Hugging Face's logo

WebScraper991923
/
Test

Safetensors
qwen3_5
4-bit precision
auto-round
Model card Files
xet
 Community
WebScraper991923 commited on
Commit
edeab8a
·
verified ·
1 Parent(s): 13a215c

Clean repository before upload

Browse files
Files changed (22) hide show
  1. .gitattributes +0 -36
  2. README.md +0 -106
  3. chat_template.jinja +0 -154
  4. config.json +0 -545
  5. generation_config.json +0 -13
  6. model-00001-of-00010.safetensors +0 -3
  7. model-00002-of-00010.safetensors +0 -3
  8. model-00003-of-00010.safetensors +0 -3
  9. model-00004-of-00010.safetensors +0 -3
  10. model-00005-of-00010.safetensors +0 -3
  11. model-00006-of-00010.safetensors +0 -3
  12. model-00007-of-00010.safetensors +0 -3
  13. model-00008-of-00010.safetensors +0 -3
  14. model-00009-of-00010.safetensors +0 -0
  15. model-00010-of-00010.safetensors +0 -3
  16. model.safetensors.index.json +0 -0
  17. model_extra_tensors.safetensors +0 -3
  18. preprocessor_config.json +0 -26
  19. processor_config.json +0 -60
  20. quantization_config.json +0 -396
  21. tokenizer.json +0 -3
  22. tokenizer_config.json +0 -33
.gitattributes DELETED
@@ -1,36 +0,0 @@
1
- *.7z filter=lfs diff=lfs merge=lfs -text
2
- *.arrow filter=lfs diff=lfs merge=lfs -text
3
- *.bin filter=lfs diff=lfs merge=lfs -text
4
- *.bz2 filter=lfs diff=lfs merge=lfs -text
5
- *.ckpt filter=lfs diff=lfs merge=lfs -text
6
- *.ftz filter=lfs diff=lfs merge=lfs -text
7
- *.gz filter=lfs diff=lfs merge=lfs -text
8
- *.h5 filter=lfs diff=lfs merge=lfs -text
9
- *.joblib filter=lfs diff=lfs merge=lfs -text
10
- *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
- *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
- *.model filter=lfs diff=lfs merge=lfs -text
13
- *.msgpack filter=lfs diff=lfs merge=lfs -text
14
- *.npy filter=lfs diff=lfs merge=lfs -text
15
- *.npz filter=lfs diff=lfs merge=lfs -text
16
- *.onnx filter=lfs diff=lfs merge=lfs -text
17
- *.ot filter=lfs diff=lfs merge=lfs -text
18
- *.parquet filter=lfs diff=lfs merge=lfs -text
19
- *.pb filter=lfs diff=lfs merge=lfs -text
20
- *.pickle filter=lfs diff=lfs merge=lfs -text
21
- *.pkl filter=lfs diff=lfs merge=lfs -text
22
- *.pt filter=lfs diff=lfs merge=lfs -text
23
- *.pth filter=lfs diff=lfs merge=lfs -text
24
- *.rar filter=lfs diff=lfs merge=lfs -text
25
- *.safetensors filter=lfs diff=lfs merge=lfs -text
26
- saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
- *.tar.* filter=lfs diff=lfs merge=lfs -text
28
- *.tar filter=lfs diff=lfs merge=lfs -text
29
- *.tflite filter=lfs diff=lfs merge=lfs -text
30
- *.tgz filter=lfs diff=lfs merge=lfs -text
31
- *.wasm filter=lfs diff=lfs merge=lfs -text
32
- *.xz 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 DELETED
@@ -1,106 +0,0 @@
1
- ---
2
- base_model:
3
- - Qwen/Qwen3.6-27B
4
- ---
5
- ## Model Details
6
-
7
- This model is a int4 model with group_size 128 of [Qwen/Qwen3.6-27B](https://huggingface.co/Qwen/Qwen3.6-27B) generated by [intel/auto-round](https://github.com/intel/auto-round). Please follow the license of the original model.
8
-
9
- ## vllm Inference Example
10
-
11
- ~~~bash
12
- vllm serve Intel/Qwen3.6-27B-int4-AutoRound --port 8000 --tensor-parallel-size 1 --max-model-len 2048 --reasoning-parser qwen3 --served-model-name qwen --speculative-config '{"method":"qwen3_next_mtp","num_speculative_tokens":2}'
13
-
14
-
15
- curl http://localhost:8000/v1/chat/completions -H "Content-Type: application/json" -d ' {
16
- "model": "qwen",
17
- "messages": [
18
- {"role": "system", "content": "You are a helpful assistant."},
19
- {"role": "user", "content": "Summarize Qwen 3.6 in one sentence."}
20
- ],
21
- "temperature": 1,
22
- "max_tokens": 512
23
- } '
24
-
25
-
26
- ~~~
27
-
28
-
29
-
30
- **Transformers Inference Example**
31
-
32
- ```PYTHON
33
- from transformers import AutoProcessor, Qwen3_5ForConditionalGeneration
34
- model_name
35
- model_name = "Intel/Qwen3.6-27B-int4-AutoRound"
36
- model = Qwen3_5ForConditionalGeneration.from_pretrained(model_name, dtype="auto",
37
- device_map="auto")
38
- processor = AutoProcessor.from_pretrained(model_name)
39
-
40
- messages = [
41
- {
42
- "role": "user",
43
- "content": [
44
- {
45
- "type": "image",
46
- "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
47
- },
48
- {"type": "text", "text": "Describe this image in short."},
49
- ],
50
- }
51
- ]
52
-
53
-
54
- inputs = processor.apply_chat_template(
55
- messages,
56
- tokenize=True,
57
- add_generation_prompt=True,
58
- return_dict=True,
59
- return_tensors="pt"
60
- )
61
- inputs = inputs.to(model.device)
62
-
63
-
64
- generated_ids = model.generate(**inputs, max_new_tokens=128)
65
- generated_ids_trimmed = [
66
- out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
67
- ]
68
- print(processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0])
69
- """
70
- The user wants a short description of the image.
71
-
72
- 1. **Identify the main subjects:** A young woman and a golden retriever dog.
73
- 2. **Identify the setting:** A sandy beach with the ocean in the background. The lighting suggests sunrise or sunset (golden hour).
74
- 3. **Identify the action:** The dog is sitting and lifting its paw to touch the woman's hand (a "high five" or "shake"). The woman is smiling and looking at the dog, holding a treat or just engaging with it.
75
- 4. **Identify details:** The dog is wearing a
76
- """
77
-
78
- ```
79
-
80
- ## Generate the Model
81
-
82
- ```
83
- auto-round "Qwen/Qwen3.6-27B" --output_dir "./Qwen36-int4"
84
- ```
85
-
86
- ## Ethical Considerations and Limitations
87
-
88
- The model can produce factually incorrect output, and should not be relied on to produce factually accurate information. Because of the limitations of the pretrained model and the finetuning datasets, it is possible that this model could generate lewd, biased or otherwise offensive outputs.
89
-
90
- Therefore, before deploying any applications of the model, developers should perform safety testing.
91
-
92
- ## Caveats and Recommendations
93
-
94
- Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model.
95
-
96
- Here are a couple of useful links to learn more about Intel's AI software:
97
-
98
- - [Intel Neural Compressor](https://github.com/intel/neural-compressor)
99
-
100
- ## Disclaimer
101
-
102
- The license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model. Please consult an attorney before using this model for commercial purposes.
103
-
104
- ## Cite
105
-
106
- @article{cheng2023optimize, title={Optimize weight rounding via signed gradient descent for the quantization of llms}, author={Cheng, Wenhua and Zhang, Weiwei and Shen, Haihao and Cai, Yiyang and He, Xin and Lv, Kaokao and Liu, Yi}, journal={arXiv preprint arXiv:2309.05516}, year={2023} }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
chat_template.jinja DELETED
@@ -1,154 +0,0 @@
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
- {%- if tools and tools is iterable and tools is not mapping %}
46
- {{- '<|im_start|>system\n' }}
47
- {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
48
- {%- for tool in tools %}
49
- {{- "\n" }}
50
- {{- tool | tojson }}
51
- {%- endfor %}
52
- {{- "\n</tools>" }}
53
- {{- '\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>' }}
54
- {%- if messages[0].role == 'system' %}
55
- {%- set content = render_content(messages[0].content, false, true)|trim %}
56
- {%- if content %}
57
- {{- '\n\n' + content }}
58
- {%- endif %}
59
- {%- endif %}
60
- {{- '<|im_end|>\n' }}
61
- {%- else %}
62
- {%- if messages[0].role == 'system' %}
63
- {%- set content = render_content(messages[0].content, false, true)|trim %}
64
- {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
65
- {%- endif %}
66
- {%- endif %}
67
- {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
68
- {%- for message in messages[::-1] %}
69
- {%- set index = (messages|length - 1) - loop.index0 %}
70
- {%- if ns.multi_step_tool and message.role == "user" %}
71
- {%- set content = render_content(message.content, false)|trim %}
72
- {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
73
- {%- set ns.multi_step_tool = false %}
74
- {%- set ns.last_query_index = index %}
75
- {%- endif %}
76
- {%- endif %}
77
- {%- endfor %}
78
- {%- if ns.multi_step_tool %}
79
- {{- raise_exception('No user query found in messages.') }}
80
- {%- endif %}
81
- {%- for message in messages %}
82
- {%- set content = render_content(message.content, true)|trim %}
83
- {%- if message.role == "system" %}
84
- {%- if not loop.first %}
85
- {{- raise_exception('System message must be at the beginning.') }}
86
- {%- endif %}
87
- {%- elif message.role == "user" %}
88
- {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
89
- {%- elif message.role == "assistant" %}
90
- {%- set reasoning_content = '' %}
91
- {%- if message.reasoning_content is string %}
92
- {%- set reasoning_content = message.reasoning_content %}
93
- {%- else %}
94
- {%- if '</think>' in content %}
95
- {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
96
- {%- set content = content.split('</think>')[-1].lstrip('\n') %}
97
- {%- endif %}
98
- {%- endif %}
99
- {%- set reasoning_content = reasoning_content|trim %}
100
- {%- if (preserve_thinking is defined and preserve_thinking is true) or (loop.index0 > ns.last_query_index) %}
101
- {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
102
- {%- else %}
103
- {{- '<|im_start|>' + message.role + '\n' + content }}
104
- {%- endif %}
105
- {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
106
- {%- for tool_call in message.tool_calls %}
107
- {%- if tool_call.function is defined %}
108
- {%- set tool_call = tool_call.function %}
109
- {%- endif %}
110
- {%- if loop.first %}
111
- {%- if content|trim %}
112
- {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
113
- {%- else %}
114
- {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
115
- {%- endif %}
116
- {%- else %}
117
- {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
118
- {%- endif %}
119
- {%- if tool_call.arguments is defined %}
120
- {%- for args_name, args_value in tool_call.arguments|items %}
121
- {{- '<parameter=' + args_name + '>\n' }}
122
- {%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}
123
- {{- args_value }}
124
- {{- '\n</parameter>\n' }}
125
- {%- endfor %}
126
- {%- endif %}
127
- {{- '</function>\n</tool_call>' }}
128
- {%- endfor %}
129
- {%- endif %}
130
- {{- '<|im_end|>\n' }}
131
- {%- elif message.role == "tool" %}
132
- {%- if loop.previtem and loop.previtem.role != "tool" %}
133
- {{- '<|im_start|>user' }}
134
- {%- endif %}
135
- {{- '\n<tool_response>\n' }}
136
- {{- content }}
137
- {{- '\n</tool_response>' }}
138
- {%- if not loop.last and loop.nextitem.role != "tool" %}
139
- {{- '<|im_end|>\n' }}
140
- {%- elif loop.last %}
141
- {{- '<|im_end|>\n' }}
142
- {%- endif %}
143
- {%- else %}
144
- {{- raise_exception('Unexpected message role.') }}
145
- {%- endif %}
146
- {%- endfor %}
147
- {%- if add_generation_prompt %}
148
- {{- '<|im_start|>assistant\n' }}
149
- {%- if enable_thinking is defined and enable_thinking is false %}
150
- {{- '<think>\n\n</think>\n\n' }}
151
- {%- else %}
152
- {{- '<think>\n' }}
153
- {%- endif %}
154
- {%- endif %}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
config.json DELETED
@@ -1,545 +0,0 @@
1
- {
2
- "architectures": [
3
- "Qwen3_5ForConditionalGeneration"
4
- ],
5
- "dtype": "bfloat16",
6
- "image_token_id": 248056,
7
- "language_model_only": false,
8
- "model_type": "qwen3_5",
9
- "quantization_config": {
10
- "autoround_version": "0.13.0",
11
- "bits": 4,
12
- "block_name_to_quantize": [
13
- "model.language_model.layers",
14
- "mtp.layers"
15
- ],
16
- "data_type": "int",
17
- "extra_config": {
18
- "model.language_model.layers.0.linear_attn.in_proj_a": {
19
- "bits": 16,
20
- "data_type": "fp"
21
- },
22
- "model.language_model.layers.0.linear_attn.in_proj_b": {
23
- "bits": 16,
24
- "data_type": "fp"
25
- },
26
- "model.language_model.layers.1.linear_attn.in_proj_a": {
27
- "bits": 16,
28
- "data_type": "fp"
29
- },
30
- "model.language_model.layers.1.linear_attn.in_proj_b": {
31
- "bits": 16,
32
- "data_type": "fp"
33
- },
34
- "model.language_model.layers.10.linear_attn.in_proj_a": {
35
- "bits": 16,
36
- "data_type": "fp"
37
- },
38
- "model.language_model.layers.10.linear_attn.in_proj_b": {
39
- "bits": 16,
40
- "data_type": "fp"
41
- },
42
- "model.language_model.layers.12.linear_attn.in_proj_a": {
43
- "bits": 16,
44
- "data_type": "fp"
45
- },
46
- "model.language_model.layers.12.linear_attn.in_proj_b": {
47
- "bits": 16,
48
- "data_type": "fp"
49
- },
50
- "model.language_model.layers.13.linear_attn.in_proj_a": {
51
- "bits": 16,
52
- "data_type": "fp"
53
- },
54
- "model.language_model.layers.13.linear_attn.in_proj_b": {
55
- "bits": 16,
56
- "data_type": "fp"
57
- },
58
- "model.language_model.layers.14.linear_attn.in_proj_a": {
59
- "bits": 16,
60
- "data_type": "fp"
61
- },
62
- "model.language_model.layers.14.linear_attn.in_proj_b": {
63
- "bits": 16,
64
- "data_type": "fp"
65
- },
66
- "model.language_model.layers.16.linear_attn.in_proj_a": {
67
- "bits": 16,
68
- "data_type": "fp"
69
- },
70
- "model.language_model.layers.16.linear_attn.in_proj_b": {
71
- "bits": 16,
72
- "data_type": "fp"
73
- },
74
- "model.language_model.layers.17.linear_attn.in_proj_a": {
75
- "bits": 16,
76
- "data_type": "fp"
77
- },
78
- "model.language_model.layers.17.linear_attn.in_proj_b": {
79
- "bits": 16,
80
- "data_type": "fp"
81
- },
82
- "model.language_model.layers.18.linear_attn.in_proj_a": {
83
- "bits": 16,
84
- "data_type": "fp"
85
- },
86
- "model.language_model.layers.18.linear_attn.in_proj_b": {
87
- "bits": 16,
88
- "data_type": "fp"
89
- },
90
- "model.language_model.layers.2.linear_attn.in_proj_a": {
91
- "bits": 16,
92
- "data_type": "fp"
93
- },
94
- "model.language_model.layers.2.linear_attn.in_proj_b": {
95
- "bits": 16,
96
- "data_type": "fp"
97
- },
98
- "model.language_model.layers.20.linear_attn.in_proj_a": {
99
- "bits": 16,
100
- "data_type": "fp"
101
- },
102
- "model.language_model.layers.20.linear_attn.in_proj_b": {
103
- "bits": 16,
104
- "data_type": "fp"
105
- },
106
- "model.language_model.layers.21.linear_attn.in_proj_a": {
107
- "bits": 16,
108
- "data_type": "fp"
109
- },
110
- "model.language_model.layers.21.linear_attn.in_proj_b": {
111
- "bits": 16,
112
- "data_type": "fp"
113
- },
114
- "model.language_model.layers.22.linear_attn.in_proj_a": {
115
- "bits": 16,
116
- "data_type": "fp"
117
- },
118
- "model.language_model.layers.22.linear_attn.in_proj_b": {
119
- "bits": 16,
120
- "data_type": "fp"
121
- },
122
- "model.language_model.layers.24.linear_attn.in_proj_a": {
123
- "bits": 16,
124
- "data_type": "fp"
125
- },
126
- "model.language_model.layers.24.linear_attn.in_proj_b": {
127
- "bits": 16,
128
- "data_type": "fp"
129
- },
130
- "model.language_model.layers.25.linear_attn.in_proj_a": {
131
- "bits": 16,
132
- "data_type": "fp"
133
- },
134
- "model.language_model.layers.25.linear_attn.in_proj_b": {
135
- "bits": 16,
136
- "data_type": "fp"
137
- },
138
- "model.language_model.layers.26.linear_attn.in_proj_a": {
139
- "bits": 16,
140
- "data_type": "fp"
141
- },
142
- "model.language_model.layers.26.linear_attn.in_proj_b": {
143
- "bits": 16,
144
- "data_type": "fp"
145
- },
146
- "model.language_model.layers.28.linear_attn.in_proj_a": {
147
- "bits": 16,
148
- "data_type": "fp"
149
- },
150
- "model.language_model.layers.28.linear_attn.in_proj_b": {
151
- "bits": 16,
152
- "data_type": "fp"
153
- },
154
- "model.language_model.layers.29.linear_attn.in_proj_a": {
155
- "bits": 16,
156
- "data_type": "fp"
157
- },
158
- "model.language_model.layers.29.linear_attn.in_proj_b": {
159
- "bits": 16,
160
- "data_type": "fp"
161
- },
162
- "model.language_model.layers.30.linear_attn.in_proj_a": {
163
- "bits": 16,
164
- "data_type": "fp"
165
- },
166
- "model.language_model.layers.30.linear_attn.in_proj_b": {
167
- "bits": 16,
168
- "data_type": "fp"
169
- },
170
- "model.language_model.layers.32.linear_attn.in_proj_a": {
171
- "bits": 16,
172
- "data_type": "fp"
173
- },
174
- "model.language_model.layers.32.linear_attn.in_proj_b": {
175
- "bits": 16,
176
- "data_type": "fp"
177
- },
178
- "model.language_model.layers.33.linear_attn.in_proj_a": {
179
- "bits": 16,
180
- "data_type": "fp"
181
- },
182
- "model.language_model.layers.33.linear_attn.in_proj_b": {
183
- "bits": 16,
184
- "data_type": "fp"
185
- },
186
- "model.language_model.layers.34.linear_attn.in_proj_a": {
187
- "bits": 16,
188
- "data_type": "fp"
189
- },
190
- "model.language_model.layers.34.linear_attn.in_proj_b": {
191
- "bits": 16,
192
- "data_type": "fp"
193
- },
194
- "model.language_model.layers.36.linear_attn.in_proj_a": {
195
- "bits": 16,
196
- "data_type": "fp"
197
- },
198
- "model.language_model.layers.36.linear_attn.in_proj_b": {
199
- "bits": 16,
200
- "data_type": "fp"
201
- },
202
- "model.language_model.layers.37.linear_attn.in_proj_a": {
203
- "bits": 16,
204
- "data_type": "fp"
205
- },
206
- "model.language_model.layers.37.linear_attn.in_proj_b": {
207
- "bits": 16,
208
- "data_type": "fp"
209
- },
210
- "model.language_model.layers.38.linear_attn.in_proj_a": {
211
- "bits": 16,
212
- "data_type": "fp"
213
- },
214
- "model.language_model.layers.38.linear_attn.in_proj_b": {
215
- "bits": 16,
216
- "data_type": "fp"
217
- },
218
- "model.language_model.layers.4.linear_attn.in_proj_a": {
219
- "bits": 16,
220
- "data_type": "fp"
221
- },
222
- "model.language_model.layers.4.linear_attn.in_proj_b": {
223
- "bits": 16,
224
- "data_type": "fp"
225
- },
226
- "model.language_model.layers.40.linear_attn.in_proj_a": {
227
- "bits": 16,
228
- "data_type": "fp"
229
- },
230
- "model.language_model.layers.40.linear_attn.in_proj_b": {
231
- "bits": 16,
232
- "data_type": "fp"
233
- },
234
- "model.language_model.layers.41.linear_attn.in_proj_a": {
235
- "bits": 16,
236
- "data_type": "fp"
237
- },
238
- "model.language_model.layers.41.linear_attn.in_proj_b": {
239
- "bits": 16,
240
- "data_type": "fp"
241
- },
242
- "model.language_model.layers.42.linear_attn.in_proj_a": {
243
- "bits": 16,
244
- "data_type": "fp"
245
- },
246
- "model.language_model.layers.42.linear_attn.in_proj_b": {
247
- "bits": 16,
248
- "data_type": "fp"
249
- },
250
- "model.language_model.layers.44.linear_attn.in_proj_a": {
251
- "bits": 16,
252
- "data_type": "fp"
253
- },
254
- "model.language_model.layers.44.linear_attn.in_proj_b": {
255
- "bits": 16,
256
- "data_type": "fp"
257
- },
258
- "model.language_model.layers.45.linear_attn.in_proj_a": {
259
- "bits": 16,
260
- "data_type": "fp"
261
- },
262
- "model.language_model.layers.45.linear_attn.in_proj_b": {
263
- "bits": 16,
264
- "data_type": "fp"
265
- },
266
- "model.language_model.layers.46.linear_attn.in_proj_a": {
267
- "bits": 16,
268
- "data_type": "fp"
269
- },
270
- "model.language_model.layers.46.linear_attn.in_proj_b": {
271
- "bits": 16,
272
- "data_type": "fp"
273
- },
274
- "model.language_model.layers.48.linear_attn.in_proj_a": {
275
- "bits": 16,
276
- "data_type": "fp"
277
- },
278
- "model.language_model.layers.48.linear_attn.in_proj_b": {
279
- "bits": 16,
280
- "data_type": "fp"
281
- },
282
- "model.language_model.layers.49.linear_attn.in_proj_a": {
283
- "bits": 16,
284
- "data_type": "fp"
285
- },
286
- "model.language_model.layers.49.linear_attn.in_proj_b": {
287
- "bits": 16,
288
- "data_type": "fp"
289
- },
290
- "model.language_model.layers.5.linear_attn.in_proj_a": {
291
- "bits": 16,
292
- "data_type": "fp"
293
- },
294
- "model.language_model.layers.5.linear_attn.in_proj_b": {
295
- "bits": 16,
296
- "data_type": "fp"
297
- },
298
- "model.language_model.layers.50.linear_attn.in_proj_a": {
299
- "bits": 16,
300
- "data_type": "fp"
301
- },
302
- "model.language_model.layers.50.linear_attn.in_proj_b": {
303
- "bits": 16,
304
- "data_type": "fp"
305
- },
306
- "model.language_model.layers.52.linear_attn.in_proj_a": {
307
- "bits": 16,
308
- "data_type": "fp"
309
- },
310
- "model.language_model.layers.52.linear_attn.in_proj_b": {
311
- "bits": 16,
312
- "data_type": "fp"
313
- },
314
- "model.language_model.layers.53.linear_attn.in_proj_a": {
315
- "bits": 16,
316
- "data_type": "fp"
317
- },
318
- "model.language_model.layers.53.linear_attn.in_proj_b": {
319
- "bits": 16,
320
- "data_type": "fp"
321
- },
322
- "model.language_model.layers.54.linear_attn.in_proj_a": {
323
- "bits": 16,
324
- "data_type": "fp"
325
- },
326
- "model.language_model.layers.54.linear_attn.in_proj_b": {
327
- "bits": 16,
328
- "data_type": "fp"
329
- },
330
- "model.language_model.layers.56.linear_attn.in_proj_a": {
331
- "bits": 16,
332
- "data_type": "fp"
333
- },
334
- "model.language_model.layers.56.linear_attn.in_proj_b": {
335
- "bits": 16,
336
- "data_type": "fp"
337
- },
338
- "model.language_model.layers.57.linear_attn.in_proj_a": {
339
- "bits": 16,
340
- "data_type": "fp"
341
- },
342
- "model.language_model.layers.57.linear_attn.in_proj_b": {
343
- "bits": 16,
344
- "data_type": "fp"
345
- },
346
- "model.language_model.layers.58.linear_attn.in_proj_a": {
347
- "bits": 16,
348
- "data_type": "fp"
349
- },
350
- "model.language_model.layers.58.linear_attn.in_proj_b": {
351
- "bits": 16,
352
- "data_type": "fp"
353
- },
354
- "model.language_model.layers.6.linear_attn.in_proj_a": {
355
- "bits": 16,
356
- "data_type": "fp"
357
- },
358
- "model.language_model.layers.6.linear_attn.in_proj_b": {
359
- "bits": 16,
360
- "data_type": "fp"
361
- },
362
- "model.language_model.layers.60.linear_attn.in_proj_a": {
363
- "bits": 16,
364
- "data_type": "fp"
365
- },
366
- "model.language_model.layers.60.linear_attn.in_proj_b": {
367
- "bits": 16,
368
- "data_type": "fp"
369
- },
370
- "model.language_model.layers.61.linear_attn.in_proj_a": {
371
- "bits": 16,
372
- "data_type": "fp"
373
- },
374
- "model.language_model.layers.61.linear_attn.in_proj_b": {
375
- "bits": 16,
376
- "data_type": "fp"
377
- },
378
- "model.language_model.layers.62.linear_attn.in_proj_a": {
379
- "bits": 16,
380
- "data_type": "fp"
381
- },
382
- "model.language_model.layers.62.linear_attn.in_proj_b": {
383
- "bits": 16,
384
- "data_type": "fp"
385
- },
386
- "model.language_model.layers.8.linear_attn.in_proj_a": {
387
- "bits": 16,
388
- "data_type": "fp"
389
- },
390
- "model.language_model.layers.8.linear_attn.in_proj_b": {
391
- "bits": 16,
392
- "data_type": "fp"
393
- },
394
- "model.language_model.layers.9.linear_attn.in_proj_a": {
395
- "bits": 16,
396
- "data_type": "fp"
397
- },
398
- "model.language_model.layers.9.linear_attn.in_proj_b": {
399
- "bits": 16,
400
- "data_type": "fp"
401
- },
402
- "mtp.fc": {
403
- "bits": 16,
404
- "data_type": "fp"
405
- }
406
- },
407
- "group_size": 128,
408
- "packing_format": "auto_round:auto_gptq",
409
- "quant_method": "auto-round",
410
- "sym": true
411
- },
412
- "text_config": {
413
- "attention_bias": false,
414
- "attention_dropout": 0.0,
415
- "attn_output_gate": true,
416
- "bos_token_id": 248044,
417
- "dtype": "bfloat16",
418
- "eos_token_id": 248044,
419
- "full_attention_interval": 4,
420
- "head_dim": 256,
421
- "hidden_act": "silu",
422
- "hidden_size": 5120,
423
- "initializer_range": 0.02,
424
- "intermediate_size": 17408,
425
- "layer_types": [
426
- "linear_attention",
427
- "linear_attention",
428
- "linear_attention",
429
- "full_attention",
430
- "linear_attention",
431
- "linear_attention",
432
- "linear_attention",
433
- "full_attention",
434
- "linear_attention",
435
- "linear_attention",
436
- "linear_attention",
437
- "full_attention",
438
- "linear_attention",
439
- "linear_attention",
440
- "linear_attention",
441
- "full_attention",
442
- "linear_attention",
443
- "linear_attention",
444
- "linear_attention",
445
- "full_attention",
446
- "linear_attention",
447
- "linear_attention",
448
- "linear_attention",
449
- "full_attention",
450
- "linear_attention",
451
- "linear_attention",
452
- "linear_attention",
453
- "full_attention",
454
- "linear_attention",
455
- "linear_attention",
456
- "linear_attention",
457
- "full_attention",
458
- "linear_attention",
459
- "linear_attention",
460
- "linear_attention",
461
- "full_attention",
462
- "linear_attention",
463
- "linear_attention",
464
- "linear_attention",
465
- "full_attention",
466
- "linear_attention",
467
- "linear_attention",
468
- "linear_attention",
469
- "full_attention",
470
- "linear_attention",
471
- "linear_attention",
472
- "linear_attention",
473
- "full_attention",
474
- "linear_attention",
475
- "linear_attention",
476
- "linear_attention",
477
- "full_attention",
478
- "linear_attention",
479
- "linear_attention",
480
- "linear_attention",
481
- "full_attention",
482
- "linear_attention",
483
- "linear_attention",
484
- "linear_attention",
485
- "full_attention",
486
- "linear_attention",
487
- "linear_attention",
488
- "linear_attention",
489
- "full_attention"
490
- ],
491
- "linear_conv_kernel_dim": 4,
492
- "linear_key_head_dim": 128,
493
- "linear_num_key_heads": 16,
494
- "linear_num_value_heads": 48,
495
- "linear_value_head_dim": 128,
496
- "mamba_ssm_dtype": "float32",
497
- "max_position_embeddings": 262144,
498
- "model_type": "qwen3_5_text",
499
- "mtp_num_hidden_layers": 1,
500
- "mtp_use_dedicated_embeddings": false,
501
- "num_attention_heads": 24,
502
- "num_hidden_layers": 64,
503
- "num_key_value_heads": 4,
504
- "output_gate_type": "swish",
505
- "pad_token_id": null,
506
- "partial_rotary_factor": 0.25,
507
- "rms_norm_eps": 1e-06,
508
- "rope_parameters": {
509
- "mrope_interleaved": true,
510
- "mrope_section": [
511
- 11,
512
- 11,
513
- 10
514
- ],
515
- "partial_rotary_factor": 0.25,
516
- "rope_theta": 10000000,
517
- "rope_type": "default"
518
- },
519
- "tie_word_embeddings": false,
520
- "use_cache": true,
521
- "vocab_size": 248320
522
- },
523
- "tie_word_embeddings": false,
524
- "transformers_version": "5.6.1",
525
- "video_token_id": 248057,
526
- "vision_config": {
527
- "deepstack_visual_indexes": [],
528
- "depth": 27,
529
- "dtype": "bfloat16",
530
- "hidden_act": "gelu_pytorch_tanh",
531
- "hidden_size": 1152,
532
- "in_channels": 3,
533
- "initializer_range": 0.02,
534
- "intermediate_size": 4304,
535
- "model_type": "qwen3_5_vision",
536
- "num_heads": 16,
537
- "num_position_embeddings": 2304,
538
- "out_hidden_size": 5120,
539
- "patch_size": 16,
540
- "spatial_merge_size": 2,
541
- "temporal_patch_size": 2
542
- },
543
- "vision_end_token_id": 248054,
544
- "vision_start_token_id": 248053
545
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
generation_config.json DELETED
@@ -1,13 +0,0 @@
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": "5.6.1"
13
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
model-00001-of-00010.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:de9849af50d0c49ff68f9790ef803808ab0bfb2ae19c24ecb96d52c877d294a1
3
- size 2139874788
 
 
 
 
model-00002-of-00010.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5a92cab665b9353ad9785c9d3ef6e6f84de014333164638c304c52a44723e148
3
- size 2133383575
 
 
 
 
model-00003-of-00010.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:e8e7772966ca4da1cfbdca73e520ccc66ad2939f1aadddfeef11ba3473a01bea
3
- size 2133383523
 
 
 
 
model-00004-of-00010.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d04504f6b1acde06508dae98b5a23dbb2ba408f2fc50c3c91187274496db575e
3
- size 2125209531
 
 
 
 
model-00005-of-00010.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:98fb8549fc385a714ab65d644ff7af2a0fa635961b59c47970078ff9b5c761fc
3
- size 2133362786
 
 
 
 
model-00006-of-00010.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:388e9ba86050a414be41c79e12ae11974466e356fd00dd03590ec61e4c019145
3
- size 2146938433
 
 
 
 
model-00007-of-00010.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7077b17d639aa9a551f46e2eba2682a5d2d40ff3b668f74812d5104f00827934
3
- size 800645085
 
 
 
 
model-00008-of-00010.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:1312a936ca58c47dce3941403f5d3eb9af24e52652920168bcdb2d0fdd7712e2
3
- size 2542797136
 
 
 
 
model-00009-of-00010.safetensors DELETED
Binary file (10.6 kB)
 
model-00010-of-00010.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:13eb655a0f5940f6c9f9477bb9c4a20443f1d31fea822ec629aa0d677480e2e6
3
- size 2542797101
 
 
 
 
model.safetensors.index.json DELETED
The diff for this file is too large to render. See raw diff
 
model_extra_tensors.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f9ef902c50850de4de8b8dbf2671ab16d1401cb3a03fdacadceae23ed281726
3
- size 298305796
 
 
 
 
preprocessor_config.json DELETED
@@ -1,26 +0,0 @@
1
- {
2
- "do_convert_rgb": true,
3
- "do_normalize": true,
4
- "do_rescale": true,
5
- "do_resize": true,
6
- "image_mean": [
7
- 0.5,
8
- 0.5,
9
- 0.5
10
- ],
11
- "image_processor_type": "Qwen2VLImageProcessor",
12
- "image_std": [
13
- 0.5,
14
- 0.5,
15
- 0.5
16
- ],
17
- "merge_size": 2,
18
- "patch_size": 16,
19
- "resample": 3,
20
- "rescale_factor": 0.00392156862745098,
21
- "size": {
22
- "longest_edge": 16777216,
23
- "shortest_edge": 65536
24
- },
25
- "temporal_patch_size": 2
26
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
quantization_config.json DELETED
@@ -1,396 +0,0 @@
1
- {
2
- "bits": 4,
3
- "data_type": "int",
4
- "group_size": 128,
5
- "sym": true,
6
- "autoround_version": "0.13.0",
7
- "block_name_to_quantize": "model.language_model.layers",
8
- "quant_method": "auto-round",
9
- "packing_format": "auto_round:auto_gptq",
10
- "extra_config": {
11
- "model.language_model.layers.0.linear_attn.in_proj_b": {
12
- "bits": 16,
13
- "data_type": "fp"
14
- },
15
- "model.language_model.layers.0.linear_attn.in_proj_a": {
16
- "bits": 16,
17
- "data_type": "fp"
18
- },
19
- "model.language_model.layers.1.linear_attn.in_proj_b": {
20
- "bits": 16,
21
- "data_type": "fp"
22
- },
23
- "model.language_model.layers.1.linear_attn.in_proj_a": {
24
- "bits": 16,
25
- "data_type": "fp"
26
- },
27
- "model.language_model.layers.2.linear_attn.in_proj_b": {
28
- "bits": 16,
29
- "data_type": "fp"
30
- },
31
- "model.language_model.layers.2.linear_attn.in_proj_a": {
32
- "bits": 16,
33
- "data_type": "fp"
34
- },
35
- "model.language_model.layers.4.linear_attn.in_proj_b": {
36
- "bits": 16,
37
- "data_type": "fp"
38
- },
39
- "model.language_model.layers.4.linear_attn.in_proj_a": {
40
- "bits": 16,
41
- "data_type": "fp"
42
- },
43
- "model.language_model.layers.5.linear_attn.in_proj_b": {
44
- "bits": 16,
45
- "data_type": "fp"
46
- },
47
- "model.language_model.layers.5.linear_attn.in_proj_a": {
48
- "bits": 16,
49
- "data_type": "fp"
50
- },
51
- "model.language_model.layers.6.linear_attn.in_proj_b": {
52
- "bits": 16,
53
- "data_type": "fp"
54
- },
55
- "model.language_model.layers.6.linear_attn.in_proj_a": {
56
- "bits": 16,
57
- "data_type": "fp"
58
- },
59
- "model.language_model.layers.8.linear_attn.in_proj_b": {
60
- "bits": 16,
61
- "data_type": "fp"
62
- },
63
- "model.language_model.layers.8.linear_attn.in_proj_a": {
64
- "bits": 16,
65
- "data_type": "fp"
66
- },
67
- "model.language_model.layers.9.linear_attn.in_proj_b": {
68
- "bits": 16,
69
- "data_type": "fp"
70
- },
71
- "model.language_model.layers.9.linear_attn.in_proj_a": {
72
- "bits": 16,
73
- "data_type": "fp"
74
- },
75
- "model.language_model.layers.10.linear_attn.in_proj_b": {
76
- "bits": 16,
77
- "data_type": "fp"
78
- },
79
- "model.language_model.layers.10.linear_attn.in_proj_a": {
80
- "bits": 16,
81
- "data_type": "fp"
82
- },
83
- "model.language_model.layers.12.linear_attn.in_proj_b": {
84
- "bits": 16,
85
- "data_type": "fp"
86
- },
87
- "model.language_model.layers.12.linear_attn.in_proj_a": {
88
- "bits": 16,
89
- "data_type": "fp"
90
- },
91
- "model.language_model.layers.13.linear_attn.in_proj_b": {
92
- "bits": 16,
93
- "data_type": "fp"
94
- },
95
- "model.language_model.layers.13.linear_attn.in_proj_a": {
96
- "bits": 16,
97
- "data_type": "fp"
98
- },
99
- "model.language_model.layers.14.linear_attn.in_proj_b": {
100
- "bits": 16,
101
- "data_type": "fp"
102
- },
103
- "model.language_model.layers.14.linear_attn.in_proj_a": {
104
- "bits": 16,
105
- "data_type": "fp"
106
- },
107
- "model.language_model.layers.16.linear_attn.in_proj_b": {
108
- "bits": 16,
109
- "data_type": "fp"
110
- },
111
- "model.language_model.layers.16.linear_attn.in_proj_a": {
112
- "bits": 16,
113
- "data_type": "fp"
114
- },
115
- "model.language_model.layers.17.linear_attn.in_proj_b": {
116
- "bits": 16,
117
- "data_type": "fp"
118
- },
119
- "model.language_model.layers.17.linear_attn.in_proj_a": {
120
- "bits": 16,
121
- "data_type": "fp"
122
- },
123
- "model.language_model.layers.18.linear_attn.in_proj_b": {
124
- "bits": 16,
125
- "data_type": "fp"
126
- },
127
- "model.language_model.layers.18.linear_attn.in_proj_a": {
128
- "bits": 16,
129
- "data_type": "fp"
130
- },
131
- "model.language_model.layers.20.linear_attn.in_proj_b": {
132
- "bits": 16,
133
- "data_type": "fp"
134
- },
135
- "model.language_model.layers.20.linear_attn.in_proj_a": {
136
- "bits": 16,
137
- "data_type": "fp"
138
- },
139
- "model.language_model.layers.21.linear_attn.in_proj_b": {
140
- "bits": 16,
141
- "data_type": "fp"
142
- },
143
- "model.language_model.layers.21.linear_attn.in_proj_a": {
144
- "bits": 16,
145
- "data_type": "fp"
146
- },
147
- "model.language_model.layers.22.linear_attn.in_proj_b": {
148
- "bits": 16,
149
- "data_type": "fp"
150
- },
151
- "model.language_model.layers.22.linear_attn.in_proj_a": {
152
- "bits": 16,
153
- "data_type": "fp"
154
- },
155
- "model.language_model.layers.24.linear_attn.in_proj_b": {
156
- "bits": 16,
157
- "data_type": "fp"
158
- },
159
- "model.language_model.layers.24.linear_attn.in_proj_a": {
160
- "bits": 16,
161
- "data_type": "fp"
162
- },
163
- "model.language_model.layers.25.linear_attn.in_proj_b": {
164
- "bits": 16,
165
- "data_type": "fp"
166
- },
167
- "model.language_model.layers.25.linear_attn.in_proj_a": {
168
- "bits": 16,
169
- "data_type": "fp"
170
- },
171
- "model.language_model.layers.26.linear_attn.in_proj_b": {
172
- "bits": 16,
173
- "data_type": "fp"
174
- },
175
- "model.language_model.layers.26.linear_attn.in_proj_a": {
176
- "bits": 16,
177
- "data_type": "fp"
178
- },
179
- "model.language_model.layers.28.linear_attn.in_proj_b": {
180
- "bits": 16,
181
- "data_type": "fp"
182
- },
183
- "model.language_model.layers.28.linear_attn.in_proj_a": {
184
- "bits": 16,
185
- "data_type": "fp"
186
- },
187
- "model.language_model.layers.29.linear_attn.in_proj_b": {
188
- "bits": 16,
189
- "data_type": "fp"
190
- },
191
- "model.language_model.layers.29.linear_attn.in_proj_a": {
192
- "bits": 16,
193
- "data_type": "fp"
194
- },
195
- "model.language_model.layers.30.linear_attn.in_proj_b": {
196
- "bits": 16,
197
- "data_type": "fp"
198
- },
199
- "model.language_model.layers.30.linear_attn.in_proj_a": {
200
- "bits": 16,
201
- "data_type": "fp"
202
- },
203
- "model.language_model.layers.32.linear_attn.in_proj_b": {
204
- "bits": 16,
205
- "data_type": "fp"
206
- },
207
- "model.language_model.layers.32.linear_attn.in_proj_a": {
208
- "bits": 16,
209
- "data_type": "fp"
210
- },
211
- "model.language_model.layers.33.linear_attn.in_proj_b": {
212
- "bits": 16,
213
- "data_type": "fp"
214
- },
215
- "model.language_model.layers.33.linear_attn.in_proj_a": {
216
- "bits": 16,
217
- "data_type": "fp"
218
- },
219
- "model.language_model.layers.34.linear_attn.in_proj_b": {
220
- "bits": 16,
221
- "data_type": "fp"
222
- },
223
- "model.language_model.layers.34.linear_attn.in_proj_a": {
224
- "bits": 16,
225
- "data_type": "fp"
226
- },
227
- "model.language_model.layers.36.linear_attn.in_proj_b": {
228
- "bits": 16,
229
- "data_type": "fp"
230
- },
231
- "model.language_model.layers.36.linear_attn.in_proj_a": {
232
- "bits": 16,
233
- "data_type": "fp"
234
- },
235
- "model.language_model.layers.37.linear_attn.in_proj_b": {
236
- "bits": 16,
237
- "data_type": "fp"
238
- },
239
- "model.language_model.layers.37.linear_attn.in_proj_a": {
240
- "bits": 16,
241
- "data_type": "fp"
242
- },
243
- "model.language_model.layers.38.linear_attn.in_proj_b": {
244
- "bits": 16,
245
- "data_type": "fp"
246
- },
247
- "model.language_model.layers.38.linear_attn.in_proj_a": {
248
- "bits": 16,
249
- "data_type": "fp"
250
- },
251
- "model.language_model.layers.40.linear_attn.in_proj_b": {
252
- "bits": 16,
253
- "data_type": "fp"
254
- },
255
- "model.language_model.layers.40.linear_attn.in_proj_a": {
256
- "bits": 16,
257
- "data_type": "fp"
258
- },
259
- "model.language_model.layers.41.linear_attn.in_proj_b": {
260
- "bits": 16,
261
- "data_type": "fp"
262
- },
263
- "model.language_model.layers.41.linear_attn.in_proj_a": {
264
- "bits": 16,
265
- "data_type": "fp"
266
- },
267
- "model.language_model.layers.42.linear_attn.in_proj_b": {
268
- "bits": 16,
269
- "data_type": "fp"
270
- },
271
- "model.language_model.layers.42.linear_attn.in_proj_a": {
272
- "bits": 16,
273
- "data_type": "fp"
274
- },
275
- "model.language_model.layers.44.linear_attn.in_proj_b": {
276
- "bits": 16,
277
- "data_type": "fp"
278
- },
279
- "model.language_model.layers.44.linear_attn.in_proj_a": {
280
- "bits": 16,
281
- "data_type": "fp"
282
- },
283
- "model.language_model.layers.45.linear_attn.in_proj_b": {
284
- "bits": 16,
285
- "data_type": "fp"
286
- },
287
- "model.language_model.layers.45.linear_attn.in_proj_a": {
288
- "bits": 16,
289
- "data_type": "fp"
290
- },
291
- "model.language_model.layers.46.linear_attn.in_proj_b": {
292
- "bits": 16,
293
- "data_type": "fp"
294
- },
295
- "model.language_model.layers.46.linear_attn.in_proj_a": {
296
- "bits": 16,
297
- "data_type": "fp"
298
- },
299
- "model.language_model.layers.48.linear_attn.in_proj_b": {
300
- "bits": 16,
301
- "data_type": "fp"
302
- },
303
- "model.language_model.layers.48.linear_attn.in_proj_a": {
304
- "bits": 16,
305
- "data_type": "fp"
306
- },
307
- "model.language_model.layers.49.linear_attn.in_proj_b": {
308
- "bits": 16,
309
- "data_type": "fp"
310
- },
311
- "model.language_model.layers.49.linear_attn.in_proj_a": {
312
- "bits": 16,
313
- "data_type": "fp"
314
- },
315
- "model.language_model.layers.50.linear_attn.in_proj_b": {
316
- "bits": 16,
317
- "data_type": "fp"
318
- },
319
- "model.language_model.layers.50.linear_attn.in_proj_a": {
320
- "bits": 16,
321
- "data_type": "fp"
322
- },
323
- "model.language_model.layers.52.linear_attn.in_proj_b": {
324
- "bits": 16,
325
- "data_type": "fp"
326
- },
327
- "model.language_model.layers.52.linear_attn.in_proj_a": {
328
- "bits": 16,
329
- "data_type": "fp"
330
- },
331
- "model.language_model.layers.53.linear_attn.in_proj_b": {
332
- "bits": 16,
333
- "data_type": "fp"
334
- },
335
- "model.language_model.layers.53.linear_attn.in_proj_a": {
336
- "bits": 16,
337
- "data_type": "fp"
338
- },
339
- "model.language_model.layers.54.linear_attn.in_proj_b": {
340
- "bits": 16,
341
- "data_type": "fp"
342
- },
343
- "model.language_model.layers.54.linear_attn.in_proj_a": {
344
- "bits": 16,
345
- "data_type": "fp"
346
- },
347
- "model.language_model.layers.56.linear_attn.in_proj_b": {
348
- "bits": 16,
349
- "data_type": "fp"
350
- },
351
- "model.language_model.layers.56.linear_attn.in_proj_a": {
352
- "bits": 16,
353
- "data_type": "fp"
354
- },
355
- "model.language_model.layers.57.linear_attn.in_proj_b": {
356
- "bits": 16,
357
- "data_type": "fp"
358
- },
359
- "model.language_model.layers.57.linear_attn.in_proj_a": {
360
- "bits": 16,
361
- "data_type": "fp"
362
- },
363
- "model.language_model.layers.58.linear_attn.in_proj_b": {
364
- "bits": 16,
365
- "data_type": "fp"
366
- },
367
- "model.language_model.layers.58.linear_attn.in_proj_a": {
368
- "bits": 16,
369
- "data_type": "fp"
370
- },
371
- "model.language_model.layers.60.linear_attn.in_proj_b": {
372
- "bits": 16,
373
- "data_type": "fp"
374
- },
375
- "model.language_model.layers.60.linear_attn.in_proj_a": {
376
- "bits": 16,
377
- "data_type": "fp"
378
- },
379
- "model.language_model.layers.61.linear_attn.in_proj_b": {
380
- "bits": 16,
381
- "data_type": "fp"
382
- },
383
- "model.language_model.layers.61.linear_attn.in_proj_a": {
384
- "bits": 16,
385
- "data_type": "fp"
386
- },
387
- "model.language_model.layers.62.linear_attn.in_proj_b": {
388
- "bits": 16,
389
- "data_type": "fp"
390
- },
391
- "model.language_model.layers.62.linear_attn.in_proj_a": {
392
- "bits": 16,
393
- "data_type": "fp"
394
- }
395
- }
396
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
tokenizer.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
3
- size 19989325
 
 
 
 
tokenizer_config.json DELETED
@@ -1,33 +0,0 @@
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
- "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+",
26
- "processor_class": "Qwen3VLProcessor",
27
- "split_special_tokens": false,
28
- "tokenizer_class": "Qwen2Tokenizer",
29
- "unk_token": null,
30
- "video_token": "<|video_pad|>",
31
- "vision_bos_token": "<|vision_start|>",
32
- "vision_eos_token": "<|vision_end|>"
33
- }