Hugging Face's logo

gorbatjovy
/
Qwen3.8-27B-Cold-Fusion-GAIN-V1.1-heretic-W4A16

Image-Text-to-Text
Transformers
Safetensors
English
Chinese
qwen3_5
abliterated
uncensored
heretic
qwen
qwen3
qwen3.8
cold-fusion
vision-language
mtp
w4a16
int4
compressed-tensors
vllm
conversational
Model card Files
xet
 Community
1
gorbatjovy commited on
Commit
cb978ab
·
verified ·
1 Parent(s): 79c1181

W4A16 abliterated Cold-Fusion (Heretic)

Browse files
Files changed (20) hide show
  1. .gitattributes +1 -0
  2. README.md +97 -0
  3. chat_template.jinja +170 -0
  4. config.json +450 -0
  5. generation_config.json +13 -0
  6. model-00001-of-00007.safetensors +3 -0
  7. model-00002-of-00007.safetensors +3 -0
  8. model-00003-of-00007.safetensors +3 -0
  9. model-00004-of-00007.safetensors +3 -0
  10. model-00005-of-00007.safetensors +3 -0
  11. model-00006-of-00007.safetensors +3 -0
  12. model-00007-of-00007.safetensors +3 -0
  13. model.safetensors.index.json +0 -0
  14. model_extra_tensors.safetensors +3 -0
  15. preprocessor_config.json +21 -0
  16. processor_config.json +60 -0
  17. quantization_config.json +240 -0
  18. tokenizer.json +3 -0
  19. tokenizer_config.json +34 -0
  20. video_preprocessor_config.json +21 -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
README.md ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model:
4
+ - gorbatjovy/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1-heretic
5
+ base_model_relation: quantized
6
+ pipeline_tag: image-text-to-text
7
+ library_name: transformers
8
+ language:
9
+ - en
10
+ - zh
11
+ tags:
12
+ - abliterated
13
+ - uncensored
14
+ - heretic
15
+ - qwen
16
+ - qwen3
17
+ - qwen3.8
18
+ - cold-fusion
19
+ - vision-language
20
+ - mtp
21
+ - w4a16
22
+ - int4
23
+ - compressed-tensors
24
+ - vllm
25
+ ---
26
+
27
+ # Qwen3.8-27B-Cold-Fusion-GAIN-V1.1-heretic-W4A16
28
+
29
+ **W4A16 (int4) quantization of
30
+ [`gorbatjovy/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1-heretic`](https://huggingface.co/gorbatjovy/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1-heretic)** —
31
+ the Heretic-abliterated build of
32
+ [`DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1`](https://huggingface.co/DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1).
33
+
34
+ Runs the full vision-language model with MTP / DFlash2 speculative decoding on a single **24 GB**
35
+ GPU (e.g. RTX 4090). ~19 GB on disk. Credit for all capability goes to
36
+ [**DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1**](https://huggingface.co/DavidAU/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1);
37
+ this repo only removes refusals and quantizes.
38
+
39
+ ---
40
+
41
+ ## ⚠️ Disclaimer — read before use
42
+
43
+ This model has had its **safety alignment removed** via abliteration. It will comply with
44
+ harmful requests the base model would refuse. Released **for research** (interpretability,
45
+ red-teaming, robustness). **You own what you do with it and what it generates.** Add your own
46
+ moderation before any deployment. Use must comply with the inherited **Apache 2.0** license and
47
+ applicable law. No liability is accepted for misuse.
48
+
49
+ ---
50
+
51
+ ## Quantization
52
+
53
+ Produced with [AutoRound](https://github.com/intel/auto-round), served with
54
+ [compressed-tensors](https://github.com/neuralmagic/compressed-tensors) in vLLM.
55
+
56
+ | Component | Precision |
57
+ |---|---|
58
+ | Language-decoder `Linear` layers | **int4**, group 128, symmetric (W4A16) |
59
+ | `lm_head`, `embed_tokens`, MTP module | **int8**, group 128 |
60
+ | Vision tower (`visual.*`), Gated DeltaNet `in_proj_a`/`in_proj_b` | **BF16** (untouched) |
61
+
62
+ The vision tower and the recurrence controls are kept at BF16 so image understanding and the
63
+ hybrid-attention dynamics are unaffected. Round-trip errors on the int8 steps are 0.6–1.5%.
64
+
65
+ ## Refusal / quality (served build)
66
+
67
+ Measured on **this quantized build**, served under vLLM with an opening-phrase refusal
68
+ classifier:
69
+
70
+ | Benchmark | Refusal |
71
+ |---|---:|
72
+ | AdvBench | **0.0%** |
73
+ | JailbreakBench (harmful) | **0.0%** |
74
+ | MaliciousInstruct | **0.0%** |
75
+
76
+ The underlying abliteration scored **8 / 100** on Heretic's own (stricter) keyword scorer at
77
+ KL divergence **0.0315** vs the base — see the
78
+ [BF16 card](https://huggingface.co/gorbatjovy/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1-heretic) for
79
+ method details. Vision verified working on the quantized build.
80
+
81
+ ## Serving (vLLM)
82
+
83
+ ```bash
84
+ vllm serve gorbatjovy/Qwen3.8-27B-Cold-Fusion-GAIN-V1.1-heretic-W4A16 \
85
+ --served-model-name qwen3.8-27b \
86
+ --max-model-len 32768 \
87
+ --trust-remote-code \
88
+ --reasoning-parser qwen3 \
89
+ --limit-mm-per-prompt '{"image":1}'
90
+ ```
91
+
92
+ Measured ~**142 tok/s** single-stream on an RTX 4090 with DFlash2 speculative decoding
93
+ (mean acceptance length ~3.1). MTP speculative decoding also works out of the box.
94
+
95
+ ## License
96
+
97
+ **Apache 2.0**, inherited. Abliteration and quantization do not change the license.
chat_template.jinja ADDED
@@ -0,0 +1,170 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- set image_count = namespace(value=0) %}
2
+ {%- set video_count = namespace(value=0) %}
3
+ {%- macro render_content(content, do_vision_count, is_system_content=false) %}
4
+ {%- if content is string %}
5
+ {{- content }}
6
+ {%- elif content is iterable and content is not mapping %}
7
+ {%- for item in content %}
8
+ {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
9
+ {%- if is_system_content %}
10
+ {{- raise_exception('System message cannot contain images.') }}
11
+ {%- endif %}
12
+ {%- if do_vision_count %}
13
+ {%- set image_count.value = image_count.value + 1 %}
14
+ {%- endif %}
15
+ {%- if add_vision_id %}
16
+ {{- 'Picture ' ~ image_count.value ~ ': ' }}
17
+ {%- endif %}
18
+ {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
19
+ {%- elif 'video' in item or item.type == 'video' %}
20
+ {%- if is_system_content %}
21
+ {{- raise_exception('System message cannot contain videos.') }}
22
+ {%- endif %}
23
+ {%- if do_vision_count %}
24
+ {%- set video_count.value = video_count.value + 1 %}
25
+ {%- endif %}
26
+ {%- if add_vision_id %}
27
+ {{- 'Video ' ~ video_count.value ~ ': ' }}
28
+ {%- endif %}
29
+ {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
30
+ {%- elif 'text' in item %}
31
+ {{- item.text }}
32
+ {%- else %}
33
+ {{- raise_exception('Unexpected item type in content.') }}
34
+ {%- endif %}
35
+ {%- endfor %}
36
+ {%- elif content is none or content is undefined %}
37
+ {{- '' }}
38
+ {%- else %}
39
+ {{- raise_exception('Unexpected content type.') }}
40
+ {%- endif %}
41
+ {%- endmacro %}
42
+ {%- if not messages %}
43
+ {{- raise_exception('No messages provided.') }}
44
+ {%- endif %}
45
+ {%- set reasoning_instructions = '' %}
46
+ {%- if enable_thinking is undefined or enable_thinking is true %}
47
+ {%- set resolved_reasoning_effort = reasoning_effort|default('xhigh') %}
48
+ {%- if resolved_reasoning_effort not in ('xhigh', 'medium', 'low') %}
49
+ {{- raise_exception('Unexpected reasoning effort ' ~ reasoning_effort ~ '. Supported types are xhigh (default), medium, and low.') }}
50
+ {%- endif %}
51
+ {%- if resolved_reasoning_effort == 'xhigh' %}
52
+ {%- set reasoning_instructions = 'Reasoning effort is set to xhigh. Please think carefully through the task, validate key assumptions, consider plausible alternatives, and prioritize correctness, consistency, and clarity in the final answer.' %}
53
+ {%- elif resolved_reasoning_effort == 'low' %}
54
+ {%- set reasoning_instructions = 'Reasoning effort is set to low. Keep your thinking brief and focused, moving directly to the conclusion without unnecessary elaboration.' %}
55
+ {%- endif %}
56
+ {%- endif %}
57
+ {%- if tools and tools is iterable and tools is not mapping %}
58
+ {{- '<|im_start|>system\n' }}
59
+ {%- if reasoning_instructions %}
60
+ {{- reasoning_instructions + '\n\n' }}
61
+ {%- endif %}
62
+ {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
63
+ {%- for tool in tools %}
64
+ {{- "\n" }}
65
+ {{- tool | tojson }}
66
+ {%- endfor %}
67
+ {{- "\n</tools>" }}
68
+ {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
69
+ {%- if messages[0].role == 'system' %}
70
+ {%- set content = render_content(messages[0].content, false, true)|trim %}
71
+ {%- if content %}
72
+ {{- '\n\n' + content }}
73
+ {%- endif %}
74
+ {%- endif %}
75
+ {{- '<|im_end|>\n' }}
76
+ {%- else %}
77
+ {%- if messages[0].role == 'system' %}
78
+ {%- set content = render_content(messages[0].content, false, true)|trim %}
79
+ {%- if content %}
80
+ {{- '<|im_start|>system\n' + (reasoning_instructions + '\n\n' if reasoning_instructions else '') + content + '<|im_end|>\n' }}
81
+ {%- elif reasoning_instructions %}
82
+ {{- '<|im_start|>system\n' + reasoning_instructions + '<|im_end|>\n' }}
83
+ {%- endif %}
84
+ {%- elif reasoning_instructions %}
85
+ {{- '<|im_start|>system\n' + reasoning_instructions + '<|im_end|>\n' }}
86
+ {%- endif %}
87
+ {%- endif %}
88
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
89
+ {%- for message in messages[::-1] %}
90
+ {%- set index = (messages|length - 1) - loop.index0 %}
91
+ {%- if ns.multi_step_tool and message.role == "user" %}
92
+ {%- set content = render_content(message.content, false)|trim %}
93
+ {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
94
+ {%- set ns.multi_step_tool = false %}
95
+ {%- set ns.last_query_index = index %}
96
+ {%- endif %}
97
+ {%- endif %}
98
+ {%- endfor %}
99
+ {%- if ns.multi_step_tool %}
100
+ {{- raise_exception('No user query found in messages.') }}
101
+ {%- endif %}
102
+ {%- for message in messages %}
103
+ {%- set content = render_content(message.content, true)|trim %}
104
+ {%- if message.role == "system" %}
105
+ {%- if not loop.first %}
106
+ {{- raise_exception('System message must be at the beginning.') }}
107
+ {%- endif %}
108
+ {%- elif message.role == "user" %}
109
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
110
+ {%- elif message.role == "assistant" %}
111
+ {%- set reasoning_content = '' %}
112
+ {%- if message.reasoning_content is string %}
113
+ {%- set reasoning_content = message.reasoning_content %}
114
+ {%- endif %}
115
+ {%- set reasoning_content = reasoning_content|trim %}
116
+ {%- if preserve_thinking is undefined or preserve_thinking is true or loop.index0 > ns.last_query_index %}
117
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
118
+ {%- else %}
119
+ {{- '<|im_start|>' + message.role + '\n' + content }}
120
+ {%- endif %}
121
+ {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
122
+ {%- for tool_call in message.tool_calls %}
123
+ {%- if tool_call.function is defined %}
124
+ {%- set tool_call = tool_call.function %}
125
+ {%- endif %}
126
+ {%- if loop.first %}
127
+ {%- if content|trim %}
128
+ {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
129
+ {%- else %}
130
+ {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
131
+ {%- endif %}
132
+ {%- else %}
133
+ {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
134
+ {%- endif %}
135
+ {%- if tool_call.arguments is defined and tool_call.arguments != '' %}
136
+ {%- for args_name, args_value in tool_call.arguments|items %}
137
+ {{- '<parameter=' + args_name + '>\n' }}
138
+ {%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}
139
+ {{- args_value }}
140
+ {{- '\n</parameter>\n' }}
141
+ {%- endfor %}
142
+ {%- endif %}
143
+ {{- '</function>\n</tool_call>' }}
144
+ {%- endfor %}
145
+ {%- endif %}
146
+ {{- '<|im_end|>\n' }}
147
+ {%- elif message.role == "tool" %}
148
+ {%- if loop.previtem and loop.previtem.role != "tool" %}
149
+ {{- '<|im_start|>user' }}
150
+ {%- endif %}
151
+ {{- '\n<tool_response>\n' }}
152
+ {{- content }}
153
+ {{- '\n</tool_response>' }}
154
+ {%- if not loop.last and loop.nextitem.role != "tool" %}
155
+ {{- '<|im_end|>\n' }}
156
+ {%- elif loop.last %}
157
+ {{- '<|im_end|>\n' }}
158
+ {%- endif %}
159
+ {%- else %}
160
+ {{- raise_exception('Unexpected message role.') }}
161
+ {%- endif %}
162
+ {%- endfor %}
163
+ {%- if add_generation_prompt %}
164
+ {{- '<|im_start|>assistant\n' }}
165
+ {%- if enable_thinking is defined and enable_thinking is false %}
166
+ {{- '<think>\n\n</think>\n\n' }}
167
+ {%- else %}
168
+ {{- '<think>\n' }}
169
+ {%- endif %}
170
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,450 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3_5ForConditionalGeneration"
4
+ ],
5
+ "dtype": "bfloat16",
6
+ "image_token_id": 248056,
7
+ "language_model_only": false,
8
+ "model_name": "/mnt/x/Qwen3.8-27B",
9
+ "model_type": "qwen3_5",
10
+ "pad_token_id": 248044,
11
+ "quantization_config": {
12
+ "config_groups": {
13
+ "group_0": {
14
+ "format": "pack-quantized",
15
+ "input_activations": null,
16
+ "output_activations": null,
17
+ "targets": [
18
+ "Linear"
19
+ ],
20
+ "weights": {
21
+ "actorder": null,
22
+ "block_structure": null,
23
+ "dynamic": false,
24
+ "group_size": 128,
25
+ "num_bits": 4,
26
+ "observer": "memoryless_minmax",
27
+ "observer_kwargs": {},
28
+ "scale_dtype": null,
29
+ "strategy": "group",
30
+ "symmetric": true,
31
+ "type": "int",
32
+ "zp_dtype": null
33
+ }
34
+ },
35
+ "group_1": {
36
+ "format": "pack-quantized",
37
+ "input_activations": null,
38
+ "output_activations": null,
39
+ "targets": [
40
+ "re:.*lm_head$"
41
+ ],
42
+ "weights": {
43
+ "actorder": null,
44
+ "block_structure": null,
45
+ "dynamic": false,
46
+ "group_size": 128,
47
+ "num_bits": 8,
48
+ "observer": "memoryless_minmax",
49
+ "observer_kwargs": {},
50
+ "scale_dtype": null,
51
+ "strategy": "group",
52
+ "symmetric": true,
53
+ "type": "int",
54
+ "zp_dtype": null
55
+ }
56
+ },
57
+ "group_2": {
58
+ "format": "pack-quantized",
59
+ "input_activations": null,
60
+ "output_activations": null,
61
+ "targets": [
62
+ "re:.*embed_tokens$"
63
+ ],
64
+ "weights": {
65
+ "actorder": null,
66
+ "block_structure": null,
67
+ "dynamic": false,
68
+ "group_size": 128,
69
+ "num_bits": 8,
70
+ "observer": "memoryless_minmax",
71
+ "observer_kwargs": {},
72
+ "scale_dtype": null,
73
+ "strategy": "group",
74
+ "symmetric": true,
75
+ "type": "int",
76
+ "zp_dtype": null
77
+ }
78
+ },
79
+ "group_3": {
80
+ "format": "pack-quantized",
81
+ "input_activations": null,
82
+ "output_activations": null,
83
+ "targets": [
84
+ "re:^mtp\\..*"
85
+ ],
86
+ "weights": {
87
+ "actorder": null,
88
+ "block_structure": null,
89
+ "dynamic": false,
90
+ "group_size": 128,
91
+ "num_bits": 8,
92
+ "observer": "memoryless_minmax",
93
+ "observer_kwargs": {},
94
+ "scale_dtype": null,
95
+ "strategy": "group",
96
+ "symmetric": true,
97
+ "type": "int",
98
+ "zp_dtype": null
99
+ }
100
+ }
101
+ },
102
+ "format": "pack-quantized",
103
+ "global_compression_ratio": null,
104
+ "ignore": [
105
+ "model.language_model.layers.0.linear_attn.in_proj_a",
106
+ "model.language_model.layers.0.linear_attn.in_proj_b",
107
+ "model.language_model.layers.1.linear_attn.in_proj_a",
108
+ "model.language_model.layers.1.linear_attn.in_proj_b",
109
+ "model.language_model.layers.10.linear_attn.in_proj_a",
110
+ "model.language_model.layers.10.linear_attn.in_proj_b",
111
+ "model.language_model.layers.12.linear_attn.in_proj_a",
112
+ "model.language_model.layers.12.linear_attn.in_proj_b",
113
+ "model.language_model.layers.13.linear_attn.in_proj_a",
114
+ "model.language_model.layers.13.linear_attn.in_proj_b",
115
+ "model.language_model.layers.14.linear_attn.in_proj_a",
116
+ "model.language_model.layers.14.linear_attn.in_proj_b",
117
+ "model.language_model.layers.16.linear_attn.in_proj_a",
118
+ "model.language_model.layers.16.linear_attn.in_proj_b",
119
+ "model.language_model.layers.17.linear_attn.in_proj_a",
120
+ "model.language_model.layers.17.linear_attn.in_proj_b",
121
+ "model.language_model.layers.18.linear_attn.in_proj_a",
122
+ "model.language_model.layers.18.linear_attn.in_proj_b",
123
+ "model.language_model.layers.2.linear_attn.in_proj_a",
124
+ "model.language_model.layers.2.linear_attn.in_proj_b",
125
+ "model.language_model.layers.20.linear_attn.in_proj_a",
126
+ "model.language_model.layers.20.linear_attn.in_proj_b",
127
+ "model.language_model.layers.21.linear_attn.in_proj_a",
128
+ "model.language_model.layers.21.linear_attn.in_proj_b",
129
+ "model.language_model.layers.22.linear_attn.in_proj_a",
130
+ "model.language_model.layers.22.linear_attn.in_proj_b",
131
+ "model.language_model.layers.24.linear_attn.in_proj_a",
132
+ "model.language_model.layers.24.linear_attn.in_proj_b",
133
+ "model.language_model.layers.25.linear_attn.in_proj_a",
134
+ "model.language_model.layers.25.linear_attn.in_proj_b",
135
+ "model.language_model.layers.26.linear_attn.in_proj_a",
136
+ "model.language_model.layers.26.linear_attn.in_proj_b",
137
+ "model.language_model.layers.28.linear_attn.in_proj_a",
138
+ "model.language_model.layers.28.linear_attn.in_proj_b",
139
+ "model.language_model.layers.29.linear_attn.in_proj_a",
140
+ "model.language_model.layers.29.linear_attn.in_proj_b",
141
+ "model.language_model.layers.30.linear_attn.in_proj_a",
142
+ "model.language_model.layers.30.linear_attn.in_proj_b",
143
+ "model.language_model.layers.32.linear_attn.in_proj_a",
144
+ "model.language_model.layers.32.linear_attn.in_proj_b",
145
+ "model.language_model.layers.33.linear_attn.in_proj_a",
146
+ "model.language_model.layers.33.linear_attn.in_proj_b",
147
+ "model.language_model.layers.34.linear_attn.in_proj_a",
148
+ "model.language_model.layers.34.linear_attn.in_proj_b",
149
+ "model.language_model.layers.36.linear_attn.in_proj_a",
150
+ "model.language_model.layers.36.linear_attn.in_proj_b",
151
+ "model.language_model.layers.37.linear_attn.in_proj_a",
152
+ "model.language_model.layers.37.linear_attn.in_proj_b",
153
+ "model.language_model.layers.38.linear_attn.in_proj_a",
154
+ "model.language_model.layers.38.linear_attn.in_proj_b",
155
+ "model.language_model.layers.4.linear_attn.in_proj_a",
156
+ "model.language_model.layers.4.linear_attn.in_proj_b",
157
+ "model.language_model.layers.40.linear_attn.in_proj_a",
158
+ "model.language_model.layers.40.linear_attn.in_proj_b",
159
+ "model.language_model.layers.41.linear_attn.in_proj_a",
160
+ "model.language_model.layers.41.linear_attn.in_proj_b",
161
+ "model.language_model.layers.42.linear_attn.in_proj_a",
162
+ "model.language_model.layers.42.linear_attn.in_proj_b",
163
+ "model.language_model.layers.44.linear_attn.in_proj_a",
164
+ "model.language_model.layers.44.linear_attn.in_proj_b",
165
+ "model.language_model.layers.45.linear_attn.in_proj_a",
166
+ "model.language_model.layers.45.linear_attn.in_proj_b",
167
+ "model.language_model.layers.46.linear_attn.in_proj_a",
168
+ "model.language_model.layers.46.linear_attn.in_proj_b",
169
+ "model.language_model.layers.48.linear_attn.in_proj_a",
170
+ "model.language_model.layers.48.linear_attn.in_proj_b",
171
+ "model.language_model.layers.49.linear_attn.in_proj_a",
172
+ "model.language_model.layers.49.linear_attn.in_proj_b",
173
+ "model.language_model.layers.5.linear_attn.in_proj_a",
174
+ "model.language_model.layers.5.linear_attn.in_proj_b",
175
+ "model.language_model.layers.50.linear_attn.in_proj_a",
176
+ "model.language_model.layers.50.linear_attn.in_proj_b",
177
+ "model.language_model.layers.52.linear_attn.in_proj_a",
178
+ "model.language_model.layers.52.linear_attn.in_proj_b",
179
+ "model.language_model.layers.53.linear_attn.in_proj_a",
180
+ "model.language_model.layers.53.linear_attn.in_proj_b",
181
+ "model.language_model.layers.54.linear_attn.in_proj_a",
182
+ "model.language_model.layers.54.linear_attn.in_proj_b",
183
+ "model.language_model.layers.56.linear_attn.in_proj_a",
184
+ "model.language_model.layers.56.linear_attn.in_proj_b",
185
+ "model.language_model.layers.57.linear_attn.in_proj_a",
186
+ "model.language_model.layers.57.linear_attn.in_proj_b",
187
+ "model.language_model.layers.58.linear_attn.in_proj_a",
188
+ "model.language_model.layers.58.linear_attn.in_proj_b",
189
+ "model.language_model.layers.6.linear_attn.in_proj_a",
190
+ "model.language_model.layers.6.linear_attn.in_proj_b",
191
+ "model.language_model.layers.60.linear_attn.in_proj_a",
192
+ "model.language_model.layers.60.linear_attn.in_proj_b",
193
+ "model.language_model.layers.61.linear_attn.in_proj_a",
194
+ "model.language_model.layers.61.linear_attn.in_proj_b",
195
+ "model.language_model.layers.62.linear_attn.in_proj_a",
196
+ "model.language_model.layers.62.linear_attn.in_proj_b",
197
+ "model.language_model.layers.8.linear_attn.in_proj_a",
198
+ "model.language_model.layers.8.linear_attn.in_proj_b",
199
+ "model.language_model.layers.9.linear_attn.in_proj_a",
200
+ "model.language_model.layers.9.linear_attn.in_proj_b",
201
+ "model.visual.blocks.0.attn.proj",
202
+ "model.visual.blocks.0.attn.qkv",
203
+ "model.visual.blocks.0.mlp.linear_fc1",
204
+ "model.visual.blocks.0.mlp.linear_fc2",
205
+ "model.visual.blocks.1.attn.proj",
206
+ "model.visual.blocks.1.attn.qkv",
207
+ "model.visual.blocks.1.mlp.linear_fc1",
208
+ "model.visual.blocks.1.mlp.linear_fc2",
209
+ "model.visual.blocks.10.attn.proj",
210
+ "model.visual.blocks.10.attn.qkv",
211
+ "model.visual.blocks.10.mlp.linear_fc1",
212
+ "model.visual.blocks.10.mlp.linear_fc2",
213
+ "model.visual.blocks.11.attn.proj",
214
+ "model.visual.blocks.11.attn.qkv",
215
+ "model.visual.blocks.11.mlp.linear_fc1",
216
+ "model.visual.blocks.11.mlp.linear_fc2",
217
+ "model.visual.blocks.12.attn.proj",
218
+ "model.visual.blocks.12.attn.qkv",
219
+ "model.visual.blocks.12.mlp.linear_fc1",
220
+ "model.visual.blocks.12.mlp.linear_fc2",
221
+ "model.visual.blocks.13.attn.proj",
222
+ "model.visual.blocks.13.attn.qkv",
223
+ "model.visual.blocks.13.mlp.linear_fc1",
224
+ "model.visual.blocks.13.mlp.linear_fc2",
225
+ "model.visual.blocks.14.attn.proj",
226
+ "model.visual.blocks.14.attn.qkv",
227
+ "model.visual.blocks.14.mlp.linear_fc1",
228
+ "model.visual.blocks.14.mlp.linear_fc2",
229
+ "model.visual.blocks.15.attn.proj",
230
+ "model.visual.blocks.15.attn.qkv",
231
+ "model.visual.blocks.15.mlp.linear_fc1",
232
+ "model.visual.blocks.15.mlp.linear_fc2",
233
+ "model.visual.blocks.16.attn.proj",
234
+ "model.visual.blocks.16.attn.qkv",
235
+ "model.visual.blocks.16.mlp.linear_fc1",
236
+ "model.visual.blocks.16.mlp.linear_fc2",
237
+ "model.visual.blocks.17.attn.proj",
238
+ "model.visual.blocks.17.attn.qkv",
239
+ "model.visual.blocks.17.mlp.linear_fc1",
240
+ "model.visual.blocks.17.mlp.linear_fc2",
241
+ "model.visual.blocks.18.attn.proj",
242
+ "model.visual.blocks.18.attn.qkv",
243
+ "model.visual.blocks.18.mlp.linear_fc1",
244
+ "model.visual.blocks.18.mlp.linear_fc2",
245
+ "model.visual.blocks.19.attn.proj",
246
+ "model.visual.blocks.19.attn.qkv",
247
+ "model.visual.blocks.19.mlp.linear_fc1",
248
+ "model.visual.blocks.19.mlp.linear_fc2",
249
+ "model.visual.blocks.2.attn.proj",
250
+ "model.visual.blocks.2.attn.qkv",
251
+ "model.visual.blocks.2.mlp.linear_fc1",
252
+ "model.visual.blocks.2.mlp.linear_fc2",
253
+ "model.visual.blocks.20.attn.proj",
254
+ "model.visual.blocks.20.attn.qkv",
255
+ "model.visual.blocks.20.mlp.linear_fc1",
256
+ "model.visual.blocks.20.mlp.linear_fc2",
257
+ "model.visual.blocks.21.attn.proj",
258
+ "model.visual.blocks.21.attn.qkv",
259
+ "model.visual.blocks.21.mlp.linear_fc1",
260
+ "model.visual.blocks.21.mlp.linear_fc2",
261
+ "model.visual.blocks.22.attn.proj",
262
+ "model.visual.blocks.22.attn.qkv",
263
+ "model.visual.blocks.22.mlp.linear_fc1",
264
+ "model.visual.blocks.22.mlp.linear_fc2",
265
+ "model.visual.blocks.23.attn.proj",
266
+ "model.visual.blocks.23.attn.qkv",
267
+ "model.visual.blocks.23.mlp.linear_fc1",
268
+ "model.visual.blocks.23.mlp.linear_fc2",
269
+ "model.visual.blocks.24.attn.proj",
270
+ "model.visual.blocks.24.attn.qkv",
271
+ "model.visual.blocks.24.mlp.linear_fc1",
272
+ "model.visual.blocks.24.mlp.linear_fc2",
273
+ "model.visual.blocks.25.attn.proj",
274
+ "model.visual.blocks.25.attn.qkv",
275
+ "model.visual.blocks.25.mlp.linear_fc1",
276
+ "model.visual.blocks.25.mlp.linear_fc2",
277
+ "model.visual.blocks.26.attn.proj",
278
+ "model.visual.blocks.26.attn.qkv",
279
+ "model.visual.blocks.26.mlp.linear_fc1",
280
+ "model.visual.blocks.26.mlp.linear_fc2",
281
+ "model.visual.blocks.3.attn.proj",
282
+ "model.visual.blocks.3.attn.qkv",
283
+ "model.visual.blocks.3.mlp.linear_fc1",
284
+ "model.visual.blocks.3.mlp.linear_fc2",
285
+ "model.visual.blocks.4.attn.proj",
286
+ "model.visual.blocks.4.attn.qkv",
287
+ "model.visual.blocks.4.mlp.linear_fc1",
288
+ "model.visual.blocks.4.mlp.linear_fc2",
289
+ "model.visual.blocks.5.attn.proj",
290
+ "model.visual.blocks.5.attn.qkv",
291
+ "model.visual.blocks.5.mlp.linear_fc1",
292
+ "model.visual.blocks.5.mlp.linear_fc2",
293
+ "model.visual.blocks.6.attn.proj",
294
+ "model.visual.blocks.6.attn.qkv",
295
+ "model.visual.blocks.6.mlp.linear_fc1",
296
+ "model.visual.blocks.6.mlp.linear_fc2",
297
+ "model.visual.blocks.7.attn.proj",
298
+ "model.visual.blocks.7.attn.qkv",
299
+ "model.visual.blocks.7.mlp.linear_fc1",
300
+ "model.visual.blocks.7.mlp.linear_fc2",
301
+ "model.visual.blocks.8.attn.proj",
302
+ "model.visual.blocks.8.attn.qkv",
303
+ "model.visual.blocks.8.mlp.linear_fc1",
304
+ "model.visual.blocks.8.mlp.linear_fc2",
305
+ "model.visual.blocks.9.attn.proj",
306
+ "model.visual.blocks.9.attn.qkv",
307
+ "model.visual.blocks.9.mlp.linear_fc1",
308
+ "model.visual.blocks.9.mlp.linear_fc2",
309
+ "model.visual.merger.linear_fc1",
310
+ "model.visual.merger.linear_fc2"
311
+ ],
312
+ "kv_cache_scheme": null,
313
+ "quant_method": "compressed-tensors",
314
+ "quantization_status": "compressed"
315
+ },
316
+ "text_config": {
317
+ "attention_bias": false,
318
+ "attention_dropout": 0.0,
319
+ "attn_output_gate": true,
320
+ "bos_token_id": 248044,
321
+ "dtype": "bfloat16",
322
+ "eos_token_id": 248044,
323
+ "full_attention_interval": 4,
324
+ "head_dim": 256,
325
+ "hidden_act": "silu",
326
+ "hidden_size": 5120,
327
+ "initializer_range": 0.02,
328
+ "intermediate_size": 17408,
329
+ "layer_types": [
330
+ "linear_attention",
331
+ "linear_attention",
332
+ "linear_attention",
333
+ "full_attention",
334
+ "linear_attention",
335
+ "linear_attention",
336
+ "linear_attention",
337
+ "full_attention",
338
+ "linear_attention",
339
+ "linear_attention",
340
+ "linear_attention",
341
+ "full_attention",
342
+ "linear_attention",
343
+ "linear_attention",
344
+ "linear_attention",
345
+ "full_attention",
346
+ "linear_attention",
347
+ "linear_attention",
348
+ "linear_attention",
349
+ "full_attention",
350
+ "linear_attention",
351
+ "linear_attention",
352
+ "linear_attention",
353
+ "full_attention",
354
+ "linear_attention",
355
+ "linear_attention",
356
+ "linear_attention",
357
+ "full_attention",
358
+ "linear_attention",
359
+ "linear_attention",
360
+ "linear_attention",
361
+ "full_attention",
362
+ "linear_attention",
363
+ "linear_attention",
364
+ "linear_attention",
365
+ "full_attention",
366
+ "linear_attention",
367
+ "linear_attention",
368
+ "linear_attention",
369
+ "full_attention",
370
+ "linear_attention",
371
+ "linear_attention",
372
+ "linear_attention",
373
+ "full_attention",
374
+ "linear_attention",
375
+ "linear_attention",
376
+ "linear_attention",
377
+ "full_attention",
378
+ "linear_attention",
379
+ "linear_attention",
380
+ "linear_attention",
381
+ "full_attention",
382
+ "linear_attention",
383
+ "linear_attention",
384
+ "linear_attention",
385
+ "full_attention",
386
+ "linear_attention",
387
+ "linear_attention",
388
+ "linear_attention",
389
+ "full_attention",
390
+ "linear_attention",
391
+ "linear_attention",
392
+ "linear_attention",
393
+ "full_attention"
394
+ ],
395
+ "linear_conv_kernel_dim": 4,
396
+ "linear_key_head_dim": 128,
397
+ "linear_num_key_heads": 16,
398
+ "linear_num_value_heads": 48,
399
+ "linear_value_head_dim": 128,
400
+ "mamba_ssm_dtype": "float32",
401
+ "max_position_embeddings": 262144,
402
+ "model_type": "qwen3_5_text",
403
+ "mtp_num_hidden_layers": 1,
404
+ "mtp_use_dedicated_embeddings": false,
405
+ "num_attention_heads": 24,
406
+ "num_hidden_layers": 64,
407
+ "num_key_value_heads": 4,
408
+ "output_gate_type": "swish",
409
+ "pad_token_id": null,
410
+ "partial_rotary_factor": 0.25,
411
+ "rms_norm_eps": 1e-06,
412
+ "rope_parameters": {
413
+ "mrope_interleaved": true,
414
+ "mrope_section": [
415
+ 11,
416
+ 11,
417
+ 10
418
+ ],
419
+ "partial_rotary_factor": 0.25,
420
+ "rope_theta": 10000000,
421
+ "rope_type": "default"
422
+ },
423
+ "tie_word_embeddings": false,
424
+ "use_cache": false,
425
+ "vocab_size": 248320
426
+ },
427
+ "tie_word_embeddings": false,
428
+ "transformers_version": "5.16.0.dev0",
429
+ "unsloth_version": "2026.7.2",
430
+ "video_token_id": 248057,
431
+ "vision_config": {
432
+ "deepstack_visual_indexes": [],
433
+ "depth": 27,
434
+ "dtype": "bfloat16",
435
+ "hidden_act": "gelu_pytorch_tanh",
436
+ "hidden_size": 1152,
437
+ "in_channels": 3,
438
+ "initializer_range": 0.02,
439
+ "intermediate_size": 4304,
440
+ "model_type": "qwen3_5_vision",
441
+ "num_heads": 16,
442
+ "num_position_embeddings": 2304,
443
+ "out_hidden_size": 5120,
444
+ "patch_size": 16,
445
+ "spatial_merge_size": 2,
446
+ "temporal_patch_size": 2
447
+ },
448
+ "vision_end_token_id": 248054,
449
+ "vision_start_token_id": 248053
450
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 248044,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 248046,
6
+ 248044
7
+ ],
8
+ "pad_token_id": 248044,
9
+ "temperature": 1.0,
10
+ "top_k": 20,
11
+ "top_p": 0.95,
12
+ "transformers_version": "5.16.0.dev0"
13
+ }
model-00001-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76eef8bc20061d0504733255db3ac79291ce547927fe65d1075a1d792f638eb6
3
+ size 3211003472
model-00002-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac1fae6217e84fb9539f8ece4f7a543a751ac67f353baf33e89378ceec41ba9c
3
+ size 3195027104
model-00003-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cabc1b3d4f9dd86e6f92bb42f8b87d2ae1c71a8369adbea861df0c62b258ef5
3
+ size 3195027104
model-00004-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5abdf4e53b8e6bd2eb0e5aec3fcd3b221125154cd7ddca44fe6d4e7063ca9c34
3
+ size 3217442568
model-00005-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0994bb8d91c07ceefc4bfffd3a7b7fd110cc9bd3ce865bdcb2821abf02a02fab
3
+ size 699275200
model-00006-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c1274a7544fcc9c786f9ee35f7bec1ff51d95c7878a252f89244fa863701622
3
+ size 1291274752
model-00007-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce55d80ec123bac872f2ff27eb39b2c11d50ede0b0e272656738b628b7f496a9
3
+ size 1291264320
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
model_extra_tensors.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29ae11082aa57044f50f0a4d3664e4499896abe252e32d8081a133d941104f06
3
+ size 431364472
preprocessor_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "size": {
3
+ "longest_edge": 16777216,
4
+ "shortest_edge": 65536
5
+ },
6
+ "patch_size": 16,
7
+ "temporal_patch_size": 2,
8
+ "merge_size": 2,
9
+ "image_mean": [
10
+ 0.5,
11
+ 0.5,
12
+ 0.5
13
+ ],
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "processor_class": "Qwen3VLProcessor",
20
+ "image_processor_type": "Qwen2VLImageProcessorFast"
21
+ }
processor_config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ }
quantization_config.json ADDED
@@ -0,0 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "config_groups": {
3
+ "group_0": {
4
+ "targets": [
5
+ "Linear"
6
+ ],
7
+ "weights": {
8
+ "num_bits": 4,
9
+ "type": "int",
10
+ "symmetric": true,
11
+ "group_size": 128,
12
+ "strategy": "group",
13
+ "block_structure": null,
14
+ "dynamic": false,
15
+ "actorder": null,
16
+ "scale_dtype": null,
17
+ "zp_dtype": null,
18
+ "observer": "memoryless_minmax",
19
+ "observer_kwargs": {}
20
+ },
21
+ "input_activations": null,
22
+ "output_activations": null,
23
+ "format": "pack-quantized"
24
+ }
25
+ },
26
+ "quant_method": "compressed-tensors",
27
+ "kv_cache_scheme": null,
28
+ "format": "pack-quantized",
29
+ "quantization_status": "compressed",
30
+ "global_compression_ratio": null,
31
+ "ignore": [
32
+ "model.visual.blocks.0.attn.qkv",
33
+ "model.visual.blocks.0.attn.proj",
34
+ "model.visual.blocks.0.mlp.linear_fc1",
35
+ "model.visual.blocks.0.mlp.linear_fc2",
36
+ "model.visual.blocks.1.attn.qkv",
37
+ "model.visual.blocks.1.attn.proj",
38
+ "model.visual.blocks.1.mlp.linear_fc1",
39
+ "model.visual.blocks.1.mlp.linear_fc2",
40
+ "model.visual.blocks.2.attn.qkv",
41
+ "model.visual.blocks.2.attn.proj",
42
+ "model.visual.blocks.2.mlp.linear_fc1",
43
+ "model.visual.blocks.2.mlp.linear_fc2",
44
+ "model.visual.blocks.3.attn.qkv",
45
+ "model.visual.blocks.3.attn.proj",
46
+ "model.visual.blocks.3.mlp.linear_fc1",
47
+ "model.visual.blocks.3.mlp.linear_fc2",
48
+ "model.visual.blocks.4.attn.qkv",
49
+ "model.visual.blocks.4.attn.proj",
50
+ "model.visual.blocks.4.mlp.linear_fc1",
51
+ "model.visual.blocks.4.mlp.linear_fc2",
52
+ "model.visual.blocks.5.attn.qkv",
53
+ "model.visual.blocks.5.attn.proj",
54
+ "model.visual.blocks.5.mlp.linear_fc1",
55
+ "model.visual.blocks.5.mlp.linear_fc2",
56
+ "model.visual.blocks.6.attn.qkv",
57
+ "model.visual.blocks.6.attn.proj",
58
+ "model.visual.blocks.6.mlp.linear_fc1",
59
+ "model.visual.blocks.6.mlp.linear_fc2",
60
+ "model.visual.blocks.7.attn.qkv",
61
+ "model.visual.blocks.7.attn.proj",
62
+ "model.visual.blocks.7.mlp.linear_fc1",
63
+ "model.visual.blocks.7.mlp.linear_fc2",
64
+ "model.visual.blocks.8.attn.qkv",
65
+ "model.visual.blocks.8.attn.proj",
66
+ "model.visual.blocks.8.mlp.linear_fc1",
67
+ "model.visual.blocks.8.mlp.linear_fc2",
68
+ "model.visual.blocks.9.attn.qkv",
69
+ "model.visual.blocks.9.attn.proj",
70
+ "model.visual.blocks.9.mlp.linear_fc1",
71
+ "model.visual.blocks.9.mlp.linear_fc2",
72
+ "model.visual.blocks.10.attn.qkv",
73
+ "model.visual.blocks.10.attn.proj",
74
+ "model.visual.blocks.10.mlp.linear_fc1",
75
+ "model.visual.blocks.10.mlp.linear_fc2",
76
+ "model.visual.blocks.11.attn.qkv",
77
+ "model.visual.blocks.11.attn.proj",
78
+ "model.visual.blocks.11.mlp.linear_fc1",
79
+ "model.visual.blocks.11.mlp.linear_fc2",
80
+ "model.visual.blocks.12.attn.qkv",
81
+ "model.visual.blocks.12.attn.proj",
82
+ "model.visual.blocks.12.mlp.linear_fc1",
83
+ "model.visual.blocks.12.mlp.linear_fc2",
84
+ "model.visual.blocks.13.attn.qkv",
85
+ "model.visual.blocks.13.attn.proj",
86
+ "model.visual.blocks.13.mlp.linear_fc1",
87
+ "model.visual.blocks.13.mlp.linear_fc2",
88
+ "model.visual.blocks.14.attn.qkv",
89
+ "model.visual.blocks.14.attn.proj",
90
+ "model.visual.blocks.14.mlp.linear_fc1",
91
+ "model.visual.blocks.14.mlp.linear_fc2",
92
+ "model.visual.blocks.15.attn.qkv",
93
+ "model.visual.blocks.15.attn.proj",
94
+ "model.visual.blocks.15.mlp.linear_fc1",
95
+ "model.visual.blocks.15.mlp.linear_fc2",
96
+ "model.visual.blocks.16.attn.qkv",
97
+ "model.visual.blocks.16.attn.proj",
98
+ "model.visual.blocks.16.mlp.linear_fc1",
99
+ "model.visual.blocks.16.mlp.linear_fc2",
100
+ "model.visual.blocks.17.attn.qkv",
101
+ "model.visual.blocks.17.attn.proj",
102
+ "model.visual.blocks.17.mlp.linear_fc1",
103
+ "model.visual.blocks.17.mlp.linear_fc2",
104
+ "model.visual.blocks.18.attn.qkv",
105
+ "model.visual.blocks.18.attn.proj",
106
+ "model.visual.blocks.18.mlp.linear_fc1",
107
+ "model.visual.blocks.18.mlp.linear_fc2",
108
+ "model.visual.blocks.19.attn.qkv",
109
+ "model.visual.blocks.19.attn.proj",
110
+ "model.visual.blocks.19.mlp.linear_fc1",
111
+ "model.visual.blocks.19.mlp.linear_fc2",
112
+ "model.visual.blocks.20.attn.qkv",
113
+ "model.visual.blocks.20.attn.proj",
114
+ "model.visual.blocks.20.mlp.linear_fc1",
115
+ "model.visual.blocks.20.mlp.linear_fc2",
116
+ "model.visual.blocks.21.attn.qkv",
117
+ "model.visual.blocks.21.attn.proj",
118
+ "model.visual.blocks.21.mlp.linear_fc1",
119
+ "model.visual.blocks.21.mlp.linear_fc2",
120
+ "model.visual.blocks.22.attn.qkv",
121
+ "model.visual.blocks.22.attn.proj",
122
+ "model.visual.blocks.22.mlp.linear_fc1",
123
+ "model.visual.blocks.22.mlp.linear_fc2",
124
+ "model.visual.blocks.23.attn.qkv",
125
+ "model.visual.blocks.23.attn.proj",
126
+ "model.visual.blocks.23.mlp.linear_fc1",
127
+ "model.visual.blocks.23.mlp.linear_fc2",
128
+ "model.visual.blocks.24.attn.qkv",
129
+ "model.visual.blocks.24.attn.proj",
130
+ "model.visual.blocks.24.mlp.linear_fc1",
131
+ "model.visual.blocks.24.mlp.linear_fc2",
132
+ "model.visual.blocks.25.attn.qkv",
133
+ "model.visual.blocks.25.attn.proj",
134
+ "model.visual.blocks.25.mlp.linear_fc1",
135
+ "model.visual.blocks.25.mlp.linear_fc2",
136
+ "model.visual.blocks.26.attn.qkv",
137
+ "model.visual.blocks.26.attn.proj",
138
+ "model.visual.blocks.26.mlp.linear_fc1",
139
+ "model.visual.blocks.26.mlp.linear_fc2",
140
+ "model.visual.merger.linear_fc1",
141
+ "model.visual.merger.linear_fc2",
142
+ "model.language_model.layers.0.linear_attn.in_proj_b",
143
+ "model.language_model.layers.0.linear_attn.in_proj_a",
144
+ "model.language_model.layers.1.linear_attn.in_proj_b",
145
+ "model.language_model.layers.1.linear_attn.in_proj_a",
146
+ "model.language_model.layers.2.linear_attn.in_proj_b",
147
+ "model.language_model.layers.2.linear_attn.in_proj_a",
148
+ "model.language_model.layers.4.linear_attn.in_proj_b",
149
+ "model.language_model.layers.4.linear_attn.in_proj_a",
150
+ "model.language_model.layers.5.linear_attn.in_proj_b",
151
+ "model.language_model.layers.5.linear_attn.in_proj_a",
152
+ "model.language_model.layers.6.linear_attn.in_proj_b",
153
+ "model.language_model.layers.6.linear_attn.in_proj_a",
154
+ "model.language_model.layers.8.linear_attn.in_proj_b",
155
+ "model.language_model.layers.8.linear_attn.in_proj_a",
156
+ "model.language_model.layers.9.linear_attn.in_proj_b",
157
+ "model.language_model.layers.9.linear_attn.in_proj_a",
158
+ "model.language_model.layers.10.linear_attn.in_proj_b",
159
+ "model.language_model.layers.10.linear_attn.in_proj_a",
160
+ "model.language_model.layers.12.linear_attn.in_proj_b",
161
+ "model.language_model.layers.12.linear_attn.in_proj_a",
162
+ "model.language_model.layers.13.linear_attn.in_proj_b",
163
+ "model.language_model.layers.13.linear_attn.in_proj_a",
164
+ "model.language_model.layers.14.linear_attn.in_proj_b",
165
+ "model.language_model.layers.14.linear_attn.in_proj_a",
166
+ "model.language_model.layers.16.linear_attn.in_proj_b",
167
+ "model.language_model.layers.16.linear_attn.in_proj_a",
168
+ "model.language_model.layers.17.linear_attn.in_proj_b",
169
+ "model.language_model.layers.17.linear_attn.in_proj_a",
170
+ "model.language_model.layers.18.linear_attn.in_proj_b",
171
+ "model.language_model.layers.18.linear_attn.in_proj_a",
172
+ "model.language_model.layers.20.linear_attn.in_proj_b",
173
+ "model.language_model.layers.20.linear_attn.in_proj_a",
174
+ "model.language_model.layers.21.linear_attn.in_proj_b",
175
+ "model.language_model.layers.21.linear_attn.in_proj_a",
176
+ "model.language_model.layers.22.linear_attn.in_proj_b",
177
+ "model.language_model.layers.22.linear_attn.in_proj_a",
178
+ "model.language_model.layers.24.linear_attn.in_proj_b",
179
+ "model.language_model.layers.24.linear_attn.in_proj_a",
180
+ "model.language_model.layers.25.linear_attn.in_proj_b",
181
+ "model.language_model.layers.25.linear_attn.in_proj_a",
182
+ "model.language_model.layers.26.linear_attn.in_proj_b",
183
+ "model.language_model.layers.26.linear_attn.in_proj_a",
184
+ "model.language_model.layers.28.linear_attn.in_proj_b",
185
+ "model.language_model.layers.28.linear_attn.in_proj_a",
186
+ "model.language_model.layers.29.linear_attn.in_proj_b",
187
+ "model.language_model.layers.29.linear_attn.in_proj_a",
188
+ "model.language_model.layers.30.linear_attn.in_proj_b",
189
+ "model.language_model.layers.30.linear_attn.in_proj_a",
190
+ "model.language_model.layers.32.linear_attn.in_proj_b",
191
+ "model.language_model.layers.32.linear_attn.in_proj_a",
192
+ "model.language_model.layers.33.linear_attn.in_proj_b",
193
+ "model.language_model.layers.33.linear_attn.in_proj_a",
194
+ "model.language_model.layers.34.linear_attn.in_proj_b",
195
+ "model.language_model.layers.34.linear_attn.in_proj_a",
196
+ "model.language_model.layers.36.linear_attn.in_proj_b",
197
+ "model.language_model.layers.36.linear_attn.in_proj_a",
198
+ "model.language_model.layers.37.linear_attn.in_proj_b",
199
+ "model.language_model.layers.37.linear_attn.in_proj_a",
200
+ "model.language_model.layers.38.linear_attn.in_proj_b",
201
+ "model.language_model.layers.38.linear_attn.in_proj_a",
202
+ "model.language_model.layers.40.linear_attn.in_proj_b",
203
+ "model.language_model.layers.40.linear_attn.in_proj_a",
204
+ "model.language_model.layers.41.linear_attn.in_proj_b",
205
+ "model.language_model.layers.41.linear_attn.in_proj_a",
206
+ "model.language_model.layers.42.linear_attn.in_proj_b",
207
+ "model.language_model.layers.42.linear_attn.in_proj_a",
208
+ "model.language_model.layers.44.linear_attn.in_proj_b",
209
+ "model.language_model.layers.44.linear_attn.in_proj_a",
210
+ "model.language_model.layers.45.linear_attn.in_proj_b",
211
+ "model.language_model.layers.45.linear_attn.in_proj_a",
212
+ "model.language_model.layers.46.linear_attn.in_proj_b",
213
+ "model.language_model.layers.46.linear_attn.in_proj_a",
214
+ "model.language_model.layers.48.linear_attn.in_proj_b",
215
+ "model.language_model.layers.48.linear_attn.in_proj_a",
216
+ "model.language_model.layers.49.linear_attn.in_proj_b",
217
+ "model.language_model.layers.49.linear_attn.in_proj_a",
218
+ "model.language_model.layers.50.linear_attn.in_proj_b",
219
+ "model.language_model.layers.50.linear_attn.in_proj_a",
220
+ "model.language_model.layers.52.linear_attn.in_proj_b",
221
+ "model.language_model.layers.52.linear_attn.in_proj_a",
222
+ "model.language_model.layers.53.linear_attn.in_proj_b",
223
+ "model.language_model.layers.53.linear_attn.in_proj_a",
224
+ "model.language_model.layers.54.linear_attn.in_proj_b",
225
+ "model.language_model.layers.54.linear_attn.in_proj_a",
226
+ "model.language_model.layers.56.linear_attn.in_proj_b",
227
+ "model.language_model.layers.56.linear_attn.in_proj_a",
228
+ "model.language_model.layers.57.linear_attn.in_proj_b",
229
+ "model.language_model.layers.57.linear_attn.in_proj_a",
230
+ "model.language_model.layers.58.linear_attn.in_proj_b",
231
+ "model.language_model.layers.58.linear_attn.in_proj_a",
232
+ "model.language_model.layers.60.linear_attn.in_proj_b",
233
+ "model.language_model.layers.60.linear_attn.in_proj_a",
234
+ "model.language_model.layers.61.linear_attn.in_proj_b",
235
+ "model.language_model.layers.61.linear_attn.in_proj_a",
236
+ "model.language_model.layers.62.linear_attn.in_proj_b",
237
+ "model.language_model.layers.62.linear_attn.in_proj_a",
238
+ "lm_head"
239
+ ]
240
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
3
+ size 19989325
tokenizer_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "audio_bos_token": "<|audio_start|>",
4
+ "audio_eos_token": "<|audio_end|>",
5
+ "audio_token": "<|audio_pad|>",
6
+ "backend": "tokenizers",
7
+ "bos_token": null,
8
+ "clean_up_tokenization_spaces": false,
9
+ "eos_token": "<|im_end|>",
10
+ "errors": "replace",
11
+ "image_token": "<|image_pad|>",
12
+ "is_local": true,
13
+ "local_files_only": false,
14
+ "model_max_length": 262144,
15
+ "model_specific_special_tokens": {
16
+ "audio_bos_token": "<|audio_start|>",
17
+ "audio_eos_token": "<|audio_end|>",
18
+ "audio_token": "<|audio_pad|>",
19
+ "image_token": "<|image_pad|>",
20
+ "video_token": "<|video_pad|>",
21
+ "vision_bos_token": "<|vision_start|>",
22
+ "vision_eos_token": "<|vision_end|>"
23
+ },
24
+ "pad_token": "<|endoftext|>",
25
+ "padding_side": "left",
26
+ "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
27
+ "processor_class": "Qwen3VLProcessor",
28
+ "split_special_tokens": false,
29
+ "tokenizer_class": "Qwen2Tokenizer",
30
+ "unk_token": null,
31
+ "video_token": "<|video_pad|>",
32
+ "vision_bos_token": "<|vision_start|>",
33
+ "vision_eos_token": "<|vision_end|>"
34
+ }
video_preprocessor_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "size": {
3
+ "longest_edge": 25165824,
4
+ "shortest_edge": 4096
5
+ },
6
+ "patch_size": 16,
7
+ "temporal_patch_size": 2,
8
+ "merge_size": 2,
9
+ "image_mean": [
10
+ 0.5,
11
+ 0.5,
12
+ 0.5
13
+ ],
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "processor_class": "Qwen3VLProcessor",
20
+ "video_processor_type": "Qwen3VLVideoProcessor"
21
+ }