Hugging Face's logo

Xingyu-Zheng
/
Qwen3.5-9B-GLM5.1-Distill-v1-INT4-FOEM

Image-Text-to-Text
Safetensors
English
Chinese
qwen3_5
unsloth
qwen
qwen3.5
reasoning
chain-of-thought
Dense
vLLM
SGLang
conversational
4-bit precision
gptq
Model card Files
xet
 Community
Xingyu-Zheng commited on
Commit
13d0bf9
·
verified ·
1 Parent(s): 4e1596f

Upload folder using huggingface_hub

Browse files
Files changed (12) hide show
  1. .gitattributes +1 -0
  2. chat_template.jinja +88 -0
  3. config.json +170 -0
  4. generation_config.json +10 -0
  5. model-00001-of-00003.safetensors +3 -0
  6. model-00002-of-00003.safetensors +3 -0
  7. model-00003-of-00003.safetensors +3 -0
  8. model.safetensors.index.json +0 -0
  9. processor_config.json +63 -0
  10. quantize_config.json +51 -0
  11. tokenizer.json +3 -0
  12. tokenizer_config.json +34 -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
chat_template.jinja ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0].role == 'system' %}
4
+ {{- messages[0].content + '\n\n' }}
5
+ {%- endif %}
6
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
7
+ {%- for tool in tools %}
8
+ {{- "\n" }}
9
+ {{- tool | tojson }}
10
+ {%- endfor %}
11
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
12
+ {%- else %}
13
+ {%- if messages[0].role == 'system' %}
14
+ {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
+ {%- endif %}
16
+ {%- endif %}
17
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
18
+ {%- for message in messages[::-1] %}
19
+ {%- set index = (messages|length - 1) - loop.index0 %}
20
+ {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
21
+ {%- set ns.multi_step_tool = false %}
22
+ {%- set ns.last_query_index = index %}
23
+ {%- endif %}
24
+ {%- endfor %}
25
+ {%- for message in messages %}
26
+ {%- if message.content is string %}
27
+ {%- set content = message.content %}
28
+ {%- else %}
29
+ {%- set content = '' %}
30
+ {%- endif %}
31
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
32
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
33
+ {%- elif message.role == "assistant" %}
34
+ {%- set reasoning_content = '' %}
35
+ {%- if message.reasoning_content is string %}
36
+ {%- set reasoning_content = message.reasoning_content %}
37
+ {%- else %}
38
+ {%- if '</think>' in content %}
39
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
40
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
41
+ {%- endif %}
42
+ {%- endif %}
43
+ {%- if loop.index0 > ns.last_query_index %}
44
+ {%- if loop.last or (not loop.last and reasoning_content) %}
45
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
46
+ {%- else %}
47
+ {{- '<|im_start|>' + message.role + '\n' + content }}
48
+ {%- endif %}
49
+ {%- else %}
50
+ {{- '<|im_start|>' + message.role + '\n' + content }}
51
+ {%- endif %}
52
+ {%- if message.tool_calls %}
53
+ {%- for tool_call in message.tool_calls %}
54
+ {%- if (loop.first and content) or (not loop.first) %}
55
+ {{- '\n' }}
56
+ {%- endif %}
57
+ {%- if tool_call.function %}
58
+ {%- set tool_call = tool_call.function %}
59
+ {%- endif %}
60
+ {{- '<tool_call>\n{"name": "' }}
61
+ {{- tool_call.name }}
62
+ {{- '", "arguments": ' }}
63
+ {%- if tool_call.arguments is string %}
64
+ {{- tool_call.arguments }}
65
+ {%- else %}
66
+ {{- tool_call.arguments | tojson }}
67
+ {%- endif %}
68
+ {{- '}\n</tool_call>' }}
69
+ {%- endfor %}
70
+ {%- endif %}
71
+ {{- '<|im_end|>\n' }}
72
+ {%- elif message.role == "tool" %}
73
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
74
+ {{- '<|im_start|>user' }}
75
+ {%- endif %}
76
+ {{- '\n<tool_response>\n' }}
77
+ {{- content }}
78
+ {{- '\n</tool_response>' }}
79
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
80
+ {{- '<|im_end|>\n' }}
81
+ {%- endif %}
82
+ {%- endif %}
83
+ {%- endfor %}
84
+ {%- if add_generation_prompt %}
85
+ {{- '<|im_start|>assistant
86
+ <think>
87
+ ' }}
88
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,170 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3_5ForConditionalGeneration"
4
+ ],
5
+ "dtype": "bfloat16",
6
+ "eos_token_id": 248046,
7
+ "image_token_id": 248056,
8
+ "model_name": "unsloth/Qwen3.5-9B",
9
+ "model_type": "qwen3_5",
10
+ "pad_token_id": 248055,
11
+ "quantization_config": {
12
+ "bits": 4,
13
+ "checkpoint_format": "gptq",
14
+ "desc_act": false,
15
+ "format": "gptq",
16
+ "group_size": 128,
17
+ "lm_head": false,
18
+ "meta": {
19
+ "act_group_aware": true,
20
+ "auto_forward_data_parallel": true,
21
+ "damp_auto_increment": 0.01,
22
+ "damp_percent": 0.05,
23
+ "dense_vram_strategy": "exclusive",
24
+ "dense_vram_strategy_devices": null,
25
+ "fallback": {
26
+ "smooth": null,
27
+ "strategy": "rtn",
28
+ "threshold": "0.5%"
29
+ },
30
+ "foem": {
31
+ "alpha": 0,
32
+ "beta": 0.2,
33
+ "device": "auto"
34
+ },
35
+ "gc_mode": "interval",
36
+ "gptaq": null,
37
+ "hessian": {
38
+ "chunk_bytes": null,
39
+ "chunk_size": null,
40
+ "staging_dtype": "float32"
41
+ },
42
+ "mock_quantization": false,
43
+ "moe_vram_strategy": "exclusive",
44
+ "moe_vram_strategy_devices": null,
45
+ "mse": 0.0,
46
+ "offload_to_disk": true,
47
+ "offload_to_disk_path": "./gptqmodel_offload/tkjfqxnv-hfdznbuo/",
48
+ "pack_impl": "cpu",
49
+ "quantizer": [
50
+ "gptqmodel:6.1.0-dev"
51
+ ],
52
+ "static_groups": false,
53
+ "true_sequential": true,
54
+ "uri": "https://github.com/modelcloud/gptqmodel",
55
+ "wait_for_submodule_finalizers": false
56
+ },
57
+ "method": "gptq",
58
+ "pack_dtype": "int32",
59
+ "quant_method": "gptq",
60
+ "sym": true
61
+ },
62
+ "rope_parameters": {
63
+ "rope_theta": 10000.0,
64
+ "rope_type": "default"
65
+ },
66
+ "text_config": {
67
+ "attention_bias": false,
68
+ "attention_dropout": 0.0,
69
+ "attn_output_gate": true,
70
+ "bos_token_id": null,
71
+ "dtype": "bfloat16",
72
+ "eos_token_id": 248044,
73
+ "full_attention_interval": 4,
74
+ "head_dim": 256,
75
+ "hidden_act": "silu",
76
+ "hidden_size": 4096,
77
+ "initializer_range": 0.02,
78
+ "intermediate_size": 12288,
79
+ "layer_types": [
80
+ "linear_attention",
81
+ "linear_attention",
82
+ "linear_attention",
83
+ "full_attention",
84
+ "linear_attention",
85
+ "linear_attention",
86
+ "linear_attention",
87
+ "full_attention",
88
+ "linear_attention",
89
+ "linear_attention",
90
+ "linear_attention",
91
+ "full_attention",
92
+ "linear_attention",
93
+ "linear_attention",
94
+ "linear_attention",
95
+ "full_attention",
96
+ "linear_attention",
97
+ "linear_attention",
98
+ "linear_attention",
99
+ "full_attention",
100
+ "linear_attention",
101
+ "linear_attention",
102
+ "linear_attention",
103
+ "full_attention",
104
+ "linear_attention",
105
+ "linear_attention",
106
+ "linear_attention",
107
+ "full_attention",
108
+ "linear_attention",
109
+ "linear_attention",
110
+ "linear_attention",
111
+ "full_attention"
112
+ ],
113
+ "linear_conv_kernel_dim": 4,
114
+ "linear_key_head_dim": 128,
115
+ "linear_num_key_heads": 16,
116
+ "linear_num_value_heads": 32,
117
+ "linear_value_head_dim": 128,
118
+ "mamba_ssm_dtype": "float32",
119
+ "max_position_embeddings": 262144,
120
+ "mlp_only_layers": [],
121
+ "model_type": "qwen3_5_text",
122
+ "mtp_num_hidden_layers": 1,
123
+ "mtp_use_dedicated_embeddings": false,
124
+ "num_attention_heads": 16,
125
+ "num_hidden_layers": 32,
126
+ "num_key_value_heads": 4,
127
+ "pad_token_id": 248055,
128
+ "partial_rotary_factor": 0.25,
129
+ "rms_norm_eps": 1e-06,
130
+ "rope_parameters": {
131
+ "mrope_interleaved": true,
132
+ "mrope_section": [
133
+ 11,
134
+ 11,
135
+ 10
136
+ ],
137
+ "partial_rotary_factor": 0.25,
138
+ "rope_theta": 10000000,
139
+ "rope_type": "default"
140
+ },
141
+ "tie_word_embeddings": false,
142
+ "use_cache": true,
143
+ "vocab_size": 248320
144
+ },
145
+ "tie_word_embeddings": false,
146
+ "transformers_version": "5.5.0.dev0",
147
+ "unsloth_fixed": true,
148
+ "unsloth_version": "2026.4.5",
149
+ "use_cache": false,
150
+ "video_token_id": 248057,
151
+ "vision_config": {
152
+ "deepstack_visual_indexes": [],
153
+ "depth": 27,
154
+ "dtype": "bfloat16",
155
+ "hidden_act": "gelu_pytorch_tanh",
156
+ "hidden_size": 1152,
157
+ "in_channels": 3,
158
+ "initializer_range": 0.02,
159
+ "intermediate_size": 4304,
160
+ "model_type": "qwen3_5",
161
+ "num_heads": 16,
162
+ "num_position_embeddings": 2304,
163
+ "out_hidden_size": 4096,
164
+ "patch_size": 16,
165
+ "spatial_merge_size": 2,
166
+ "temporal_patch_size": 2
167
+ },
168
+ "vision_end_token_id": 248054,
169
+ "vision_start_token_id": 248053
170
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "do_sample": true,
4
+ "eos_token_id": 248046,
5
+ "output_attentions": false,
6
+ "output_hidden_states": false,
7
+ "pad_token_id": 248055,
8
+ "transformers_version": "5.5.0.dev0",
9
+ "use_cache": true
10
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b346f58f43778520d56d0cdd1245faa4c2becc3659b8a5b6e6c3f5338bdd6852
3
+ size 2961030304
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b2c3f2a4de59197fe6daae40a83bf91c5122db4a0f4b067f4e47805279a7bcb
3
+ size 4290723872
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60a9f4bd90914205686e0dce5e052285c34eac05fd79d032190df8cad051b9a3
3
+ size 1339052864
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
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": "Qwen2VLImageProcessor",
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
+ }
quantize_config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bits": 4,
3
+ "group_size": 128,
4
+ "desc_act": false,
5
+ "lm_head": false,
6
+ "method": "gptq",
7
+ "quant_method": "gptq",
8
+ "format": "gptq",
9
+ "checkpoint_format": "gptq",
10
+ "pack_dtype": "int32",
11
+ "meta": {
12
+ "quantizer": [
13
+ "gptqmodel:6.1.0-dev"
14
+ ],
15
+ "uri": "https://github.com/modelcloud/gptqmodel",
16
+ "damp_percent": 0.05,
17
+ "damp_auto_increment": 0.01,
18
+ "static_groups": false,
19
+ "true_sequential": true,
20
+ "mse": 0.0,
21
+ "gptaq": null,
22
+ "foem": {
23
+ "alpha": 0,
24
+ "beta": 0.2,
25
+ "device": "auto"
26
+ },
27
+ "act_group_aware": true,
28
+ "fallback": {
29
+ "strategy": "rtn",
30
+ "threshold": "0.5%",
31
+ "smooth": null
32
+ },
33
+ "offload_to_disk": true,
34
+ "offload_to_disk_path": "./gptqmodel_offload/tkjfqxnv-hfdznbuo/",
35
+ "pack_impl": "cpu",
36
+ "gc_mode": "interval",
37
+ "wait_for_submodule_finalizers": false,
38
+ "auto_forward_data_parallel": true,
39
+ "dense_vram_strategy": "exclusive",
40
+ "dense_vram_strategy_devices": null,
41
+ "moe_vram_strategy": "exclusive",
42
+ "moe_vram_strategy_devices": null,
43
+ "mock_quantization": false,
44
+ "hessian": {
45
+ "chunk_size": null,
46
+ "chunk_bytes": null,
47
+ "staging_dtype": "float32"
48
+ }
49
+ },
50
+ "sym": true
51
+ }
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 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "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": "<|vision_pad|>",
24
+ "padding_side": "right",
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": "TokenizersBackendFast",
29
+ "unk_token": null,
30
+ "video_token": "<|video_pad|>",
31
+ "vision_bos_token": "<|vision_start|>",
32
+ "vision_eos_token": "<|vision_end|>",
33
+ "_commit_hash": null
34
+ }