Hugging Face's logo

BoghdadyJR
/
Qwen_MERGED_final

Image-to-Text
Transformers
Safetensors
English
qwen2_vl
text-generation-inference
unsloth
trl
Model card Files
xet
Community
BoghdadyJR commited on
Commit
63dfcb8
·
verified ·
1 Parent(s): ecf0262

Upload Qwen2VLForConditionalGeneration

Browse files
Files changed (3) hide show
  1. config.json +97 -0
  2. generation_config.json +13 -0
  3. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2VLForConditionalGeneration"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "eos_token_id": 151645,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 1536,
10
+ "image_token_id": 151655,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 8960,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 28,
15
+ "model_type": "qwen2_vl",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 28,
18
+ "num_key_value_heads": 2,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_scaling": {
21
+ "mrope_section": [
22
+ 16,
23
+ 24,
24
+ 24
25
+ ],
26
+ "rope_type": "default",
27
+ "type": "default"
28
+ },
29
+ "rope_theta": 1000000.0,
30
+ "sliding_window": 32768,
31
+ "text_config": {
32
+ "architectures": [
33
+ "Qwen2VLForConditionalGeneration"
34
+ ],
35
+ "attention_dropout": 0.0,
36
+ "bos_token_id": 151643,
37
+ "eos_token_id": 151645,
38
+ "hidden_act": "silu",
39
+ "hidden_size": 1536,
40
+ "image_token_id": null,
41
+ "initializer_range": 0.02,
42
+ "intermediate_size": 8960,
43
+ "max_position_embeddings": 32768,
44
+ "max_window_layers": 28,
45
+ "model_type": "qwen2_vl_text",
46
+ "num_attention_heads": 12,
47
+ "num_hidden_layers": 28,
48
+ "num_key_value_heads": 2,
49
+ "rms_norm_eps": 1e-06,
50
+ "rope_scaling": {
51
+ "mrope_section": [
52
+ 16,
53
+ 24,
54
+ 24
55
+ ],
56
+ "rope_type": "default",
57
+ "type": "default"
58
+ },
59
+ "rope_theta": 1000000.0,
60
+ "sliding_window": 32768,
61
+ "tie_word_embeddings": true,
62
+ "torch_dtype": "bfloat16",
63
+ "use_cache": true,
64
+ "use_sliding_window": false,
65
+ "video_token_id": null,
66
+ "vision_end_token_id": 151653,
67
+ "vision_start_token_id": 151652,
68
+ "vision_token_id": 151654,
69
+ "vocab_size": 151936
70
+ },
71
+ "torch_dtype": "bfloat16",
72
+ "transformers_version": "4.52.4",
73
+ "use_cache": true,
74
+ "use_sliding_window": false,
75
+ "video_token_id": 151656,
76
+ "vision_config": {
77
+ "depth": 32,
78
+ "embed_dim": 1280,
79
+ "hidden_act": "quick_gelu",
80
+ "hidden_size": 1536,
81
+ "in_channels": 3,
82
+ "in_chans": 3,
83
+ "initializer_range": 0.02,
84
+ "mlp_ratio": 4,
85
+ "model_type": "qwen2_vl",
86
+ "num_heads": 16,
87
+ "patch_size": 14,
88
+ "spatial_merge_size": 2,
89
+ "spatial_patch_size": 14,
90
+ "temporal_patch_size": 2,
91
+ "torch_dtype": "bfloat16"
92
+ },
93
+ "vision_end_token_id": 151653,
94
+ "vision_start_token_id": 151652,
95
+ "vision_token_id": 151654,
96
+ "vocab_size": 151936
97
+ }
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
+ "temperature": 0.01,
10
+ "top_k": 1,
11
+ "top_p": 0.001,
12
+ "transformers_version": "4.52.4"
13
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8467351968202a320c86bc5d2b84217a331fb8488a33be660ea0ee5127ff7c98
3
+ size 4418050848