00001-of-00007.safetensors",
537
+ "visual.blocks.22.norm2.weight": "model-00001-of-00007.safetensors",
538
+ "visual.blocks.23.attn.proj.bias": "model-00001-of-00007.safetensors",
539
+ "visual.blocks.23.attn.proj.weight": "model-00001-of-00007.safetensors",
540
+ "visual.blocks.23.attn.qkv.bias": "model-00001-of-00007.safetensors",
541
+ "visual.blocks.23.attn.qkv.weight": "model-00001-of-00007.safetensors",
542
+ "visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
543
+ "visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
544
+ "visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
545
+ "visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
546
+ "visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
547
+ "visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
548
+ "visual.blocks.23.norm1.weight": "model-00001-of-00007.safetensors",
549
+ "visual.blocks.23.norm2.weight": "model-00001-of-00007.safetensors",
550
+ "visual.blocks.24.attn.proj.bias": "model-00001-of-00007.safetensors",
551
+ "visual.blocks.24.attn.proj.weight": "model-00001-of-00007.safetensors",
552
+ "visual.blocks.24.attn.qkv.bias": "model-00001-of-00007.safetensors",
553
+ "visual.blocks.24.attn.qkv.weight": "model-00001-of-00007.safetensors",
554
+ "visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
555
+ "visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
556
+ "visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
557
+ "visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
558
+ "visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
559
+ "visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
560
+ "visual.blocks.24.norm1.weight": "model-00001-of-00007.safetensors",
561
+ "visual.blocks.24.norm2.weight": "model-00001-of-00007.safetensors",
562
+ "visual.blocks.25.attn.proj.bias": "model-00001-of-00007.safetensors",
563
+ "visual.blocks.25.attn.proj.weight": "model-00001-of-00007.safetensors",
564
+ "visual.blocks.25.attn.qkv.bias": "model-00001-of-00007.safetensors",
565
+ "visual.blocks.25.attn.qkv.weight": "model-00001-of-00007.safetensors",
566
+ "visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
567
+ "visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
568
+ "visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
569
+ "visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
570
+ "visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
571
+ "visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
572
+ "visual.blocks.25.norm1.weight": "model-00001-of-00007.safetensors",
573
+ "visual.blocks.25.norm2.weight": "model-00001-of-00007.safetensors",
574
+ "visual.blocks.26.attn.proj.bias": "model-00001-of-00007.safetensors",
575
+ "visual.blocks.26.attn.proj.weight": "model-00001-of-00007.safetensors",
576
+ "visual.blocks.26.attn.qkv.bias": "model-00001-of-00007.safetensors",
577
+ "visual.blocks.26.attn.qkv.weight": "model-00001-of-00007.safetensors",
578
+ "visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
579
+ "visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
580
+ "visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
581
+ "visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
582
+ "visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
583
+ "visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
584
+ "visual.blocks.26.norm1.weight": "model-00001-of-00007.safetensors",
585
+ "visual.blocks.26.norm2.weight": "model-00001-of-00007.safetensors",
586
+ "visual.blocks.27.attn.proj.bias": "model-00001-of-00007.safetensors",
587
+ "visual.blocks.27.attn.proj.weight": "model-00001-of-00007.safetensors",
588
+ "visual.blocks.27.attn.qkv.bias": "model-00001-of-00007.safetensors",
589
+ "visual.blocks.27.attn.qkv.weight": "model-00001-of-00007.safetensors",
590
+ "visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
591
+ "visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
592
+ "visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
593
+ "visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
594
+ "visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
595
+ "visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
596
+ "visual.blocks.27.norm1.weight": "model-00001-of-00007.safetensors",
597
+ "visual.blocks.27.norm2.weight": "model-00001-of-00007.safetensors",
598
+ "visual.blocks.28.attn.proj.bias": "model-00001-of-00007.safetensors",
599
+ "visual.blocks.28.attn.proj.weight": "model-00001-of-00007.safetensors",
600
+ "visual.blocks.28.attn.qkv.bias": "model-00001-of-00007.safetensors",
601
+ "visual.blocks.28.attn.qkv.weight": "model-00001-of-00007.safetensors",
602
+ "visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
603
+ "visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
604
+ "visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
605
+ "visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
606
+ "visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
607
+ "visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
608
+ "visual.blocks.28.norm1.weight": "model-00001-of-00007.safetensors",
609
+ "visual.blocks.28.norm2.weight": "model-00001-of-00007.safetensors",
610
+ "visual.blocks.29.attn.proj.bias": "model-00001-of-00007.safetensors",
611
+ "visual.blocks.29.attn.proj.weight": "model-00001-of-00007.safetensors",
612
+ "visual.blocks.29.attn.qkv.bias": "model-00001-of-00007.safetensors",
613
+ "visual.blocks.29.attn.qkv.weight": "model-00001-of-00007.safetensors",
614
+ "visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
615
+ "visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
616
+ "visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
617
+ "visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
618
+ "visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
619
+ "visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
620
+ "visual.blocks.29.norm1.weight": "model-00001-of-00007.safetensors",
621
+ "visual.blocks.29.norm2.weight": "model-00001-of-00007.safetensors",
622
+ "visual.blocks.3.attn.proj.bias": "model-00001-of-00007.safetensors",
623
+ "visual.blocks.3.attn.proj.weight": "model-00001-of-00007.safetensors",
624
+ "visual.blocks.3.attn.qkv.bias": "model-00001-of-00007.safetensors",
625
+ "visual.blocks.3.attn.qkv.weight": "model-00001-of-00007.safetensors",
626
+ "visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
627
+ "visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
628
+ "visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
629
+ "visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
630
+ "visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
631
+ "visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
632
+ "visual.blocks.3.norm1.weight": "model-00001-of-00007.safetensors",
633
+ "visual.blocks.3.norm2.weight": "model-00001-of-00007.safetensors",
634
+ "visual.blocks.30.attn.proj.bias": "model-00001-of-00007.safetensors",
635
+ "visual.blocks.30.attn.proj.weight": "model-00001-of-00007.safetensors",
636
+ "visual.blocks.30.attn.qkv.bias": "model-00001-of-00007.safetensors",
637
+ "visual.blocks.30.attn.qkv.weight": "model-00001-of-00007.safetensors",
638
+ "visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
639
+ "visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
640
+ "visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
641
+ "visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
642
+ "visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
643
+ "visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
644
+ "visual.blocks.30.norm1.weight": "model-00001-of-00007.safetensors",
645
+ "visual.blocks.30.norm2.weight": "model-00001-of-00007.safetensors",
646
+ "visual.blocks.31.attn.proj.bias": "model-00001-of-00007.safetensors",
647
+ "visual.blocks.31.attn.proj.weight": "model-00001-of-00007.safetensors",
648
+ "visual.blocks.31.attn.qkv.bias": "model-00001-of-00007.safetensors",
649
+ "visual.blocks.31.attn.qkv.weight": "model-00001-of-00007.safetensors",
650
+ "visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
651
+ "visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
652
+ "visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
653
+ "visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
654
+ "visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
655
+ "visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
656
+ "visual.blocks.31.norm1.weight": "model-00001-of-00007.safetensors",
657
+ "visual.blocks.31.norm2.weight": "model-00001-of-00007.safetensors",
658
+ "visual.blocks.4.attn.proj.bias": "model-00001-of-00007.safetensors",
659
+ "visual.blocks.4.attn.proj.weight": "model-00001-of-00007.safetensors",
660
+ "visual.blocks.4.attn.qkv.bias": "model-00001-of-00007.safetensors",
661
+ "visual.blocks.4.attn.qkv.weight": "model-00001-of-00007.safetensors",
662
+ "visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
663
+ "visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
664
+ "visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
665
+ "visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
666
+ "visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
667
+ "visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
668
+ "visual.blocks.4.norm1.weight": "model-00001-of-00007.safetensors",
669
+ "visual.blocks.4.norm2.weight": "model-00001-of-00007.safetensors",
670
+ "visual.blocks.5.attn.proj.bias": "model-00001-of-00007.safetensors",
671
+ "visual.blocks.5.attn.proj.weight": "model-00001-of-00007.safetensors",
672
+ "visual.blocks.5.attn.qkv.bias": "model-00001-of-00007.safetensors",
673
+ "visual.blocks.5.attn.qkv.weight": "model-00001-of-00007.safetensors",
674
+ "visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
675
+ "visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
676
+ "visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
677
+ "visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
678
+ "visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
679
+ "visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
680
+ "visual.blocks.5.norm1.weight": "model-00001-of-00007.safetensors",
681
+ "visual.blocks.5.norm2.weight": "model-00001-of-00007.safetensors",
682
+ "visual.blocks.6.attn.proj.bias": "model-00001-of-00007.safetensors",
683
+ "visual.blocks.6.attn.proj.weight": "model-00001-of-00007.safetensors",
684
+ "visual.blocks.6.attn.qkv.bias": "model-00001-of-00007.safetensors",
685
+ "visual.blocks.6.attn.qkv.weight": "model-00001-of-00007.safetensors",
686
+ "visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
687
+ "visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
688
+ "visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
689
+ "visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
690
+ "visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
691
+ "visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
692
+ "visual.blocks.6.norm1.weight": "model-00001-of-00007.safetensors",
693
+ "visual.blocks.6.norm2.weight": "model-00001-of-00007.safetensors",
694
+ "visual.blocks.7.attn.proj.bias": "model-00001-of-00007.safetensors",
695
+ "visual.blocks.7.attn.proj.weight": "model-00001-of-00007.safetensors",
696
+ "visual.blocks.7.attn.qkv.bias": "model-00001-of-00007.safetensors",
697
+ "visual.blocks.7.attn.qkv.weight": "model-00001-of-00007.safetensors",
698
+ "visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
699
+ "visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
700
+ "visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
701
+ "visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
702
+ "visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
703
+ "visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
704
+ "visual.blocks.7.norm1.weight": "model-00001-of-00007.safetensors",
705
+ "visual.blocks.7.norm2.weight": "model-00001-of-00007.safetensors",
706
+ "visual.blocks.8.attn.proj.bias": "model-00001-of-00007.safetensors",
707
+ "visual.blocks.8.attn.proj.weight": "model-00001-of-00007.safetensors",
708
+ "visual.blocks.8.attn.qkv.bias": "model-00001-of-00007.safetensors",
709
+ "visual.blocks.8.attn.qkv.weight": "model-00001-of-00007.safetensors",
710
+ "visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
711
+ "visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
712
+ "visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
713
+ "visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
714
+ "visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
715
+ "visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
716
+ "visual.blocks.8.norm1.weight": "model-00001-of-00007.safetensors",
717
+ "visual.blocks.8.norm2.weight": "model-00001-of-00007.safetensors",
718
+ "visual.blocks.9.attn.proj.bias": "model-00001-of-00007.safetensors",
719
+ "visual.blocks.9.attn.proj.weight": "model-00001-of-00007.safetensors",
720
+ "visual.blocks.9.attn.qkv.bias": "model-00001-of-00007.safetensors",
721
+ "visual.blocks.9.attn.qkv.weight": "model-00001-of-00007.safetensors",
722
+ "visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00007.safetensors",
723
+ "visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
724
+ "visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00007.safetensors",
725
+ "visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
726
+ "visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00007.safetensors",
727
+ "visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
728
+ "visual.blocks.9.norm1.weight": "model-00001-of-00007.safetensors",
729
+ "visual.blocks.9.norm2.weight": "model-00001-of-00007.safetensors",
730
+ "visual.merger.ln_q.weight": "model-00001-of-00007.safetensors",
731
+ "visual.merger.mlp.0.bias": "model-00001-of-00007.safetensors",
732
+ "visual.merger.mlp.0.weight": "model-00001-of-00007.safetensors",
733
+ "visual.merger.mlp.2.bias": "model-00001-of-00007.safetensors",
734
+ "visual.merger.mlp.2.weight": "model-00001-of-00007.safetensors",
735
+ "visual.patch_embed.proj.weight": "model-00001-of-00007.safetensors"
736
+ }
737
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": null,
3
+ "data_format": "channels_first",
4
+ "default_to_square": true,
5
+ "device": null,
6
+ "do_center_crop": null,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_rescale": true,
10
+ "do_resize": true,
11
+ "image_mean": [
12
+ 0.48145466,
13
+ 0.4578275,
14
+ 0.40821073
15
+ ],
16
+ "image_processor_type": "Qwen2VLImageProcessorFast",
17
+ "image_std": [
18
+ 0.26862954,
19
+ 0.26130258,
20
+ 0.27577711
21
+ ],
22
+ "input_data_format": null,
23
+ "max_pixels": 12845056,
24
+ "merge_size": 2,
25
+ "min_pixels": 3136,
26
+ "patch_size": 14,
27
+ "processor_class": "Qwen2_5_VLProcessor",
28
+ "resample": 3,
29
+ "rescale_factor": 0.00392156862745098,
30
+ "return_tensors": null,
31
+ "size": {
32
+ "longest_edge": 12845056,
33
+ "shortest_edge": 3136
34
+ },
35
+ "temporal_patch_size": 2
36
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
tokenizer_config.json ADDED
@@ -0,0 +1,209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "clean_up_tokenization_spaces": false,
199
+ "eos_token": "<|im_end|>",
200
+ "errors": "replace",
201
+ "extra_special_tokens": {},
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "processor_class": "Qwen2_5_VLProcessor",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null,
208
+ "use_fast": true
209
+ }
video_preprocessor_config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": null,
3
+ "data_format": "channels_first",
4
+ "default_to_square": true,
5
+ "device": null,
6
+ "do_center_crop": null,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_pad": null,
10
+ "do_rescale": true,
11
+ "do_resize": true,
12
+ "do_sample_frames": false,
13
+ "fps": null,
14
+ "image_mean": [
15
+ 0.48145466,
16
+ 0.4578275,
17
+ 0.40821073
18
+ ],
19
+ "image_processor_type": "Qwen2VLImageProcessorFast",
20
+ "image_std": [
21
+ 0.26862954,
22
+ 0.26130258,
23
+ 0.27577711
24
+ ],
25
+ "input_data_format": null,
26
+ "max_frames": 768,
27
+ "max_pixels": 12845056,
28
+ "merge_size": 2,
29
+ "min_frames": 4,
30
+ "min_pixels": 3136,
31
+ "num_frames": null,
32
+ "patch_size": 14,
33
+ "processor_class": "Qwen2_5_VLProcessor",
34
+ "resample": 3,
35
+ "rescale_factor": 0.00392156862745098,
36
+ "return_tensors": null,
37
+ "size": {
38
+ "longest_edge": 12845056,
39
+ "shortest_edge": 3136
40
+ },
41
+ "size_divisor": null,
42
+ "temporal_patch_size": 2,
43
+ "video_metadata": null,
44
+ "video_processor_type": "Qwen2VLVideoProcessor"
45
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff