HanSolo9682 commited on
Commit
3a8a52d
·
verified ·
1 Parent(s): 71a7dab

Upload folder using huggingface_hub

Browse files
.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 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<emb>": 151669,
6
+ "<think>": 151667,
7
+ "<tool_call>": 151657,
8
+ "<tool_response>": 151665,
9
+ "<|box_end|>": 151649,
10
+ "<|box_start|>": 151648,
11
+ "<|endoftext|>": 151643,
12
+ "<|file_sep|>": 151664,
13
+ "<|fim_middle|>": 151660,
14
+ "<|fim_pad|>": 151662,
15
+ "<|fim_prefix|>": 151659,
16
+ "<|fim_suffix|>": 151661,
17
+ "<|im_end|>": 151645,
18
+ "<|im_start|>": 151644,
19
+ "<|image_pad|>": 151655,
20
+ "<|object_ref_end|>": 151647,
21
+ "<|object_ref_start|>": 151646,
22
+ "<|quad_end|>": 151651,
23
+ "<|quad_start|>": 151650,
24
+ "<|repo_name|>": 151663,
25
+ "<|video_pad|>": 151656,
26
+ "<|vision_end|>": 151653,
27
+ "<|vision_pad|>": 151654,
28
+ "<|vision_start|>": 151652
29
+ }
arguments/data.yaml ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ assistant_key: gpt
2
+ cand_pool_path: /Data2/harrisz/colpali_extracted_data/cand_pool.jsonl
3
+ colpali_path: null
4
+ colpali_path_prefix: null
5
+ data_path: null
6
+ eval_data_path: null
7
+ image_data_path: null
8
+ image_folder: null
9
+ image_path_prefix: /Data2/harrisz/colpali_extracted_data/images/
10
+ instructions_path: /Data2/anirudh/M-BEIR/instructions/query_instructions.tsv
11
+ num_frames: 8
12
+ query_data_path: /Data2/harrisz/colpali_extracted_data/query.jsonl
13
+ rerank_data_path: null
14
+ text_data_path: null
15
+ user_key: human
16
+ video_folder: null
arguments/lora.yaml ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ lora_alpha: 256
2
+ lora_bias: none
3
+ lora_dropout: 0.05
4
+ lora_r: 128
5
+ lora_weight_path: ''
6
+ q_lora: false
7
+ use_lora: true
8
+ use_vision_lora: false
9
+ vision_lora_alpha: 16
10
+ vision_lora_r: 16
arguments/model.yaml ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ model_id: qwen3-vl-2b
2
+ model_local_path: Qwen/Qwen3-VL-2B-Instruct
3
+ use_doc_attention: false
4
+ use_full_attention: false
5
+ use_multilayer_features: false
6
+ use_up_attention: false
arguments/training.yaml ADDED
@@ -0,0 +1,162 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ _n_gpu: 1
2
+ accelerator_config:
3
+ dispatch_batches: null
4
+ even_batches: true
5
+ gradient_accumulation_kwargs: null
6
+ non_blocking: false
7
+ split_batches: false
8
+ use_configured_state: false
9
+ use_seedable_sampler: true
10
+ adafactor: false
11
+ adam_beta1: 0.9
12
+ adam_beta2: 0.999
13
+ adam_epsilon: 1.0e-08
14
+ auto_find_batch_size: false
15
+ average_tokens_across_devices: true
16
+ batch_eval_metrics: false
17
+ bf16: true
18
+ bf16_full_eval: false
19
+ data_seed: null
20
+ dataloader_drop_last: false
21
+ dataloader_num_workers: 0
22
+ dataloader_persistent_workers: false
23
+ dataloader_pin_memory: true
24
+ dataloader_prefetch_factor: null
25
+ ddp_backend: null
26
+ ddp_broadcast_buffers: null
27
+ ddp_bucket_cap_mb: null
28
+ ddp_find_unused_parameters: null
29
+ ddp_timeout: 1800
30
+ debug: []
31
+ deepspeed: ./ds_configs/zero2.json
32
+ disable_tqdm: false
33
+ do_eval: true
34
+ do_predict: false
35
+ do_train: false
36
+ eval_accumulation_steps: null
37
+ eval_delay: 0
38
+ eval_do_concat_batches: true
39
+ eval_on_start: false
40
+ eval_steps: null
41
+ eval_strategy: !!python/object/apply:transformers.trainer_utils.IntervalStrategy
42
+ - epoch
43
+ eval_use_gather_object: false
44
+ fp16: false
45
+ fp16_backend: auto
46
+ fp16_full_eval: false
47
+ fp16_opt_level: O1
48
+ freeze_backbone: false
49
+ freeze_only_attn: false
50
+ fsdp: []
51
+ fsdp_config:
52
+ min_num_params: 0
53
+ xla: false
54
+ xla_fsdp_grad_ckpt: false
55
+ xla_fsdp_v2: false
56
+ fsdp_min_num_params: 0
57
+ fsdp_transformer_layer_cls_to_wrap: null
58
+ full_determinism: false
59
+ gradient_accumulation_steps: 1
60
+ gradient_checkpointing: true
61
+ gradient_checkpointing_kwargs: null
62
+ greater_is_better: null
63
+ group_by_length: false
64
+ half_precision_backend: auto
65
+ hub_always_push: false
66
+ hub_model_id: null
67
+ hub_private_repo: null
68
+ hub_revision: null
69
+ hub_strategy: !!python/object/apply:transformers.trainer_utils.HubStrategy
70
+ - every_save
71
+ hub_token: null
72
+ ignore_data_skip: false
73
+ include_for_metrics: []
74
+ include_inputs_for_metrics: false
75
+ include_num_input_tokens_seen: 'no'
76
+ include_tokens_per_second: false
77
+ jit_mode_eval: false
78
+ label_names: null
79
+ label_smoothing_factor: 0.0
80
+ learning_rate: 0.0001
81
+ length_column_name: length
82
+ liger_kernel_config: null
83
+ load_best_model_at_end: false
84
+ local_rank: 7
85
+ log_level: passive
86
+ log_level_replica: warning
87
+ log_on_each_node: true
88
+ logging_dir: ./checkpoints/qwen3-vl-2b_visdoc_baseline/runs/May04_03-23-10_crossnode2
89
+ logging_first_step: false
90
+ logging_nan_inf_filter: true
91
+ logging_steps: 1.0
92
+ logging_strategy: !!python/object/apply:transformers.trainer_utils.IntervalStrategy
93
+ - steps
94
+ lr_scheduler_kwargs: {}
95
+ lr_scheduler_type: !!python/object/apply:transformers.trainer_utils.SchedulerType
96
+ - cosine
97
+ max_grad_norm: 1.0
98
+ max_steps: -1
99
+ metric_for_best_model: null
100
+ model_max_length: 1024
101
+ mp_parameters: ''
102
+ neftune_noise_alpha: null
103
+ no_cuda: false
104
+ num_train_epochs: 4.0
105
+ optim: !!python/object/apply:transformers.training_args.OptimizerNames
106
+ - adamw_torch_fused
107
+ optim_args: null
108
+ optim_target_modules: null
109
+ output_dir: ./checkpoints/qwen3-vl-2b_visdoc_baseline
110
+ overwrite_output_dir: false
111
+ parallelism_config: null
112
+ past_index: -1
113
+ per_device_eval_batch_size: 64
114
+ per_device_train_batch_size: 64
115
+ per_gpu_eval_batch_size: null
116
+ per_gpu_train_batch_size: null
117
+ prediction_loss_only: false
118
+ project: huggingface
119
+ push_to_hub: false
120
+ push_to_hub_model_id: null
121
+ push_to_hub_organization: null
122
+ push_to_hub_token: null
123
+ ray_scope: last
124
+ remove_unused_columns: false
125
+ replace_embed_layers: false
126
+ report_to:
127
+ - wandb
128
+ restore_callback_states_from_checkpoint: false
129
+ resume_from_checkpoint: null
130
+ run_name: qwen3-vl-2b_visdoc_baseline
131
+ save_on_each_node: false
132
+ save_only_model: false
133
+ save_safetensors: true
134
+ save_steps: 500
135
+ save_strategy: !!python/object/apply:transformers.trainer_utils.SaveStrategy
136
+ - epoch
137
+ save_total_limit: 1
138
+ seed: 42
139
+ skip_memory_metrics: true
140
+ starting_layer: null
141
+ tf32: true
142
+ torch_compile: false
143
+ torch_compile_backend: null
144
+ torch_compile_mode: null
145
+ torch_empty_cache_steps: null
146
+ torchdynamo: null
147
+ tpu_metrics_debug: false
148
+ tpu_num_cores: null
149
+ trackio_space_id: trackio
150
+ train_vision_encoder: false
151
+ train_vision_projector: false
152
+ use_cpu: false
153
+ use_flash_attn: false
154
+ use_hard_negatives: false
155
+ use_legacy_prediction_loop: false
156
+ use_liger_kernel: false
157
+ use_mps_device: false
158
+ use_steer_layers: false
159
+ vision_projector_lr: null
160
+ warmup_ratio: 0.03
161
+ warmup_steps: 0
162
+ weight_decay: 0.0
chat_template.jinja ADDED
@@ -0,0 +1,120 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0].role == 'system' %}
4
+ {%- if messages[0].content is string %}
5
+ {{- messages[0].content }}
6
+ {%- else %}
7
+ {%- for content in messages[0].content %}
8
+ {%- if 'text' in content %}
9
+ {{- content.text }}
10
+ {%- endif %}
11
+ {%- endfor %}
12
+ {%- endif %}
13
+ {{- '\n\n' }}
14
+ {%- endif %}
15
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
16
+ {%- for tool in tools %}
17
+ {{- "\n" }}
18
+ {{- tool | tojson }}
19
+ {%- endfor %}
20
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
21
+ {%- else %}
22
+ {%- if messages[0].role == 'system' %}
23
+ {{- '<|im_start|>system\n' }}
24
+ {%- if messages[0].content is string %}
25
+ {{- messages[0].content }}
26
+ {%- else %}
27
+ {%- for content in messages[0].content %}
28
+ {%- if 'text' in content %}
29
+ {{- content.text }}
30
+ {%- endif %}
31
+ {%- endfor %}
32
+ {%- endif %}
33
+ {{- '<|im_end|>\n' }}
34
+ {%- endif %}
35
+ {%- endif %}
36
+ {%- set image_count = namespace(value=0) %}
37
+ {%- set video_count = namespace(value=0) %}
38
+ {%- for message in messages %}
39
+ {%- if message.role == "user" %}
40
+ {{- '<|im_start|>' + message.role + '\n' }}
41
+ {%- if message.content is string %}
42
+ {{- message.content }}
43
+ {%- else %}
44
+ {%- for content in message.content %}
45
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
46
+ {%- set image_count.value = image_count.value + 1 %}
47
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
48
+ <|vision_start|><|image_pad|><|vision_end|>
49
+ {%- elif content.type == 'video' or 'video' in content %}
50
+ {%- set video_count.value = video_count.value + 1 %}
51
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
52
+ <|vision_start|><|video_pad|><|vision_end|>
53
+ {%- elif 'text' in content %}
54
+ {{- content.text }}
55
+ {%- endif %}
56
+ {%- endfor %}
57
+ {%- endif %}
58
+ {{- '<|im_end|>\n' }}
59
+ {%- elif message.role == "assistant" %}
60
+ {{- '<|im_start|>' + message.role + '\n' }}
61
+ {%- if message.content is string %}
62
+ {{- message.content }}
63
+ {%- else %}
64
+ {%- for content_item in message.content %}
65
+ {%- if 'text' in content_item %}
66
+ {{- content_item.text }}
67
+ {%- endif %}
68
+ {%- endfor %}
69
+ {%- endif %}
70
+ {%- if message.tool_calls %}
71
+ {%- for tool_call in message.tool_calls %}
72
+ {%- if (loop.first and message.content) or (not loop.first) %}
73
+ {{- '\n' }}
74
+ {%- endif %}
75
+ {%- if tool_call.function %}
76
+ {%- set tool_call = tool_call.function %}
77
+ {%- endif %}
78
+ {{- '<tool_call>\n{"name": "' }}
79
+ {{- tool_call.name }}
80
+ {{- '", "arguments": ' }}
81
+ {%- if tool_call.arguments is string %}
82
+ {{- tool_call.arguments }}
83
+ {%- else %}
84
+ {{- tool_call.arguments | tojson }}
85
+ {%- endif %}
86
+ {{- '}\n</tool_call>' }}
87
+ {%- endfor %}
88
+ {%- endif %}
89
+ {{- '<|im_end|>\n' }}
90
+ {%- elif message.role == "tool" %}
91
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
92
+ {{- '<|im_start|>user' }}
93
+ {%- endif %}
94
+ {{- '\n<tool_response>\n' }}
95
+ {%- if message.content is string %}
96
+ {{- message.content }}
97
+ {%- else %}
98
+ {%- for content in message.content %}
99
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
100
+ {%- set image_count.value = image_count.value + 1 %}
101
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
102
+ <|vision_start|><|image_pad|><|vision_end|>
103
+ {%- elif content.type == 'video' or 'video' in content %}
104
+ {%- set video_count.value = video_count.value + 1 %}
105
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
106
+ <|vision_start|><|video_pad|><|vision_end|>
107
+ {%- elif 'text' in content %}
108
+ {{- content.text }}
109
+ {%- endif %}
110
+ {%- endfor %}
111
+ {%- endif %}
112
+ {{- '\n</tool_response>' }}
113
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
114
+ {{- '<|im_end|>\n' }}
115
+ {%- endif %}
116
+ {%- endif %}
117
+ {%- endfor %}
118
+ {%- if add_generation_prompt %}
119
+ {{- '<|im_start|>assistant\n' }}
120
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3VLRetFinetuneForConditionalGeneration"
4
+ ],
5
+ "dtype": "bfloat16",
6
+ "emb_token_ids": [
7
+ 151669
8
+ ],
9
+ "image_token_id": 151655,
10
+ "model_type": "qwen3_vl",
11
+ "text_config": {
12
+ "attention_bias": false,
13
+ "attention_dropout": 0.0,
14
+ "bos_token_id": 151643,
15
+ "dtype": "bfloat16",
16
+ "eos_token_id": 151645,
17
+ "head_dim": 128,
18
+ "hidden_act": "silu",
19
+ "hidden_size": 2048,
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 6144,
22
+ "max_position_embeddings": 262144,
23
+ "model_type": "qwen3_vl_text",
24
+ "num_attention_heads": 16,
25
+ "num_hidden_layers": 28,
26
+ "num_key_value_heads": 8,
27
+ "rms_norm_eps": 1e-06,
28
+ "rope_scaling": {
29
+ "mrope_interleaved": true,
30
+ "mrope_section": [
31
+ 24,
32
+ 20,
33
+ 20
34
+ ],
35
+ "rope_type": "default"
36
+ },
37
+ "rope_theta": 5000000,
38
+ "tie_word_embeddings": true,
39
+ "use_cache": true,
40
+ "vocab_size": 151670
41
+ },
42
+ "tie_word_embeddings": true,
43
+ "transformers_version": "4.57.0",
44
+ "video_token_id": 151656,
45
+ "vision_config": {
46
+ "deepstack_visual_indexes": [
47
+ 5,
48
+ 11,
49
+ 17
50
+ ],
51
+ "depth": 24,
52
+ "dtype": "bfloat16",
53
+ "hidden_act": "gelu_pytorch_tanh",
54
+ "hidden_size": 1024,
55
+ "in_channels": 3,
56
+ "initializer_range": 0.02,
57
+ "intermediate_size": 4096,
58
+ "model_type": "qwen3_vl",
59
+ "num_heads": 16,
60
+ "num_position_embeddings": 2304,
61
+ "out_hidden_size": 2048,
62
+ "patch_size": 16,
63
+ "spatial_merge_size": 2,
64
+ "temporal_patch_size": 2
65
+ },
66
+ "vision_end_token_id": 151653,
67
+ "vision_start_token_id": 151652
68
+ }
generation_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "embed_dim": 1536,
5
+ "eos_token_id": [
6
+ 151645,
7
+ 151643
8
+ ],
9
+ "pad_token_id": 151643,
10
+ "temperature": 0.7,
11
+ "top_k": 20,
12
+ "top_p": 0.8,
13
+ "transformers_version": "4.57.0",
14
+ "use_doc_attention": false,
15
+ "use_full_attention": false,
16
+ "use_up_attention": false
17
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39973c63301c601400721adce222b13bb0019a360e94922da1f81a36e031dc29
3
+ size 4254050776
preprocessor_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": null,
3
+ "data_format": "channels_first",
4
+ "default_to_square": true,
5
+ "device": null,
6
+ "disable_grouping": null,
7
+ "do_center_crop": null,
8
+ "do_convert_rgb": true,
9
+ "do_normalize": true,
10
+ "do_pad": null,
11
+ "do_rescale": true,
12
+ "do_resize": true,
13
+ "image_mean": [
14
+ 0.5,
15
+ 0.5,
16
+ 0.5
17
+ ],
18
+ "image_processor_type": "Qwen2VLImageProcessorFast",
19
+ "image_std": [
20
+ 0.5,
21
+ 0.5,
22
+ 0.5
23
+ ],
24
+ "input_data_format": null,
25
+ "max_pixels": 802816,
26
+ "merge_size": 2,
27
+ "min_pixels": 200704,
28
+ "pad_size": null,
29
+ "patch_size": 16,
30
+ "processor_class": "Qwen3VLProcessor",
31
+ "resample": 3,
32
+ "rescale_factor": 0.00392156862745098,
33
+ "return_tensors": null,
34
+ "size": {
35
+ "longest_edge": 16777216,
36
+ "shortest_edge": 65536
37
+ },
38
+ "temporal_patch_size": 2
39
+ }
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 sha256:70fd357cf4e7f3fc7f5e364a4c078be3771e516ec2baed1084545ecd329e2ef1
3
+ size 11423004
tokenizer_config.json ADDED
@@ -0,0 +1,250 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ },
213
+ "151669": {
214
+ "content": "<emb>",
215
+ "lstrip": false,
216
+ "normalized": true,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": false
220
+ }
221
+ },
222
+ "additional_special_tokens": [
223
+ "<|im_start|>",
224
+ "<|im_end|>",
225
+ "<|object_ref_start|>",
226
+ "<|object_ref_end|>",
227
+ "<|box_start|>",
228
+ "<|box_end|>",
229
+ "<|quad_start|>",
230
+ "<|quad_end|>",
231
+ "<|vision_start|>",
232
+ "<|vision_end|>",
233
+ "<|vision_pad|>",
234
+ "<|image_pad|>",
235
+ "<|video_pad|>"
236
+ ],
237
+ "bos_token": null,
238
+ "clean_up_tokenization_spaces": false,
239
+ "eos_token": "<|im_end|>",
240
+ "errors": "replace",
241
+ "extra_special_tokens": {},
242
+ "max_pixels": 802816,
243
+ "min_pixels": 200704,
244
+ "model_max_length": 1024,
245
+ "pad_token": "<|endoftext|>",
246
+ "processor_class": "Qwen3VLProcessor",
247
+ "split_special_tokens": false,
248
+ "tokenizer_class": "Qwen2Tokenizer",
249
+ "unk_token": null
250
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
video_preprocessor_config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "do_sample_frames": true,
12
+ "fps": 2,
13
+ "image_mean": [
14
+ 0.5,
15
+ 0.5,
16
+ 0.5
17
+ ],
18
+ "image_std": [
19
+ 0.5,
20
+ 0.5,
21
+ 0.5
22
+ ],
23
+ "input_data_format": null,
24
+ "max_frames": 768,
25
+ "merge_size": 2,
26
+ "min_frames": 4,
27
+ "num_frames": null,
28
+ "pad_size": null,
29
+ "patch_size": 16,
30
+ "processor_class": "Qwen3VLProcessor",
31
+ "resample": 3,
32
+ "rescale_factor": 0.00392156862745098,
33
+ "return_metadata": false,
34
+ "size": {
35
+ "longest_edge": 25165824,
36
+ "shortest_edge": 4096
37
+ },
38
+ "temporal_patch_size": 2,
39
+ "video_metadata": null,
40
+ "video_processor_type": "Qwen3VLVideoProcessor"
41
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff