Hugging Face's logo

apolo13x
/
Qwen3.5-27B-NVFP4

Image-Text-to-Text
Transformers
Safetensors
qwen3_5
quantized
nvfp4
fp4
4-bit precision
vllm
llm-compressor
conversational
8-bit precision
compressed-tensors
Model card Files
xet
 Community
4
Khalil Ben Khaled commited on
Commit
f48cfc8
·
0 Parent(s):

Initial commit

Browse files
Files changed (10) hide show
  1. .gitattributes +36 -0
  2. README.md +50 -0
  3. chat_template.jinja +154 -0
  4. config.json +397 -0
  5. generation_config.json +13 -0
  6. model.safetensors +3 -0
  7. processor_config.json +63 -0
  8. recipe.yaml +7 -0
  9. tokenizer.json +3 -0
  10. tokenizer_config.json +32 -0
.gitattributes ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: transformers
4
+ pipeline_tag: image-text-to-text
5
+ base_model: Qwen/Qwen3.5-27B
6
+ base_model_relation: quantized
7
+ tags:
8
+ - transformers
9
+ - safetensors
10
+ - qwen3_5
11
+ - quantized
12
+ - nvfp4
13
+ - fp4
14
+ - 4-bit
15
+ - vllm
16
+ - llm-compressor
17
+ - image-text-to-text
18
+ - conversational
19
+ datasets:
20
+ - neuralmagic/calibration
21
+ ---
22
+
23
+ # Qwen3.5-27B-NVFP4
24
+
25
+ This is a quantized version of [Qwen/Qwen3.5-27B](https://huggingface.co/Qwen/Qwen3.5-27B). This model accepts text and images as inputs and generates text as outputs. The weights and activations were quantized to FP4 using [llm-compressor](https://github.com/vllm-project/llm-compressor) with 512 calibration samples from [neuralmagic/calibration](https://huggingface.co/datasets/neuralmagic/calibration), reducing the model size from 51.8 GB to 18.4 GB (~2.8x reduction) while maintaining 99.1% average accuracy recovery.
26
+
27
+ ---
28
+
29
+ ## Inference
30
+
31
+ As of 2/27/2026, this model is supported in vLLM nightly. To serve the model:
32
+
33
+ ```bash
34
+ vllm serve Kbenkhaled/Qwen3.5-27B-NVFP4 \
35
+ --reasoning-parser qwen3 \
36
+ --enable-prefix-caching
37
+ ```
38
+
39
+ ---
40
+
41
+ ## Evaluation
42
+
43
+ Evaluated with [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness), 0-shot, thinking mode ON.
44
+
45
+ | Benchmark | Qwen3.5-27B | Qwen3.5-27B-NVFP4 (this model) | Recovery |
46
+ |---|---|---|---|
47
+ | GPQA Diamond | 80.30% | 79.29% | 98.7% |
48
+ | IFEval | 95.08% | 93.88% | 98.7% |
49
+ | MMLU-Redux | 93.90% | 94.32% | 100.4% |
50
+ | **Average** | **89.76%** | **89.16%** | **99.1%** |
chat_template.jinja ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 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 | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
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 ADDED
@@ -0,0 +1,397 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3_5ForConditionalGeneration"
4
+ ],
5
+ "dtype": "bfloat16",
6
+ "image_token_id": 248056,
7
+ "model_type": "qwen3_5",
8
+ "quantization_config": {
9
+ "config_groups": {
10
+ "group_0": {
11
+ "format": "nvfp4-pack-quantized",
12
+ "input_activations": {
13
+ "actorder": null,
14
+ "block_structure": null,
15
+ "dynamic": "local",
16
+ "group_size": 16,
17
+ "num_bits": 4,
18
+ "observer": "static_minmax",
19
+ "observer_kwargs": {},
20
+ "scale_dtype": "torch.float8_e4m3fn",
21
+ "strategy": "tensor_group",
22
+ "symmetric": true,
23
+ "type": "float",
24
+ "zp_dtype": null
25
+ },
26
+ "output_activations": null,
27
+ "targets": [
28
+ "Linear"
29
+ ],
30
+ "weights": {
31
+ "actorder": null,
32
+ "block_structure": null,
33
+ "dynamic": false,
34
+ "group_size": 16,
35
+ "num_bits": 4,
36
+ "observer": "memoryless_minmax",
37
+ "observer_kwargs": {},
38
+ "scale_dtype": "torch.float8_e4m3fn",
39
+ "strategy": "tensor_group",
40
+ "symmetric": true,
41
+ "type": "float",
42
+ "zp_dtype": null
43
+ }
44
+ }
45
+ },
46
+ "format": "nvfp4-pack-quantized",
47
+ "global_compression_ratio": null,
48
+ "ignore": [
49
+ "model.visual.blocks.0.attn.qkv",
50
+ "model.visual.blocks.0.attn.proj",
51
+ "model.visual.blocks.0.mlp.linear_fc1",
52
+ "model.visual.blocks.0.mlp.linear_fc2",
53
+ "model.visual.blocks.1.attn.qkv",
54
+ "model.visual.blocks.1.attn.proj",
55
+ "model.visual.blocks.1.mlp.linear_fc1",
56
+ "model.visual.blocks.1.mlp.linear_fc2",
57
+ "model.visual.blocks.2.attn.qkv",
58
+ "model.visual.blocks.2.attn.proj",
59
+ "model.visual.blocks.2.mlp.linear_fc1",
60
+ "model.visual.blocks.2.mlp.linear_fc2",
61
+ "model.visual.blocks.3.attn.qkv",
62
+ "model.visual.blocks.3.attn.proj",
63
+ "model.visual.blocks.3.mlp.linear_fc1",
64
+ "model.visual.blocks.3.mlp.linear_fc2",
65
+ "model.visual.blocks.4.attn.qkv",
66
+ "model.visual.blocks.4.attn.proj",
67
+ "model.visual.blocks.4.mlp.linear_fc1",
68
+ "model.visual.blocks.4.mlp.linear_fc2",
69
+ "model.visual.blocks.5.attn.qkv",
70
+ "model.visual.blocks.5.attn.proj",
71
+ "model.visual.blocks.5.mlp.linear_fc1",
72
+ "model.visual.blocks.5.mlp.linear_fc2",
73
+ "model.visual.blocks.6.attn.qkv",
74
+ "model.visual.blocks.6.attn.proj",
75
+ "model.visual.blocks.6.mlp.linear_fc1",
76
+ "model.visual.blocks.6.mlp.linear_fc2",
77
+ "model.visual.blocks.7.attn.qkv",
78
+ "model.visual.blocks.7.attn.proj",
79
+ "model.visual.blocks.7.mlp.linear_fc1",
80
+ "model.visual.blocks.7.mlp.linear_fc2",
81
+ "model.visual.blocks.8.attn.qkv",
82
+ "model.visual.blocks.8.attn.proj",
83
+ "model.visual.blocks.8.mlp.linear_fc1",
84
+ "model.visual.blocks.8.mlp.linear_fc2",
85
+ "model.visual.blocks.9.attn.qkv",
86
+ "model.visual.blocks.9.attn.proj",
87
+ "model.visual.blocks.9.mlp.linear_fc1",
88
+ "model.visual.blocks.9.mlp.linear_fc2",
89
+ "model.visual.blocks.10.attn.qkv",
90
+ "model.visual.blocks.10.attn.proj",
91
+ "model.visual.blocks.10.mlp.linear_fc1",
92
+ "model.visual.blocks.10.mlp.linear_fc2",
93
+ "model.visual.blocks.11.attn.qkv",
94
+ "model.visual.blocks.11.attn.proj",
95
+ "model.visual.blocks.11.mlp.linear_fc1",
96
+ "model.visual.blocks.11.mlp.linear_fc2",
97
+ "model.visual.blocks.12.attn.qkv",
98
+ "model.visual.blocks.12.attn.proj",
99
+ "model.visual.blocks.12.mlp.linear_fc1",
100
+ "model.visual.blocks.12.mlp.linear_fc2",
101
+ "model.visual.blocks.13.attn.qkv",
102
+ "model.visual.blocks.13.attn.proj",
103
+ "model.visual.blocks.13.mlp.linear_fc1",
104
+ "model.visual.blocks.13.mlp.linear_fc2",
105
+ "model.visual.blocks.14.attn.qkv",
106
+ "model.visual.blocks.14.attn.proj",
107
+ "model.visual.blocks.14.mlp.linear_fc1",
108
+ "model.visual.blocks.14.mlp.linear_fc2",
109
+ "model.visual.blocks.15.attn.qkv",
110
+ "model.visual.blocks.15.attn.proj",
111
+ "model.visual.blocks.15.mlp.linear_fc1",
112
+ "model.visual.blocks.15.mlp.linear_fc2",
113
+ "model.visual.blocks.16.attn.qkv",
114
+ "model.visual.blocks.16.attn.proj",
115
+ "model.visual.blocks.16.mlp.linear_fc1",
116
+ "model.visual.blocks.16.mlp.linear_fc2",
117
+ "model.visual.blocks.17.attn.qkv",
118
+ "model.visual.blocks.17.attn.proj",
119
+ "model.visual.blocks.17.mlp.linear_fc1",
120
+ "model.visual.blocks.17.mlp.linear_fc2",
121
+ "model.visual.blocks.18.attn.qkv",
122
+ "model.visual.blocks.18.attn.proj",
123
+ "model.visual.blocks.18.mlp.linear_fc1",
124
+ "model.visual.blocks.18.mlp.linear_fc2",
125
+ "model.visual.blocks.19.attn.qkv",
126
+ "model.visual.blocks.19.attn.proj",
127
+ "model.visual.blocks.19.mlp.linear_fc1",
128
+ "model.visual.blocks.19.mlp.linear_fc2",
129
+ "model.visual.blocks.20.attn.qkv",
130
+ "model.visual.blocks.20.attn.proj",
131
+ "model.visual.blocks.20.mlp.linear_fc1",
132
+ "model.visual.blocks.20.mlp.linear_fc2",
133
+ "model.visual.blocks.21.attn.qkv",
134
+ "model.visual.blocks.21.attn.proj",
135
+ "model.visual.blocks.21.mlp.linear_fc1",
136
+ "model.visual.blocks.21.mlp.linear_fc2",
137
+ "model.visual.blocks.22.attn.qkv",
138
+ "model.visual.blocks.22.attn.proj",
139
+ "model.visual.blocks.22.mlp.linear_fc1",
140
+ "model.visual.blocks.22.mlp.linear_fc2",
141
+ "model.visual.blocks.23.attn.qkv",
142
+ "model.visual.blocks.23.attn.proj",
143
+ "model.visual.blocks.23.mlp.linear_fc1",
144
+ "model.visual.blocks.23.mlp.linear_fc2",
145
+ "model.visual.blocks.24.attn.qkv",
146
+ "model.visual.blocks.24.attn.proj",
147
+ "model.visual.blocks.24.mlp.linear_fc1",
148
+ "model.visual.blocks.24.mlp.linear_fc2",
149
+ "model.visual.blocks.25.attn.qkv",
150
+ "model.visual.blocks.25.attn.proj",
151
+ "model.visual.blocks.25.mlp.linear_fc1",
152
+ "model.visual.blocks.25.mlp.linear_fc2",
153
+ "model.visual.blocks.26.attn.qkv",
154
+ "model.visual.blocks.26.attn.proj",
155
+ "model.visual.blocks.26.mlp.linear_fc1",
156
+ "model.visual.blocks.26.mlp.linear_fc2",
157
+ "model.visual.merger.linear_fc1",
158
+ "model.visual.merger.linear_fc2",
159
+ "model.language_model.layers.0.linear_attn.in_proj_b",
160
+ "model.language_model.layers.0.linear_attn.in_proj_a",
161
+ "model.language_model.layers.1.linear_attn.in_proj_b",
162
+ "model.language_model.layers.1.linear_attn.in_proj_a",
163
+ "model.language_model.layers.2.linear_attn.in_proj_b",
164
+ "model.language_model.layers.2.linear_attn.in_proj_a",
165
+ "model.language_model.layers.4.linear_attn.in_proj_b",
166
+ "model.language_model.layers.4.linear_attn.in_proj_a",
167
+ "model.language_model.layers.5.linear_attn.in_proj_b",
168
+ "model.language_model.layers.5.linear_attn.in_proj_a",
169
+ "model.language_model.layers.6.linear_attn.in_proj_b",
170
+ "model.language_model.layers.6.linear_attn.in_proj_a",
171
+ "model.language_model.layers.8.linear_attn.in_proj_b",
172
+ "model.language_model.layers.8.linear_attn.in_proj_a",
173
+ "model.language_model.layers.9.linear_attn.in_proj_b",
174
+ "model.language_model.layers.9.linear_attn.in_proj_a",
175
+ "model.language_model.layers.10.linear_attn.in_proj_b",
176
+ "model.language_model.layers.10.linear_attn.in_proj_a",
177
+ "model.language_model.layers.12.linear_attn.in_proj_b",
178
+ "model.language_model.layers.12.linear_attn.in_proj_a",
179
+ "model.language_model.layers.13.linear_attn.in_proj_b",
180
+ "model.language_model.layers.13.linear_attn.in_proj_a",
181
+ "model.language_model.layers.14.linear_attn.in_proj_b",
182
+ "model.language_model.layers.14.linear_attn.in_proj_a",
183
+ "model.language_model.layers.16.linear_attn.in_proj_b",
184
+ "model.language_model.layers.16.linear_attn.in_proj_a",
185
+ "model.language_model.layers.17.linear_attn.in_proj_b",
186
+ "model.language_model.layers.17.linear_attn.in_proj_a",
187
+ "model.language_model.layers.18.linear_attn.in_proj_b",
188
+ "model.language_model.layers.18.linear_attn.in_proj_a",
189
+ "model.language_model.layers.20.linear_attn.in_proj_b",
190
+ "model.language_model.layers.20.linear_attn.in_proj_a",
191
+ "model.language_model.layers.21.linear_attn.in_proj_b",
192
+ "model.language_model.layers.21.linear_attn.in_proj_a",
193
+ "model.language_model.layers.22.linear_attn.in_proj_b",
194
+ "model.language_model.layers.22.linear_attn.in_proj_a",
195
+ "model.language_model.layers.24.linear_attn.in_proj_b",
196
+ "model.language_model.layers.24.linear_attn.in_proj_a",
197
+ "model.language_model.layers.25.linear_attn.in_proj_b",
198
+ "model.language_model.layers.25.linear_attn.in_proj_a",
199
+ "model.language_model.layers.26.linear_attn.in_proj_b",
200
+ "model.language_model.layers.26.linear_attn.in_proj_a",
201
+ "model.language_model.layers.28.linear_attn.in_proj_b",
202
+ "model.language_model.layers.28.linear_attn.in_proj_a",
203
+ "model.language_model.layers.29.linear_attn.in_proj_b",
204
+ "model.language_model.layers.29.linear_attn.in_proj_a",
205
+ "model.language_model.layers.30.linear_attn.in_proj_b",
206
+ "model.language_model.layers.30.linear_attn.in_proj_a",
207
+ "model.language_model.layers.32.linear_attn.in_proj_b",
208
+ "model.language_model.layers.32.linear_attn.in_proj_a",
209
+ "model.language_model.layers.33.linear_attn.in_proj_b",
210
+ "model.language_model.layers.33.linear_attn.in_proj_a",
211
+ "model.language_model.layers.34.linear_attn.in_proj_b",
212
+ "model.language_model.layers.34.linear_attn.in_proj_a",
213
+ "model.language_model.layers.36.linear_attn.in_proj_b",
214
+ "model.language_model.layers.36.linear_attn.in_proj_a",
215
+ "model.language_model.layers.37.linear_attn.in_proj_b",
216
+ "model.language_model.layers.37.linear_attn.in_proj_a",
217
+ "model.language_model.layers.38.linear_attn.in_proj_b",
218
+ "model.language_model.layers.38.linear_attn.in_proj_a",
219
+ "model.language_model.layers.40.linear_attn.in_proj_b",
220
+ "model.language_model.layers.40.linear_attn.in_proj_a",
221
+ "model.language_model.layers.41.linear_attn.in_proj_b",
222
+ "model.language_model.layers.41.linear_attn.in_proj_a",
223
+ "model.language_model.layers.42.linear_attn.in_proj_b",
224
+ "model.language_model.layers.42.linear_attn.in_proj_a",
225
+ "model.language_model.layers.44.linear_attn.in_proj_b",
226
+ "model.language_model.layers.44.linear_attn.in_proj_a",
227
+ "model.language_model.layers.45.linear_attn.in_proj_b",
228
+ "model.language_model.layers.45.linear_attn.in_proj_a",
229
+ "model.language_model.layers.46.linear_attn.in_proj_b",
230
+ "model.language_model.layers.46.linear_attn.in_proj_a",
231
+ "model.language_model.layers.48.linear_attn.in_proj_b",
232
+ "model.language_model.layers.48.linear_attn.in_proj_a",
233
+ "model.language_model.layers.49.linear_attn.in_proj_b",
234
+ "model.language_model.layers.49.linear_attn.in_proj_a",
235
+ "model.language_model.layers.50.linear_attn.in_proj_b",
236
+ "model.language_model.layers.50.linear_attn.in_proj_a",
237
+ "model.language_model.layers.52.linear_attn.in_proj_b",
238
+ "model.language_model.layers.52.linear_attn.in_proj_a",
239
+ "model.language_model.layers.53.linear_attn.in_proj_b",
240
+ "model.language_model.layers.53.linear_attn.in_proj_a",
241
+ "model.language_model.layers.54.linear_attn.in_proj_b",
242
+ "model.language_model.layers.54.linear_attn.in_proj_a",
243
+ "model.language_model.layers.56.linear_attn.in_proj_b",
244
+ "model.language_model.layers.56.linear_attn.in_proj_a",
245
+ "model.language_model.layers.57.linear_attn.in_proj_b",
246
+ "model.language_model.layers.57.linear_attn.in_proj_a",
247
+ "model.language_model.layers.58.linear_attn.in_proj_b",
248
+ "model.language_model.layers.58.linear_attn.in_proj_a",
249
+ "model.language_model.layers.60.linear_attn.in_proj_b",
250
+ "model.language_model.layers.60.linear_attn.in_proj_a",
251
+ "model.language_model.layers.61.linear_attn.in_proj_b",
252
+ "model.language_model.layers.61.linear_attn.in_proj_a",
253
+ "model.language_model.layers.62.linear_attn.in_proj_b",
254
+ "model.language_model.layers.62.linear_attn.in_proj_a",
255
+ "lm_head"
256
+ ],
257
+ "kv_cache_scheme": null,
258
+ "quant_method": "compressed-tensors",
259
+ "quantization_status": "compressed",
260
+ "sparsity_config": {},
261
+ "transform_config": {},
262
+ "version": "0.13.1.a20260225"
263
+ },
264
+ "text_config": {
265
+ "attention_bias": false,
266
+ "attention_dropout": 0.0,
267
+ "attn_output_gate": true,
268
+ "bos_token_id": null,
269
+ "dtype": "bfloat16",
270
+ "eos_token_id": 248044,
271
+ "full_attention_interval": 4,
272
+ "head_dim": 256,
273
+ "hidden_act": "silu",
274
+ "hidden_size": 5120,
275
+ "initializer_range": 0.02,
276
+ "intermediate_size": 17408,
277
+ "layer_types": [
278
+ "linear_attention",
279
+ "linear_attention",
280
+ "linear_attention",
281
+ "full_attention",
282
+ "linear_attention",
283
+ "linear_attention",
284
+ "linear_attention",
285
+ "full_attention",
286
+ "linear_attention",
287
+ "linear_attention",
288
+ "linear_attention",
289
+ "full_attention",
290
+ "linear_attention",
291
+ "linear_attention",
292
+ "linear_attention",
293
+ "full_attention",
294
+ "linear_attention",
295
+ "linear_attention",
296
+ "linear_attention",
297
+ "full_attention",
298
+ "linear_attention",
299
+ "linear_attention",
300
+ "linear_attention",
301
+ "full_attention",
302
+ "linear_attention",
303
+ "linear_attention",
304
+ "linear_attention",
305
+ "full_attention",
306
+ "linear_attention",
307
+ "linear_attention",
308
+ "linear_attention",
309
+ "full_attention",
310
+ "linear_attention",
311
+ "linear_attention",
312
+ "linear_attention",
313
+ "full_attention",
314
+ "linear_attention",
315
+ "linear_attention",
316
+ "linear_attention",
317
+ "full_attention",
318
+ "linear_attention",
319
+ "linear_attention",
320
+ "linear_attention",
321
+ "full_attention",
322
+ "linear_attention",
323
+ "linear_attention",
324
+ "linear_attention",
325
+ "full_attention",
326
+ "linear_attention",
327
+ "linear_attention",
328
+ "linear_attention",
329
+ "full_attention",
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
+ ],
343
+ "linear_conv_kernel_dim": 4,
344
+ "linear_key_head_dim": 128,
345
+ "linear_num_key_heads": 16,
346
+ "linear_num_value_heads": 48,
347
+ "linear_value_head_dim": 128,
348
+ "mamba_ssm_dtype": "float32",
349
+ "max_position_embeddings": 262144,
350
+ "mlp_only_layers": [],
351
+ "model_type": "qwen3_5_text",
352
+ "mtp_num_hidden_layers": 1,
353
+ "mtp_use_dedicated_embeddings": false,
354
+ "num_attention_heads": 24,
355
+ "num_hidden_layers": 64,
356
+ "num_key_value_heads": 4,
357
+ "pad_token_id": null,
358
+ "partial_rotary_factor": 0.25,
359
+ "rms_norm_eps": 1e-06,
360
+ "rope_parameters": {
361
+ "mrope_interleaved": true,
362
+ "mrope_section": [
363
+ 11,
364
+ 11,
365
+ 10
366
+ ],
367
+ "partial_rotary_factor": 0.25,
368
+ "rope_theta": 10000000,
369
+ "rope_type": "default"
370
+ },
371
+ "tie_word_embeddings": false,
372
+ "use_cache": true,
373
+ "vocab_size": 248320
374
+ },
375
+ "tie_word_embeddings": false,
376
+ "transformers_version": "5.2.0",
377
+ "video_token_id": 248057,
378
+ "vision_config": {
379
+ "deepstack_visual_indexes": [],
380
+ "depth": 27,
381
+ "dtype": "bfloat16",
382
+ "hidden_act": "gelu_pytorch_tanh",
383
+ "hidden_size": 1152,
384
+ "in_channels": 3,
385
+ "initializer_range": 0.02,
386
+ "intermediate_size": 4304,
387
+ "model_type": "qwen3_5",
388
+ "num_heads": 16,
389
+ "num_position_embeddings": 2304,
390
+ "out_hidden_size": 5120,
391
+ "patch_size": 16,
392
+ "spatial_merge_size": 2,
393
+ "temporal_patch_size": 2
394
+ },
395
+ "vision_end_token_id": 248054,
396
+ "vision_start_token_id": 248053
397
+ }
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": 0.6,
10
+ "top_k": 20,
11
+ "top_p": 0.95,
12
+ "transformers_version": "5.2.0"
13
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c978e3b4ea67e74960bc71a7d5ffdb641a0c3555ddda194050d9b2e42f8f676
3
+ size 19743758648
processor_config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_processor": {
3
+ "data_format": "channels_first",
4
+ "do_convert_rgb": true,
5
+ "do_normalize": true,
6
+ "do_rescale": true,
7
+ "do_resize": true,
8
+ "image_mean": [
9
+ 0.5,
10
+ 0.5,
11
+ 0.5
12
+ ],
13
+ "image_processor_type": "Qwen2VLImageProcessorFast",
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "merge_size": 2,
20
+ "patch_size": 16,
21
+ "resample": 3,
22
+ "rescale_factor": 0.00392156862745098,
23
+ "size": {
24
+ "longest_edge": 16777216,
25
+ "shortest_edge": 65536
26
+ },
27
+ "temporal_patch_size": 2
28
+ },
29
+ "processor_class": "Qwen3VLProcessor",
30
+ "video_processor": {
31
+ "data_format": "channels_first",
32
+ "default_to_square": true,
33
+ "do_convert_rgb": true,
34
+ "do_normalize": true,
35
+ "do_rescale": true,
36
+ "do_resize": true,
37
+ "do_sample_frames": true,
38
+ "fps": 2,
39
+ "image_mean": [
40
+ 0.5,
41
+ 0.5,
42
+ 0.5
43
+ ],
44
+ "image_std": [
45
+ 0.5,
46
+ 0.5,
47
+ 0.5
48
+ ],
49
+ "max_frames": 768,
50
+ "merge_size": 2,
51
+ "min_frames": 4,
52
+ "patch_size": 16,
53
+ "resample": 3,
54
+ "rescale_factor": 0.00392156862745098,
55
+ "return_metadata": false,
56
+ "size": {
57
+ "longest_edge": 25165824,
58
+ "shortest_edge": 4096
59
+ },
60
+ "temporal_patch_size": 2,
61
+ "video_processor_type": "Qwen3VLVideoProcessor"
62
+ }
63
+ }
recipe.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ default_stage:
2
+ default_modifiers:
3
+ QuantizationModifier:
4
+ targets: [Linear]
5
+ ignore: [lm_head, 're:.*visual.*', 're:.*in_proj_a$', 're:.*in_proj_b$']
6
+ scheme: NVFP4
7
+ bypass_divisibility_checks: false
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
3
+ size 19989343
tokenizer_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": null,
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": false,
13
+ "model_max_length": 262144,
14
+ "model_specific_special_tokens": {
15
+ "audio_bos_token": "<|audio_start|>",
16
+ "audio_eos_token": "<|audio_end|>",
17
+ "audio_token": "<|audio_pad|>",
18
+ "image_token": "<|image_pad|>",
19
+ "video_token": "<|video_pad|>",
20
+ "vision_bos_token": "<|vision_start|>",
21
+ "vision_eos_token": "<|vision_end|>"
22
+ },
23
+ "pad_token": "<|endoftext|>",
24
+ "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+",
25
+ "processor_class": "Qwen3VLProcessor",
26
+ "split_special_tokens": false,
27
+ "tokenizer_class": "Qwen2Tokenizer",
28
+ "unk_token": null,
29
+ "video_token": "<|video_pad|>",
30
+ "vision_bos_token": "<|vision_start|>",
31
+ "vision_eos_token": "<|vision_end|>"
32
+ }