Hugging Face's logo

unsup-opsd
/
ckpts

Safetensors
Model card Files
xet
 Community
williamium commited on
Commit
72a09fb
·
verified ·
1 Parent(s): f0cce40

keep latest 2 step ckpts for Vision-OPD-Qwen3-VL-4B-Instruct-bbox-oracle (yijiangli's retention ruling 2026-09-14)

Browse files
Files changed (21) hide show
  1. Vision-OPD-Qwen3-VL-4B-Instruct-bbox-oracle/step13/chat_template.jinja +0 -120
  2. Vision-OPD-Qwen3-VL-4B-Instruct-bbox-oracle/step13/config.json +0 -69
  3. Vision-OPD-Qwen3-VL-4B-Instruct-bbox-oracle/step13/generation_config.json +0 -14
  4. Vision-OPD-Qwen3-VL-4B-Instruct-bbox-oracle/step13/model.safetensors +0 -3
  5. Vision-OPD-Qwen3-VL-4B-Instruct-bbox-oracle/step13/processor_config.json +0 -60
  6. Vision-OPD-Qwen3-VL-4B-Instruct-bbox-oracle/step13/tokenizer.json +0 -3
  7. Vision-OPD-Qwen3-VL-4B-Instruct-bbox-oracle/step13/tokenizer_config.json +0 -30
  8. Vision-OPD-Qwen3-VL-4B-Instruct-bbox-oracle/step26/chat_template.jinja +0 -120
  9. Vision-OPD-Qwen3-VL-4B-Instruct-bbox-oracle/step26/config.json +0 -69
  10. Vision-OPD-Qwen3-VL-4B-Instruct-bbox-oracle/step26/generation_config.json +0 -14
  11. Vision-OPD-Qwen3-VL-4B-Instruct-bbox-oracle/step26/model.safetensors +0 -3
  12. Vision-OPD-Qwen3-VL-4B-Instruct-bbox-oracle/step26/processor_config.json +0 -60
  13. Vision-OPD-Qwen3-VL-4B-Instruct-bbox-oracle/step26/tokenizer.json +0 -3
  14. Vision-OPD-Qwen3-VL-4B-Instruct-bbox-oracle/step26/tokenizer_config.json +0 -30
  15. Vision-OPD-Qwen3-VL-4B-Instruct-bbox-oracle/step39/chat_template.jinja +0 -120
  16. Vision-OPD-Qwen3-VL-4B-Instruct-bbox-oracle/step39/config.json +0 -69
  17. Vision-OPD-Qwen3-VL-4B-Instruct-bbox-oracle/step39/generation_config.json +0 -14
  18. Vision-OPD-Qwen3-VL-4B-Instruct-bbox-oracle/step39/model.safetensors +0 -3
  19. Vision-OPD-Qwen3-VL-4B-Instruct-bbox-oracle/step39/processor_config.json +0 -60
  20. Vision-OPD-Qwen3-VL-4B-Instruct-bbox-oracle/step39/tokenizer.json +0 -3
  21. Vision-OPD-Qwen3-VL-4B-Instruct-bbox-oracle/step39/tokenizer_config.json +0 -30
Vision-OPD-Qwen3-VL-4B-Instruct-bbox-oracle/step13/chat_template.jinja DELETED
@@ -1,120 +0,0 @@
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 %}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Vision-OPD-Qwen3-VL-4B-Instruct-bbox-oracle/step13/config.json DELETED
@@ -1,69 +0,0 @@
1
- {
2
- "architectures": [
3
- "Qwen3VLForConditionalGeneration"
4
- ],
5
- "bos_token_id": null,
6
- "dtype": "float32",
7
- "eos_token_id": 151645,
8
- "image_token_id": 151655,
9
- "model_type": "qwen3_vl",
10
- "pad_token_id": 151643,
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": 2560,
20
- "initializer_range": 0.02,
21
- "intermediate_size": 9728,
22
- "max_position_embeddings": 262144,
23
- "model_type": "qwen3_vl_text",
24
- "num_attention_heads": 32,
25
- "num_hidden_layers": 36,
26
- "num_key_value_heads": 8,
27
- "pad_token_id": null,
28
- "rms_norm_eps": 1e-06,
29
- "rope_parameters": {
30
- "mrope_interleaved": true,
31
- "mrope_section": [
32
- 24,
33
- 20,
34
- 20
35
- ],
36
- "rope_theta": 5000000,
37
- "rope_type": "default"
38
- },
39
- "tie_word_embeddings": true,
40
- "use_cache": true,
41
- "vocab_size": 151936
42
- },
43
- "tie_word_embeddings": true,
44
- "transformers_version": "5.5.0",
45
- "video_token_id": 151656,
46
- "vision_config": {
47
- "deepstack_visual_indexes": [
48
- 5,
49
- 11,
50
- 17
51
- ],
52
- "depth": 24,
53
- "dtype": "bfloat16",
54
- "hidden_act": "gelu_pytorch_tanh",
55
- "hidden_size": 1024,
56
- "in_channels": 3,
57
- "initializer_range": 0.02,
58
- "intermediate_size": 4096,
59
- "model_type": "qwen3_vl",
60
- "num_heads": 16,
61
- "num_position_embeddings": 2304,
62
- "out_hidden_size": 2560,
63
- "patch_size": 16,
64
- "spatial_merge_size": 2,
65
- "temporal_patch_size": 2
66
- },
67
- "vision_end_token_id": 151653,
68
- "vision_start_token_id": 151652
69
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Vision-OPD-Qwen3-VL-4B-Instruct-bbox-oracle/step13/generation_config.json DELETED
@@ -1,14 +0,0 @@
1
- {
2
- "bos_token_id": 151643,
3
- "do_sample": true,
4
- "eos_token_id": [
5
- 151645,
6
- 151643
7
- ],
8
- "pad_token_id": 151643,
9
- "repetition_penalty": 1.0,
10
- "temperature": 0.7,
11
- "top_k": 20,
12
- "top_p": 0.8,
13
- "transformers_version": "5.5.0"
14
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Vision-OPD-Qwen3-VL-4B-Instruct-bbox-oracle/step13/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:89a7c1544dbf411f7c053f51c6576c7b3e5c7094a79cc705b6a9bbd692e9f2eb
3
- size 9653631848
 
 
 
 
Vision-OPD-Qwen3-VL-4B-Instruct-bbox-oracle/step13/processor_config.json DELETED
@@ -1,60 +0,0 @@
1
- {
2
- "image_processor": {
3
- "do_convert_rgb": true,
4
- "do_normalize": true,
5
- "do_rescale": true,
6
- "do_resize": true,
7
- "image_mean": [
8
- 0.5,
9
- 0.5,
10
- 0.5
11
- ],
12
- "image_processor_type": "Qwen2VLImageProcessor",
13
- "image_std": [
14
- 0.5,
15
- 0.5,
16
- 0.5
17
- ],
18
- "merge_size": 2,
19
- "patch_size": 16,
20
- "resample": 3,
21
- "rescale_factor": 0.00392156862745098,
22
- "size": {
23
- "longest_edge": 16777216,
24
- "shortest_edge": 65536
25
- },
26
- "temporal_patch_size": 2
27
- },
28
- "processor_class": "Qwen3VLProcessor",
29
- "video_processor": {
30
- "do_convert_rgb": true,
31
- "do_normalize": true,
32
- "do_rescale": true,
33
- "do_resize": true,
34
- "do_sample_frames": true,
35
- "fps": 2,
36
- "image_mean": [
37
- 0.5,
38
- 0.5,
39
- 0.5
40
- ],
41
- "image_std": [
42
- 0.5,
43
- 0.5,
44
- 0.5
45
- ],
46
- "max_frames": 768,
47
- "merge_size": 2,
48
- "min_frames": 4,
49
- "patch_size": 16,
50
- "resample": 3,
51
- "rescale_factor": 0.00392156862745098,
52
- "return_metadata": false,
53
- "size": {
54
- "longest_edge": 25165824,
55
- "shortest_edge": 4096
56
- },
57
- "temporal_patch_size": 2,
58
- "video_processor_type": "Qwen3VLVideoProcessor"
59
- }
60
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Vision-OPD-Qwen3-VL-4B-Instruct-bbox-oracle/step13/tokenizer.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
3
- size 11422650
 
 
 
 
Vision-OPD-Qwen3-VL-4B-Instruct-bbox-oracle/step13/tokenizer_config.json DELETED
@@ -1,30 +0,0 @@
1
- {
2
- "add_prefix_space": false,
3
- "backend": "tokenizers",
4
- "bos_token": null,
5
- "clean_up_tokenization_spaces": false,
6
- "eos_token": "<|im_end|>",
7
- "errors": "replace",
8
- "extra_special_tokens": [
9
- "<|im_start|>",
10
- "<|im_end|>",
11
- "<|object_ref_start|>",
12
- "<|object_ref_end|>",
13
- "<|box_start|>",
14
- "<|box_end|>",
15
- "<|quad_start|>",
16
- "<|quad_end|>",
17
- "<|vision_start|>",
18
- "<|vision_end|>",
19
- "<|vision_pad|>",
20
- "<|image_pad|>",
21
- "<|video_pad|>"
22
- ],
23
- "is_local": true,
24
- "model_max_length": 262144,
25
- "pad_token": "<|endoftext|>",
26
- "processor_class": "Qwen3VLProcessor",
27
- "split_special_tokens": false,
28
- "tokenizer_class": "Qwen2Tokenizer",
29
- "unk_token": null
30
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Vision-OPD-Qwen3-VL-4B-Instruct-bbox-oracle/step26/chat_template.jinja DELETED
@@ -1,120 +0,0 @@
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 %}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Vision-OPD-Qwen3-VL-4B-Instruct-bbox-oracle/step26/config.json DELETED
@@ -1,69 +0,0 @@
1
- {
2
- "architectures": [
3
- "Qwen3VLForConditionalGeneration"
4
- ],
5
- "bos_token_id": null,
6
- "dtype": "float32",
7
- "eos_token_id": 151645,
8
- "image_token_id": 151655,
9
- "model_type": "qwen3_vl",
10
- "pad_token_id": 151643,
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": 2560,
20
- "initializer_range": 0.02,
21
- "intermediate_size": 9728,
22
- "max_position_embeddings": 262144,
23
- "model_type": "qwen3_vl_text",
24
- "num_attention_heads": 32,
25
- "num_hidden_layers": 36,
26
- "num_key_value_heads": 8,
27
- "pad_token_id": null,
28
- "rms_norm_eps": 1e-06,
29
- "rope_parameters": {
30
- "mrope_interleaved": true,
31
- "mrope_section": [
32
- 24,
33
- 20,
34
- 20
35
- ],
36
- "rope_theta": 5000000,
37
- "rope_type": "default"
38
- },
39
- "tie_word_embeddings": true,
40
- "use_cache": true,
41
- "vocab_size": 151936
42
- },
43
- "tie_word_embeddings": true,
44
- "transformers_version": "5.5.0",
45
- "video_token_id": 151656,
46
- "vision_config": {
47
- "deepstack_visual_indexes": [
48
- 5,
49
- 11,
50
- 17
51
- ],
52
- "depth": 24,
53
- "dtype": "bfloat16",
54
- "hidden_act": "gelu_pytorch_tanh",
55
- "hidden_size": 1024,
56
- "in_channels": 3,
57
- "initializer_range": 0.02,
58
- "intermediate_size": 4096,
59
- "model_type": "qwen3_vl",
60
- "num_heads": 16,
61
- "num_position_embeddings": 2304,
62
- "out_hidden_size": 2560,
63
- "patch_size": 16,
64
- "spatial_merge_size": 2,
65
- "temporal_patch_size": 2
66
- },
67
- "vision_end_token_id": 151653,
68
- "vision_start_token_id": 151652
69
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Vision-OPD-Qwen3-VL-4B-Instruct-bbox-oracle/step26/generation_config.json DELETED
@@ -1,14 +0,0 @@
1
- {
2
- "bos_token_id": 151643,
3
- "do_sample": true,
4
- "eos_token_id": [
5
- 151645,
6
- 151643
7
- ],
8
- "pad_token_id": 151643,
9
- "repetition_penalty": 1.0,
10
- "temperature": 0.7,
11
- "top_k": 20,
12
- "top_p": 0.8,
13
- "transformers_version": "5.5.0"
14
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Vision-OPD-Qwen3-VL-4B-Instruct-bbox-oracle/step26/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9a8c2fee59d12d484e0c6328bedab13e485bbd9c2093f19b87954f1031dfbc66
3
- size 9653631848
 
 
 
 
Vision-OPD-Qwen3-VL-4B-Instruct-bbox-oracle/step26/processor_config.json DELETED
@@ -1,60 +0,0 @@
1
- {
2
- "image_processor": {
3
- "do_convert_rgb": true,
4
- "do_normalize": true,
5
- "do_rescale": true,
6
- "do_resize": true,
7
- "image_mean": [
8
- 0.5,
9
- 0.5,
10
- 0.5
11
- ],
12
- "image_processor_type": "Qwen2VLImageProcessor",
13
- "image_std": [
14
- 0.5,
15
- 0.5,
16
- 0.5
17
- ],
18
- "merge_size": 2,
19
- "patch_size": 16,
20
- "resample": 3,
21
- "rescale_factor": 0.00392156862745098,
22
- "size": {
23
- "longest_edge": 16777216,
24
- "shortest_edge": 65536
25
- },
26
- "temporal_patch_size": 2
27
- },
28
- "processor_class": "Qwen3VLProcessor",
29
- "video_processor": {
30
- "do_convert_rgb": true,
31
- "do_normalize": true,
32
- "do_rescale": true,
33
- "do_resize": true,
34
- "do_sample_frames": true,
35
- "fps": 2,
36
- "image_mean": [
37
- 0.5,
38
- 0.5,
39
- 0.5
40
- ],
41
- "image_std": [
42
- 0.5,
43
- 0.5,
44
- 0.5
45
- ],
46
- "max_frames": 768,
47
- "merge_size": 2,
48
- "min_frames": 4,
49
- "patch_size": 16,
50
- "resample": 3,
51
- "rescale_factor": 0.00392156862745098,
52
- "return_metadata": false,
53
- "size": {
54
- "longest_edge": 25165824,
55
- "shortest_edge": 4096
56
- },
57
- "temporal_patch_size": 2,
58
- "video_processor_type": "Qwen3VLVideoProcessor"
59
- }
60
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Vision-OPD-Qwen3-VL-4B-Instruct-bbox-oracle/step26/tokenizer.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
3
- size 11422650
 
 
 
 
Vision-OPD-Qwen3-VL-4B-Instruct-bbox-oracle/step26/tokenizer_config.json DELETED
@@ -1,30 +0,0 @@
1
- {
2
- "add_prefix_space": false,
3
- "backend": "tokenizers",
4
- "bos_token": null,
5
- "clean_up_tokenization_spaces": false,
6
- "eos_token": "<|im_end|>",
7
- "errors": "replace",
8
- "extra_special_tokens": [
9
- "<|im_start|>",
10
- "<|im_end|>",
11
- "<|object_ref_start|>",
12
- "<|object_ref_end|>",
13
- "<|box_start|>",
14
- "<|box_end|>",
15
- "<|quad_start|>",
16
- "<|quad_end|>",
17
- "<|vision_start|>",
18
- "<|vision_end|>",
19
- "<|vision_pad|>",
20
- "<|image_pad|>",
21
- "<|video_pad|>"
22
- ],
23
- "is_local": true,
24
- "model_max_length": 262144,
25
- "pad_token": "<|endoftext|>",
26
- "processor_class": "Qwen3VLProcessor",
27
- "split_special_tokens": false,
28
- "tokenizer_class": "Qwen2Tokenizer",
29
- "unk_token": null
30
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Vision-OPD-Qwen3-VL-4B-Instruct-bbox-oracle/step39/chat_template.jinja DELETED
@@ -1,120 +0,0 @@
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 %}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Vision-OPD-Qwen3-VL-4B-Instruct-bbox-oracle/step39/config.json DELETED
@@ -1,69 +0,0 @@
1
- {
2
- "architectures": [
3
- "Qwen3VLForConditionalGeneration"
4
- ],
5
- "bos_token_id": null,
6
- "dtype": "float32",
7
- "eos_token_id": 151645,
8
- "image_token_id": 151655,
9
- "model_type": "qwen3_vl",
10
- "pad_token_id": 151643,
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": 2560,
20
- "initializer_range": 0.02,
21
- "intermediate_size": 9728,
22
- "max_position_embeddings": 262144,
23
- "model_type": "qwen3_vl_text",
24
- "num_attention_heads": 32,
25
- "num_hidden_layers": 36,
26
- "num_key_value_heads": 8,
27
- "pad_token_id": null,
28
- "rms_norm_eps": 1e-06,
29
- "rope_parameters": {
30
- "mrope_interleaved": true,
31
- "mrope_section": [
32
- 24,
33
- 20,
34
- 20
35
- ],
36
- "rope_theta": 5000000,
37
- "rope_type": "default"
38
- },
39
- "tie_word_embeddings": true,
40
- "use_cache": true,
41
- "vocab_size": 151936
42
- },
43
- "tie_word_embeddings": true,
44
- "transformers_version": "5.5.0",
45
- "video_token_id": 151656,
46
- "vision_config": {
47
- "deepstack_visual_indexes": [
48
- 5,
49
- 11,
50
- 17
51
- ],
52
- "depth": 24,
53
- "dtype": "bfloat16",
54
- "hidden_act": "gelu_pytorch_tanh",
55
- "hidden_size": 1024,
56
- "in_channels": 3,
57
- "initializer_range": 0.02,
58
- "intermediate_size": 4096,
59
- "model_type": "qwen3_vl",
60
- "num_heads": 16,
61
- "num_position_embeddings": 2304,
62
- "out_hidden_size": 2560,
63
- "patch_size": 16,
64
- "spatial_merge_size": 2,
65
- "temporal_patch_size": 2
66
- },
67
- "vision_end_token_id": 151653,
68
- "vision_start_token_id": 151652
69
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Vision-OPD-Qwen3-VL-4B-Instruct-bbox-oracle/step39/generation_config.json DELETED
@@ -1,14 +0,0 @@
1
- {
2
- "bos_token_id": 151643,
3
- "do_sample": true,
4
- "eos_token_id": [
5
- 151645,
6
- 151643
7
- ],
8
- "pad_token_id": 151643,
9
- "repetition_penalty": 1.0,
10
- "temperature": 0.7,
11
- "top_k": 20,
12
- "top_p": 0.8,
13
- "transformers_version": "5.5.0"
14
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Vision-OPD-Qwen3-VL-4B-Instruct-bbox-oracle/step39/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d148a548f0cefbff26669f27506680a9c89688997838497684186b501da492d7
3
- size 9653631848
 
 
 
 
Vision-OPD-Qwen3-VL-4B-Instruct-bbox-oracle/step39/processor_config.json DELETED
@@ -1,60 +0,0 @@
1
- {
2
- "image_processor": {
3
- "do_convert_rgb": true,
4
- "do_normalize": true,
5
- "do_rescale": true,
6
- "do_resize": true,
7
- "image_mean": [
8
- 0.5,
9
- 0.5,
10
- 0.5
11
- ],
12
- "image_processor_type": "Qwen2VLImageProcessor",
13
- "image_std": [
14
- 0.5,
15
- 0.5,
16
- 0.5
17
- ],
18
- "merge_size": 2,
19
- "patch_size": 16,
20
- "resample": 3,
21
- "rescale_factor": 0.00392156862745098,
22
- "size": {
23
- "longest_edge": 16777216,
24
- "shortest_edge": 65536
25
- },
26
- "temporal_patch_size": 2
27
- },
28
- "processor_class": "Qwen3VLProcessor",
29
- "video_processor": {
30
- "do_convert_rgb": true,
31
- "do_normalize": true,
32
- "do_rescale": true,
33
- "do_resize": true,
34
- "do_sample_frames": true,
35
- "fps": 2,
36
- "image_mean": [
37
- 0.5,
38
- 0.5,
39
- 0.5
40
- ],
41
- "image_std": [
42
- 0.5,
43
- 0.5,
44
- 0.5
45
- ],
46
- "max_frames": 768,
47
- "merge_size": 2,
48
- "min_frames": 4,
49
- "patch_size": 16,
50
- "resample": 3,
51
- "rescale_factor": 0.00392156862745098,
52
- "return_metadata": false,
53
- "size": {
54
- "longest_edge": 25165824,
55
- "shortest_edge": 4096
56
- },
57
- "temporal_patch_size": 2,
58
- "video_processor_type": "Qwen3VLVideoProcessor"
59
- }
60
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
Vision-OPD-Qwen3-VL-4B-Instruct-bbox-oracle/step39/tokenizer.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
3
- size 11422650
 
 
 
 
Vision-OPD-Qwen3-VL-4B-Instruct-bbox-oracle/step39/tokenizer_config.json DELETED
@@ -1,30 +0,0 @@
1
- {
2
- "add_prefix_space": false,
3
- "backend": "tokenizers",
4
- "bos_token": null,
5
- "clean_up_tokenization_spaces": false,
6
- "eos_token": "<|im_end|>",
7
- "errors": "replace",
8
- "extra_special_tokens": [
9
- "<|im_start|>",
10
- "<|im_end|>",
11
- "<|object_ref_start|>",
12
- "<|object_ref_end|>",
13
- "<|box_start|>",
14
- "<|box_end|>",
15
- "<|quad_start|>",
16
- "<|quad_end|>",
17
- "<|vision_start|>",
18
- "<|vision_end|>",
19
- "<|vision_pad|>",
20
- "<|image_pad|>",
21
- "<|video_pad|>"
22
- ],
23
- "is_local": true,
24
- "model_max_length": 262144,
25
- "pad_token": "<|endoftext|>",
26
- "processor_class": "Qwen3VLProcessor",
27
- "split_special_tokens": false,
28
- "tokenizer_class": "Qwen2Tokenizer",
29
- "unk_token": null
30
- }