Hugging Face's logo

PaddlePaddle
/
PaddleOCR-VL

Image-Text-to-Text
PaddleOCR
Safetensors
English
Chinese
multilingual
paddleocr_vl
ERNIE4.5
PaddlePaddle
image-to-text
ocr
document-parse
layout
table
formula
chart
conversational
custom_code
Model card Files
xet
Community
56
root commited on
Commit
87889e8
·
1 Parent(s): f1e186d

Move PaddleOCR-VL-0.9B files to root directory

Browse files
Files changed (19) hide show
  1. PaddleOCR-VL-0.9B/.gitattributes +0 -1
  2. PaddleOCR-VL-0.9B/.gitkeep +0 -0
  3. PaddleOCR-VL-0.9B/config.json +0 -75
  4. PaddleOCR-VL-0.9B/added_tokens.json → added_tokens.json +0 -0
  5. PaddleOCR-VL-0.9B/chat_template.jinja → chat_template.jinja +0 -0
  6. config.json +74 -4
  7. PaddleOCR-VL-0.9B/configuration_paddleocr_vl.py → configuration_paddleocr_vl.py +0 -0
  8. PaddleOCR-VL-0.9B/generation_config.json → generation_config.json +0 -0
  9. PaddleOCR-VL-0.9B/image_processing.py → image_processing.py +0 -0
  10. PaddleOCR-VL-0.9B/inference.yml → inference.yml +0 -0
  11. PaddleOCR-VL-0.9B/model.safetensors → model.safetensors +0 -0
  12. PaddleOCR-VL-0.9B/modeling_paddleocr_vl.py → modeling_paddleocr_vl.py +0 -0
  13. PaddleOCR-VL-0.9B/preprocessor_config.json → preprocessor_config.json +0 -0
  14. PaddleOCR-VL-0.9B/processing_paddleocr_vl.py → processing_paddleocr_vl.py +0 -0
  15. PaddleOCR-VL-0.9B/processor_config.json → processor_config.json +0 -0
  16. PaddleOCR-VL-0.9B/special_tokens_map.json → special_tokens_map.json +0 -0
  17. PaddleOCR-VL-0.9B/tokenizer.json → tokenizer.json +0 -0
  18. PaddleOCR-VL-0.9B/tokenizer.model → tokenizer.model +0 -0
  19. PaddleOCR-VL-0.9B/tokenizer_config.json → tokenizer_config.json +0 -0
PaddleOCR-VL-0.9B/.gitattributes DELETED
@@ -1 +0,0 @@
1
- *.safetensors filter=lfs diff=lfs merge=lfs -text
 
 
PaddleOCR-VL-0.9B/.gitkeep DELETED
File without changes
PaddleOCR-VL-0.9B/config.json DELETED
@@ -1,75 +0,0 @@
1
- {
2
- "architectures": [
3
- "PaddleOCRVLForConditionalGeneration"
4
- ],
5
- "attention_probs_dropout_prob": 0.0,
6
- "auto_map": {
7
- "AutoConfig": "configuration_paddleocr_vl.PaddleOCRVLConfig",
8
- "AutoModel": "modeling_paddleocr_vl.PaddleOCRVLForConditionalGeneration",
9
- "AutoModelForCausalLM": "modeling_paddleocr_vl.PaddleOCRVLForConditionalGeneration"
10
- },
11
- "compression_ratio": 1.0,
12
- "head_dim": 128,
13
- "hidden_act": "silu",
14
- "hidden_dropout_prob": 0.0,
15
- "hidden_size": 1024,
16
- "ignored_index": -100,
17
- "image_token_id": 100295,
18
- "intermediate_size": 3072,
19
- "max_position_embeddings": 131072,
20
- "max_sequence_length": null,
21
- "model_type": "paddleocr_vl",
22
- "num_attention_heads": 16,
23
- "num_hidden_layers": 18,
24
- "num_key_value_heads": 2,
25
- "pad_token_id": 0,
26
- "rms_norm_eps": 1e-05,
27
- "rope_scaling": {
28
- "mrope_section": [
29
- 16,
30
- 24,
31
- 24
32
- ],
33
- "rope_type": "default",
34
- "type": "default"
35
- },
36
- "rope_theta": 500000,
37
- "sliding_window": null,
38
- "tie_word_embeddings": false,
39
- "torch_dtype": "bfloat16",
40
- "transformers_version": "4.55.0",
41
- "use_bias": false,
42
- "use_cache": false,
43
- "use_flash_attention": false,
44
- "video_token_id": 101307,
45
- "vision_config": {
46
- "architectures": [
47
- "SiglipVisionModel"
48
- ],
49
- "attention_dropout": 0.0,
50
- "auto_map": {
51
- "AutoConfig": "configuration_paddleocr_vl.PaddleOCRVLConfig",
52
- "AutoModel": "modeling_paddleocr_vl.SiglipVisionModel"
53
- },
54
- "hidden_act": "gelu_pytorch_tanh",
55
- "hidden_size": 1152,
56
- "image_size": 384,
57
- "intermediate_size": 4304,
58
- "layer_norm_eps": 1e-06,
59
- "model_type": "paddleocr_vl",
60
- "num_attention_heads": 16,
61
- "num_channels": 3,
62
- "num_hidden_layers": 27,
63
- "pad_token_id": 0,
64
- "patch_size": 14,
65
- "spatial_merge_size": 2,
66
- "temporal_patch_size": 2,
67
- "tokens_per_second": 2,
68
- "torch_dtype": "bfloat16"
69
- },
70
- "vision_start_token_id": 101305,
71
- "vocab_size": 103424,
72
- "weight_share_add_bias": true,
73
- "use_3d_rope": true,
74
- "rope_is_neox_style": true
75
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
PaddleOCR-VL-0.9B/added_tokens.json → added_tokens.json RENAMED
File without changes
PaddleOCR-VL-0.9B/chat_template.jinja → chat_template.jinja RENAMED
File without changes
config.json CHANGED
@@ -1,5 +1,75 @@
1
  {
2
- "Global": {
3
- "model_name": "PaddleOCR-VL"
4
- }
5
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  {
2
+ "architectures": [
3
+ "PaddleOCRVLForConditionalGeneration"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.0,
6
+ "auto_map": {
7
+ "AutoConfig": "configuration_paddleocr_vl.PaddleOCRVLConfig",
8
+ "AutoModel": "modeling_paddleocr_vl.PaddleOCRVLForConditionalGeneration",
9
+ "AutoModelForCausalLM": "modeling_paddleocr_vl.PaddleOCRVLForConditionalGeneration"
10
+ },
11
+ "compression_ratio": 1.0,
12
+ "head_dim": 128,
13
+ "hidden_act": "silu",
14
+ "hidden_dropout_prob": 0.0,
15
+ "hidden_size": 1024,
16
+ "ignored_index": -100,
17
+ "image_token_id": 100295,
18
+ "intermediate_size": 3072,
19
+ "max_position_embeddings": 131072,
20
+ "max_sequence_length": null,
21
+ "model_type": "paddleocr_vl",
22
+ "num_attention_heads": 16,
23
+ "num_hidden_layers": 18,
24
+ "num_key_value_heads": 2,
25
+ "pad_token_id": 0,
26
+ "rms_norm_eps": 1e-05,
27
+ "rope_scaling": {
28
+ "mrope_section": [
29
+ 16,
30
+ 24,
31
+ 24
32
+ ],
33
+ "rope_type": "default",
34
+ "type": "default"
35
+ },
36
+ "rope_theta": 500000,
37
+ "sliding_window": null,
38
+ "tie_word_embeddings": false,
39
+ "torch_dtype": "bfloat16",
40
+ "transformers_version": "4.55.0",
41
+ "use_bias": false,
42
+ "use_cache": false,
43
+ "use_flash_attention": false,
44
+ "video_token_id": 101307,
45
+ "vision_config": {
46
+ "architectures": [
47
+ "SiglipVisionModel"
48
+ ],
49
+ "attention_dropout": 0.0,
50
+ "auto_map": {
51
+ "AutoConfig": "configuration_paddleocr_vl.PaddleOCRVLConfig",
52
+ "AutoModel": "modeling_paddleocr_vl.SiglipVisionModel"
53
+ },
54
+ "hidden_act": "gelu_pytorch_tanh",
55
+ "hidden_size": 1152,
56
+ "image_size": 384,
57
+ "intermediate_size": 4304,
58
+ "layer_norm_eps": 1e-06,
59
+ "model_type": "paddleocr_vl",
60
+ "num_attention_heads": 16,
61
+ "num_channels": 3,
62
+ "num_hidden_layers": 27,
63
+ "pad_token_id": 0,
64
+ "patch_size": 14,
65
+ "spatial_merge_size": 2,
66
+ "temporal_patch_size": 2,
67
+ "tokens_per_second": 2,
68
+ "torch_dtype": "bfloat16"
69
+ },
70
+ "vision_start_token_id": 101305,
71
+ "vocab_size": 103424,
72
+ "weight_share_add_bias": true,
73
+ "use_3d_rope": true,
74
+ "rope_is_neox_style": true
75
+ }
PaddleOCR-VL-0.9B/configuration_paddleocr_vl.py → configuration_paddleocr_vl.py RENAMED
File without changes
PaddleOCR-VL-0.9B/generation_config.json → generation_config.json RENAMED
File without changes
PaddleOCR-VL-0.9B/image_processing.py → image_processing.py RENAMED
File without changes
PaddleOCR-VL-0.9B/inference.yml → inference.yml RENAMED
File without changes
PaddleOCR-VL-0.9B/model.safetensors → model.safetensors RENAMED
File without changes
PaddleOCR-VL-0.9B/modeling_paddleocr_vl.py → modeling_paddleocr_vl.py RENAMED
File without changes
PaddleOCR-VL-0.9B/preprocessor_config.json → preprocessor_config.json RENAMED
File without changes
PaddleOCR-VL-0.9B/processing_paddleocr_vl.py → processing_paddleocr_vl.py RENAMED
File without changes
PaddleOCR-VL-0.9B/processor_config.json → processor_config.json RENAMED
File without changes
PaddleOCR-VL-0.9B/special_tokens_map.json → special_tokens_map.json RENAMED
File without changes
PaddleOCR-VL-0.9B/tokenizer.json → tokenizer.json RENAMED
File without changes
PaddleOCR-VL-0.9B/tokenizer.model → tokenizer.model RENAMED
File without changes
PaddleOCR-VL-0.9B/tokenizer_config.json → tokenizer_config.json RENAMED
File without changes