Hugging Face's logo

aka7774
/
comfyui-models

Diffusers
ONNX
Safetensors
GGUF
Model card Files
xet
 Community
aka7774 commited on
Commit
0b385ec
·
verified ·
1 Parent(s): 24b05c8

Upload folder using huggingface_hub

Browse files
Files changed (20) hide show
  1. .gitattributes +9 -0
  2. onnx/qwen2_5_vl_3b_instruct_ort/chat_template.jinja +7 -0
  3. onnx/qwen2_5_vl_3b_instruct_ort/config.json +131 -0
  4. onnx/qwen2_5_vl_3b_instruct_ort/generation_config.json +13 -0
  5. onnx/qwen2_5_vl_3b_instruct_ort/onnx/decoder_model_merged.onnx +3 -0
  6. onnx/qwen2_5_vl_3b_instruct_ort/onnx/decoder_model_merged.onnx_data +3 -0
  7. onnx/qwen2_5_vl_3b_instruct_ort/onnx/decoder_model_merged.onnx_data_1 +3 -0
  8. onnx/qwen2_5_vl_3b_instruct_ort/onnx/decoder_model_merged.onnx_data_2 +3 -0
  9. onnx/qwen2_5_vl_3b_instruct_ort/onnx/decoder_model_merged.onnx_data_3 +3 -0
  10. onnx/qwen2_5_vl_3b_instruct_ort/onnx/decoder_model_merged.onnx_data_4 +3 -0
  11. onnx/qwen2_5_vl_3b_instruct_ort/onnx/decoder_model_merged.onnx_data_5 +3 -0
  12. onnx/qwen2_5_vl_3b_instruct_ort/onnx/embed_tokens.onnx +3 -0
  13. onnx/qwen2_5_vl_3b_instruct_ort/onnx/embed_tokens.onnx_data +3 -0
  14. onnx/qwen2_5_vl_3b_instruct_ort/onnx/vision_encoder.onnx +3 -0
  15. onnx/qwen2_5_vl_3b_instruct_ort/onnx/vision_encoder.onnx_data +3 -0
  16. onnx/qwen2_5_vl_3b_instruct_ort/onnx/vision_encoder.onnx_data_1 +3 -0
  17. onnx/qwen2_5_vl_3b_instruct_ort/preprocessor_config.json +19 -0
  18. onnx/qwen2_5_vl_3b_instruct_ort/processor_config.json +63 -0
  19. onnx/qwen2_5_vl_3b_instruct_ort/tokenizer.json +0 -0
  20. onnx/qwen2_5_vl_3b_instruct_ort/tokenizer_config.json +31 -0
.gitattributes CHANGED
@@ -71,3 +71,12 @@ llm/GGUF/unsloth/Qwen3.5-27B-GGUF/Qwen3.5-27B-UD-Q4_K_XL.gguf filter=lfs diff=lf
71
  llm/GGUF/unsloth/Qwen3.5-27B-GGUF/mmproj-BF16.gguf filter=lfs diff=lfs merge=lfs -text
72
  llm/GGUF/unsloth/Qwen3.5-4B-GGUF/Qwen3.5-4B-UD-Q4_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
73
  llm/GGUF/unsloth/Qwen3.5-4B-GGUF/mmproj-BF16.gguf filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
71
  llm/GGUF/unsloth/Qwen3.5-27B-GGUF/mmproj-BF16.gguf filter=lfs diff=lfs merge=lfs -text
72
  llm/GGUF/unsloth/Qwen3.5-4B-GGUF/Qwen3.5-4B-UD-Q4_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
73
  llm/GGUF/unsloth/Qwen3.5-4B-GGUF/mmproj-BF16.gguf filter=lfs diff=lfs merge=lfs -text
74
+ onnx/qwen2_5_vl_3b_instruct_ort/onnx/decoder_model_merged.onnx_data filter=lfs diff=lfs merge=lfs -text
75
+ onnx/qwen2_5_vl_3b_instruct_ort/onnx/decoder_model_merged.onnx_data_1 filter=lfs diff=lfs merge=lfs -text
76
+ onnx/qwen2_5_vl_3b_instruct_ort/onnx/decoder_model_merged.onnx_data_2 filter=lfs diff=lfs merge=lfs -text
77
+ onnx/qwen2_5_vl_3b_instruct_ort/onnx/decoder_model_merged.onnx_data_3 filter=lfs diff=lfs merge=lfs -text
78
+ onnx/qwen2_5_vl_3b_instruct_ort/onnx/decoder_model_merged.onnx_data_4 filter=lfs diff=lfs merge=lfs -text
79
+ onnx/qwen2_5_vl_3b_instruct_ort/onnx/decoder_model_merged.onnx_data_5 filter=lfs diff=lfs merge=lfs -text
80
+ onnx/qwen2_5_vl_3b_instruct_ort/onnx/embed_tokens.onnx_data filter=lfs diff=lfs merge=lfs -text
81
+ onnx/qwen2_5_vl_3b_instruct_ort/onnx/vision_encoder.onnx_data filter=lfs diff=lfs merge=lfs -text
82
+ onnx/qwen2_5_vl_3b_instruct_ort/onnx/vision_encoder.onnx_data_1 filter=lfs diff=lfs merge=lfs -text
onnx/qwen2_5_vl_3b_instruct_ort/chat_template.jinja ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
2
+ You are a helpful assistant.<|im_end|>
3
+ {% endif %}<|im_start|>{{ message['role'] }}
4
+ {% if message['content'] is string %}{{ message['content'] }}<|im_end|>
5
+ {% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
6
+ {% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
7
+ {% endif %}
onnx/qwen2_5_vl_3b_instruct_ort/config.json ADDED
@@ -0,0 +1,131 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2_5_VLForConditionalGeneration"
4
+ ],
5
+ "dtype": "bfloat16",
6
+ "image_token_id": 151655,
7
+ "model_type": "qwen2_5_vl",
8
+ "text_config": {
9
+ "attention_dropout": 0.0,
10
+ "bos_token_id": 151643,
11
+ "dtype": "bfloat16",
12
+ "eos_token_id": 151645,
13
+ "hidden_act": "silu",
14
+ "hidden_size": 2048,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 11008,
17
+ "layer_types": [
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention",
51
+ "full_attention",
52
+ "full_attention",
53
+ "full_attention"
54
+ ],
55
+ "max_position_embeddings": 128000,
56
+ "max_window_layers": 70,
57
+ "model_type": "qwen2_5_vl_text",
58
+ "num_attention_heads": 16,
59
+ "num_hidden_layers": 36,
60
+ "num_key_value_heads": 2,
61
+ "pad_token_id": null,
62
+ "rms_norm_eps": 1e-06,
63
+ "rope_parameters": {
64
+ "mrope_section": [
65
+ 16,
66
+ 24,
67
+ 24
68
+ ],
69
+ "rope_theta": 1000000.0,
70
+ "rope_type": "default",
71
+ "type": "mrope"
72
+ },
73
+ "sliding_window": null,
74
+ "use_cache": true,
75
+ "use_sliding_window": false,
76
+ "vocab_size": 151936
77
+ },
78
+ "tie_word_embeddings": true,
79
+ "transformers_version": "5.3.0.dev0",
80
+ "video_token_id": 151656,
81
+ "vision_config": {
82
+ "depth": 32,
83
+ "fullatt_block_indexes": [
84
+ 7,
85
+ 15,
86
+ 23,
87
+ 31
88
+ ],
89
+ "hidden_act": "silu",
90
+ "hidden_size": 1280,
91
+ "in_channels": 3,
92
+ "in_chans": 3,
93
+ "initializer_range": 0.02,
94
+ "intermediate_size": 3420,
95
+ "model_type": "qwen2_5_vl",
96
+ "num_heads": 16,
97
+ "out_hidden_size": 2048,
98
+ "patch_size": 14,
99
+ "spatial_merge_size": 2,
100
+ "spatial_patch_size": 14,
101
+ "temporal_patch_size": 2,
102
+ "tokens_per_second": 2,
103
+ "window_size": 112
104
+ },
105
+ "vision_end_token_id": 151653,
106
+ "vision_start_token_id": 151652,
107
+ "vision_token_id": 151654,
108
+ "transformers.js_config": {
109
+ "use_external_data_format": {
110
+ "vision_encoder.onnx": 2,
111
+ "vision_encoder_fp16.onnx": 1,
112
+ "vision_encoder_q4.onnx": 1,
113
+ "vision_encoder_quantized.onnx": 1,
114
+ "vision_encoder_q4f16.onnx": 1,
115
+ "decoder_model_merged.onnx": 6,
116
+ "decoder_model_merged_fp16.onnx": 3,
117
+ "decoder_model_merged_quantized.onnx": 2,
118
+ "decoder_model_merged_q4.onnx": 1,
119
+ "decoder_model_merged_q4f16.onnx": 1,
120
+ "embed_tokens.onnx": 1,
121
+ "embed_tokens_fp16.onnx": 1,
122
+ "embed_tokens_quantized.onnx": 1,
123
+ "embed_tokens_q4.onnx": 1,
124
+ "embed_tokens_q4f16.onnx": 1
125
+ },
126
+ "kv_cache_dtype": {
127
+ "q4f16": "float16",
128
+ "fp16": "float16"
129
+ }
130
+ }
131
+ }
onnx/qwen2_5_vl_3b_instruct_ort/generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.05,
10
+ "temperature": 1e-06,
11
+ "transformers_version": "5.3.0.dev0",
12
+ "trust_remote_code": false
13
+ }
onnx/qwen2_5_vl_3b_instruct_ort/onnx/decoder_model_merged.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4f2d238cb9f31f358466bb1a76983e522789b8ed4df76a3906d595860f4911f
3
+ size 566476
onnx/qwen2_5_vl_3b_instruct_ort/onnx/decoder_model_merged.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcf5727c71d6808633b16e2cf0c37560f4091200558f2f6eafd8798a8bae1b64
3
+ size 2067978240
onnx/qwen2_5_vl_3b_instruct_ort/onnx/decoder_model_merged.onnx_data_1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1277ffdea9d43ec7b4debd5b1b7fcc5c665c5b65b09badf0474d7426d062962e
3
+ size 2067978240
onnx/qwen2_5_vl_3b_instruct_ort/onnx/decoder_model_merged.onnx_data_2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9efc4850ce1e6cf54b449b427ae19246c484faa7ae83578592623256bd71ac3e
3
+ size 2067978240
onnx/qwen2_5_vl_3b_instruct_ort/onnx/decoder_model_merged.onnx_data_3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abfc69df7d4b3a2f63fb778d3062df95562bbeb32925c3da1be47c61e5bbf8ff
3
+ size 2030202880
onnx/qwen2_5_vl_3b_instruct_ort/onnx/decoder_model_merged.onnx_data_4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:492b876f351e3e4ba9d987b4593e7b3e3805c923437ca51b7056f9ddb38729ce
3
+ size 2067978240
onnx/qwen2_5_vl_3b_instruct_ort/onnx/decoder_model_merged.onnx_data_5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33a48588642b388e61f782aa88d7f76af54705150eccfad8cdab4f61c4fc378f
3
+ size 2041638912
onnx/qwen2_5_vl_3b_instruct_ort/onnx/embed_tokens.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:117668cd2f53666060b6b2a6160e10d1a8fcbbc8b8e751b1e82a0ce32f6c1925
3
+ size 435
onnx/qwen2_5_vl_3b_instruct_ort/onnx/embed_tokens.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df608b38b5f74245af866d89d946866029c818eeb5808fe05a9b0bfbcad0db77
3
+ size 1244659712
onnx/qwen2_5_vl_3b_instruct_ort/onnx/vision_encoder.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1f5b88099db0f2cba2aa0d9edd50c96a028d4db1a21fbbce14c8d6f880ec211
3
+ size 421329
onnx/qwen2_5_vl_3b_instruct_ort/onnx/vision_encoder.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a4d4587cf072871157ca82c5ca95248781ecc33077458eda73a51eb37418b0b
3
+ size 2081295040
onnx/qwen2_5_vl_3b_instruct_ort/onnx/vision_encoder.onnx_data_1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8436636c8b42d164a9aacd57c2cdfbea01dc90ca7e3b15d8528414695db55a14
3
+ size 593442112
onnx/qwen2_5_vl_3b_instruct_ort/preprocessor_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "min_pixels": 3136,
3
+ "max_pixels": 12845056,
4
+ "patch_size": 14,
5
+ "temporal_patch_size": 2,
6
+ "merge_size": 2,
7
+ "image_mean": [
8
+ 0.48145466,
9
+ 0.4578275,
10
+ 0.40821073
11
+ ],
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "image_processor_type": "Qwen2VLImageProcessor",
18
+ "processor_class": "Qwen2_5_VLProcessor"
19
+ }
onnx/qwen2_5_vl_3b_instruct_ort/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
+ 0.48145466,
10
+ 0.4578275,
11
+ 0.40821073
12
+ ],
13
+ "image_processor_type": "Qwen2VLImageProcessorFast",
14
+ "image_std": [
15
+ 0.26862954,
16
+ 0.26130258,
17
+ 0.27577711
18
+ ],
19
+ "merge_size": 2,
20
+ "patch_size": 14,
21
+ "resample": 3,
22
+ "rescale_factor": 0.00392156862745098,
23
+ "size": {
24
+ "longest_edge": 12845056,
25
+ "shortest_edge": 3136
26
+ },
27
+ "temporal_patch_size": 2
28
+ },
29
+ "processor_class": "Qwen2_5_VLProcessor",
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": false,
38
+ "image_mean": [
39
+ 0.48145466,
40
+ 0.4578275,
41
+ 0.40821073
42
+ ],
43
+ "image_processor_type": "Qwen2VLImageProcessor",
44
+ "image_std": [
45
+ 0.26862954,
46
+ 0.26130258,
47
+ 0.27577711
48
+ ],
49
+ "max_frames": 768,
50
+ "merge_size": 2,
51
+ "min_frames": 4,
52
+ "patch_size": 14,
53
+ "resample": 3,
54
+ "rescale_factor": 0.00392156862745098,
55
+ "return_metadata": false,
56
+ "size": {
57
+ "longest_edge": 12845056,
58
+ "shortest_edge": 3136
59
+ },
60
+ "temporal_patch_size": 2,
61
+ "video_processor_type": "Qwen2VLVideoProcessor"
62
+ }
63
+ }
onnx/qwen2_5_vl_3b_instruct_ort/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
onnx/qwen2_5_vl_3b_instruct_ort/tokenizer_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": null,
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|im_end|>",
7
+ "errors": "replace",
8
+ "extra_special_tokens": {
9
+ "extra_token_0": "<|im_start|>",
10
+ "extra_token_1": "<|im_end|>",
11
+ "extra_token_2": "<|object_ref_start|>",
12
+ "extra_token_3": "<|object_ref_end|>",
13
+ "extra_token_4": "<|box_start|>",
14
+ "extra_token_5": "<|box_end|>",
15
+ "extra_token_6": "<|quad_start|>",
16
+ "extra_token_7": "<|quad_end|>",
17
+ "extra_token_8": "<|vision_start|>",
18
+ "extra_token_9": "<|vision_end|>",
19
+ "extra_token_10": "<|vision_pad|>",
20
+ "extra_token_11": "<|image_pad|>",
21
+ "extra_token_12": "<|video_pad|>"
22
+ },
23
+ "is_local": false,
24
+ "model_max_length": 131072,
25
+ "pad_token": "<|endoftext|>",
26
+ "processor_class": "Qwen2_5_VLProcessor",
27
+ "split_special_tokens": false,
28
+ "tokenizer_class": "Qwen2Tokenizer",
29
+ "unk_token": null,
30
+ "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
31
+ }