Hugging Face's logo

prithivMLmods
/
Camel-Doc-OCR-080125

Image-Text-to-Text
Transformers
Safetensors
English
Chinese
qwen2_5_vl
image-to-text
Document
KIE
OCR
VL
Openpdf
Camel
text-generation-inference
Extraction
Linking
Markdown
.Md
OpenPDF
OCRmix
trl
conversational
Model card Files
xet
Community
prithivMLmods commited on
Commit
4e3e2aa
·
verified ·
1 Parent(s): 58f1db0

rm ipynb

Browse files
Files changed (1) hide show
  1. .ipynb_checkpoints/config-checkpoint.json +0 -136
.ipynb_checkpoints/config-checkpoint.json DELETED
@@ -1,136 +0,0 @@
1
- {
2
- "architectures": [
3
- "Qwen2_5_VLForConditionalGeneration"
4
- ],
5
- "attention_dropout": 0.0,
6
- "bos_token_id": 151643,
7
- "eos_token_id": 151645,
8
- "hidden_act": "silu",
9
- "hidden_size": 3584,
10
- "image_token_id": 151655,
11
- "initializer_range": 0.02,
12
- "intermediate_size": 18944,
13
- "max_position_embeddings": 128000,
14
- "max_window_layers": 28,
15
- "model_type": "qwen2_5_vl",
16
- "num_attention_heads": 28,
17
- "num_hidden_layers": 28,
18
- "num_key_value_heads": 4,
19
- "pad_token_id": 151643,
20
- "rms_norm_eps": 1e-06,
21
- "rope_scaling": {
22
- "mrope_section": [
23
- 16,
24
- 24,
25
- 24
26
- ],
27
- "rope_type": "default",
28
- "type": "default"
29
- },
30
- "rope_theta": 1000000.0,
31
- "sliding_window": 32768,
32
- "text_config": {
33
- "architectures": [
34
- "Qwen2_5_VLForConditionalGeneration"
35
- ],
36
- "attention_dropout": 0.0,
37
- "bos_token_id": 151643,
38
- "eos_token_id": 151645,
39
- "hidden_act": "silu",
40
- "hidden_size": 3584,
41
- "image_token_id": null,
42
- "initializer_range": 0.02,
43
- "intermediate_size": 18944,
44
- "layer_types": [
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
- "full_attention",
55
- "full_attention",
56
- "full_attention",
57
- "full_attention",
58
- "full_attention",
59
- "full_attention",
60
- "full_attention",
61
- "full_attention",
62
- "full_attention",
63
- "full_attention",
64
- "full_attention",
65
- "full_attention",
66
- "full_attention",
67
- "full_attention",
68
- "full_attention",
69
- "full_attention",
70
- "full_attention",
71
- "full_attention",
72
- "full_attention"
73
- ],
74
- "max_position_embeddings": 128000,
75
- "max_window_layers": 28,
76
- "model_type": "qwen2_5_vl_text",
77
- "num_attention_heads": 28,
78
- "num_hidden_layers": 28,
79
- "num_key_value_heads": 4,
80
- "rms_norm_eps": 1e-06,
81
- "rope_scaling": {
82
- "mrope_section": [
83
- 16,
84
- 24,
85
- 24
86
- ],
87
- "rope_type": "default",
88
- "type": "default"
89
- },
90
- "rope_theta": 1000000.0,
91
- "sliding_window": null,
92
- "torch_dtype": "bfloat16",
93
- "use_cache": true,
94
- "use_sliding_window": false,
95
- "video_token_id": null,
96
- "vision_end_token_id": 151653,
97
- "vision_start_token_id": 151652,
98
- "vision_token_id": 151654,
99
- "vocab_size": 152064
100
- },
101
- "tie_word_embeddings": false,
102
- "torch_dtype": "bfloat16",
103
- "transformers_version": "4.54.0",
104
- "use_cache": true,
105
- "use_sliding_window": false,
106
- "video_token_id": 151656,
107
- "vision_config": {
108
- "depth": 32,
109
- "fullatt_block_indexes": [
110
- 7,
111
- 15,
112
- 23,
113
- 31
114
- ],
115
- "hidden_act": "silu",
116
- "hidden_size": 1280,
117
- "in_channels": 3,
118
- "in_chans": 3,
119
- "initializer_range": 0.02,
120
- "intermediate_size": 3420,
121
- "model_type": "qwen2_5_vl",
122
- "num_heads": 16,
123
- "out_hidden_size": 3584,
124
- "patch_size": 14,
125
- "spatial_merge_size": 2,
126
- "spatial_patch_size": 14,
127
- "temporal_patch_size": 2,
128
- "tokens_per_second": 2,
129
- "torch_dtype": "bfloat16",
130
- "window_size": 112
131
- },
132
- "vision_end_token_id": 151653,
133
- "vision_start_token_id": 151652,
134
- "vision_token_id": 151654,
135
- "vocab_size": 152064
136
- }