Move PaddleOCR-VL-0.9B files to root directory (#31)
Browse files- Move PaddleOCR-VL-0.9B files to root directory (87889e8941d60fb6067df575f7def3fde4a659b8)
- rm useless files from .gitattributes (3a407c42f69361306d9c322914af0c549ab14da5)
- .gitattributes +0 -20
- PaddleOCR-VL-0.9B/.gitattributes +0 -1
- PaddleOCR-VL-0.9B/.gitkeep +0 -0
- PaddleOCR-VL-0.9B/config.json +0 -75
- PaddleOCR-VL-0.9B/added_tokens.json β added_tokens.json +0 -0
- PaddleOCR-VL-0.9B/chat_template.jinja β chat_template.jinja +0 -0
- config.json +74 -4
- PaddleOCR-VL-0.9B/configuration_paddleocr_vl.py β configuration_paddleocr_vl.py +0 -0
- PaddleOCR-VL-0.9B/generation_config.json β generation_config.json +0 -0
- PaddleOCR-VL-0.9B/image_processing.py β image_processing.py +0 -0
- PaddleOCR-VL-0.9B/inference.yml β inference.yml +0 -0
- PaddleOCR-VL-0.9B/model.safetensors β model.safetensors +0 -0
- PaddleOCR-VL-0.9B/modeling_paddleocr_vl.py β modeling_paddleocr_vl.py +0 -0
- PaddleOCR-VL-0.9B/preprocessor_config.json β preprocessor_config.json +0 -0
- PaddleOCR-VL-0.9B/processing_paddleocr_vl.py β processing_paddleocr_vl.py +0 -0
- PaddleOCR-VL-0.9B/processor_config.json β processor_config.json +0 -0
- PaddleOCR-VL-0.9B/special_tokens_map.json β special_tokens_map.json +0 -0
- PaddleOCR-VL-0.9B/tokenizer.json β tokenizer.json +0 -0
- PaddleOCR-VL-0.9B/tokenizer.model β tokenizer.model +0 -0
- PaddleOCR-VL-0.9B/tokenizer_config.json β tokenizer_config.json +0 -0
.gitattributes
CHANGED
|
@@ -35,23 +35,3 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
PP-DocLayoutV2/inference.pdiparams filter=lfs diff=lfs merge=lfs -text
|
| 37 |
PP-DocLayoutV2/inference.pdmodel filter=lfs diff=lfs merge=lfs -text
|
| 38 |
-
PaddleOCR-VL-0.9B/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 39 |
-
imgs/allmetric.png filter=lfs diff=lfs merge=lfs -text
|
| 40 |
-
imgs/chart_01.jpg filter=lfs diff=lfs merge=lfs -text
|
| 41 |
-
imgs/chart_02.jpg filter=lfs diff=lfs merge=lfs -text
|
| 42 |
-
imgs/formula_EN.jpg filter=lfs diff=lfs merge=lfs -text
|
| 43 |
-
imgs/inhouseocr.png filter=lfs diff=lfs merge=lfs -text
|
| 44 |
-
imgs/inhousetable.png filter=lfs diff=lfs merge=lfs -text
|
| 45 |
-
imgs/omni10.png filter=lfs diff=lfs merge=lfs -text
|
| 46 |
-
imgs/omni15.png filter=lfs diff=lfs merge=lfs -text
|
| 47 |
-
imgs/omnibenchocr.png filter=lfs diff=lfs merge=lfs -text
|
| 48 |
-
imgs/overview1.jpg filter=lfs diff=lfs merge=lfs -text
|
| 49 |
-
imgs/overview2.jpg filter=lfs diff=lfs merge=lfs -text
|
| 50 |
-
imgs/overview3.jpg filter=lfs diff=lfs merge=lfs -text
|
| 51 |
-
imgs/overview4.jpg filter=lfs diff=lfs merge=lfs -text
|
| 52 |
-
imgs/paddleocrvl.png filter=lfs diff=lfs merge=lfs -text
|
| 53 |
-
imgs/table_01.jpg filter=lfs diff=lfs merge=lfs -text
|
| 54 |
-
imgs/table_02.jpg filter=lfs diff=lfs merge=lfs -text
|
| 55 |
-
imgs/text_english_arabic.jpg filter=lfs diff=lfs merge=lfs -text
|
| 56 |
-
imgs/text_handwriting_02.jpg filter=lfs diff=lfs merge=lfs -text
|
| 57 |
-
imgs/formula_ZH.jpg filter=lfs diff=lfs merge=lfs -text
|
|
|
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
PP-DocLayoutV2/inference.pdiparams filter=lfs diff=lfs merge=lfs -text
|
| 37 |
PP-DocLayoutV2/inference.pdmodel filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 β added_tokens.json
RENAMED
|
File without changes
|
PaddleOCR-VL-0.9B/chat_template.jinja β chat_template.jinja
RENAMED
|
File without changes
|
config.json
CHANGED
|
@@ -1,5 +1,75 @@
|
|
| 1 |
{
|
| 2 |
-
|
| 3 |
-
|
| 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 β configuration_paddleocr_vl.py
RENAMED
|
File without changes
|
PaddleOCR-VL-0.9B/generation_config.json β generation_config.json
RENAMED
|
File without changes
|
PaddleOCR-VL-0.9B/image_processing.py β image_processing.py
RENAMED
|
File without changes
|
PaddleOCR-VL-0.9B/inference.yml β inference.yml
RENAMED
|
File without changes
|
PaddleOCR-VL-0.9B/model.safetensors β model.safetensors
RENAMED
|
File without changes
|
PaddleOCR-VL-0.9B/modeling_paddleocr_vl.py β modeling_paddleocr_vl.py
RENAMED
|
File without changes
|
PaddleOCR-VL-0.9B/preprocessor_config.json β preprocessor_config.json
RENAMED
|
File without changes
|
PaddleOCR-VL-0.9B/processing_paddleocr_vl.py β processing_paddleocr_vl.py
RENAMED
|
File without changes
|
PaddleOCR-VL-0.9B/processor_config.json β processor_config.json
RENAMED
|
File without changes
|
PaddleOCR-VL-0.9B/special_tokens_map.json β special_tokens_map.json
RENAMED
|
File without changes
|
PaddleOCR-VL-0.9B/tokenizer.json β tokenizer.json
RENAMED
|
File without changes
|
PaddleOCR-VL-0.9B/tokenizer.model β tokenizer.model
RENAMED
|
File without changes
|
PaddleOCR-VL-0.9B/tokenizer_config.json β tokenizer_config.json
RENAMED
|
File without changes
|