Hugging Face's logo

prithivMLmods
/
Megalodon-OCR-Sync-0713

Image-Text-to-Text
Transformers
Safetensors
English
Chinese
qwen2_5_vl
image-to-text
trl
text-generation-inference
image-captioning
optical-character-recognition
intelligent-character-recognition
caption
ocr
visual-understanding
art
icr
vlm
table
document
conversational
Model card Files
xet
Community
2
prithivMLmods commited on
Commit
3ce5b82
·
verified ·
1 Parent(s): 3bec667

Delete .ipynb_checkpoints

Browse files
Files changed (1) hide show
  1. .ipynb_checkpoints/config-checkpoint.json +0 -144
.ipynb_checkpoints/config-checkpoint.json DELETED
@@ -1,144 +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": 2048,
10
- "image_token_id": 151655,
11
- "initializer_range": 0.02,
12
- "intermediate_size": 11008,
13
- "max_position_embeddings": 128000,
14
- "max_window_layers": 70,
15
- "model_type": "qwen2_5_vl",
16
- "num_attention_heads": 16,
17
- "num_hidden_layers": 36,
18
- "num_key_value_heads": 2,
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": 2048,
41
- "image_token_id": null,
42
- "initializer_range": 0.02,
43
- "intermediate_size": 11008,
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
- "full_attention",
74
- "full_attention",
75
- "full_attention",
76
- "full_attention",
77
- "full_attention",
78
- "full_attention",
79
- "full_attention",
80
- "full_attention"
81
- ],
82
- "max_position_embeddings": 128000,
83
- "max_window_layers": 70,
84
- "model_type": "qwen2_5_vl_text",
85
- "num_attention_heads": 16,
86
- "num_hidden_layers": 36,
87
- "num_key_value_heads": 2,
88
- "rms_norm_eps": 1e-06,
89
- "rope_scaling": {
90
- "mrope_section": [
91
- 16,
92
- 24,
93
- 24
94
- ],
95
- "rope_type": "default",
96
- "type": "default"
97
- },
98
- "rope_theta": 1000000.0,
99
- "sliding_window": null,
100
- "tie_word_embeddings": true,
101
- "torch_dtype": "bfloat16",
102
- "use_cache": true,
103
- "use_sliding_window": false,
104
- "video_token_id": null,
105
- "vision_end_token_id": 151653,
106
- "vision_start_token_id": 151652,
107
- "vision_token_id": 151654,
108
- "vocab_size": 151936
109
- },
110
- "torch_dtype": "bfloat16",
111
- "transformers_version": "4.53.2",
112
- "use_cache": true,
113
- "use_sliding_window": false,
114
- "video_token_id": 151656,
115
- "vision_config": {
116
- "depth": 32,
117
- "fullatt_block_indexes": [
118
- 7,
119
- 15,
120
- 23,
121
- 31
122
- ],
123
- "hidden_act": "silu",
124
- "hidden_size": 1280,
125
- "in_channels": 3,
126
- "in_chans": 3,
127
- "initializer_range": 0.02,
128
- "intermediate_size": 3420,
129
- "model_type": "qwen2_5_vl",
130
- "num_heads": 16,
131
- "out_hidden_size": 2048,
132
- "patch_size": 14,
133
- "spatial_merge_size": 2,
134
- "spatial_patch_size": 14,
135
- "temporal_patch_size": 2,
136
- "tokens_per_second": 2,
137
- "torch_dtype": "bfloat16",
138
- "window_size": 112
139
- },
140
- "vision_end_token_id": 151653,
141
- "vision_start_token_id": 151652,
142
- "vision_token_id": 151654,
143
- "vocab_size": 151936
144
- }