Image-to-Text
MLX
Safetensors
mlx-weights
paddlepaddle-ocr
ppocrv5
ppocrv6
ppdoclayoutv3
pp-structure
apple-silicon
Instructions to use plaincompute/ppocr-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use plaincompute/ppocr-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir ppocr-mlx plaincompute/ppocr-mlx
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
| { | |
| "model_type": "pp_ocrv5_server_rec", | |
| "backbone_config": { | |
| "model_type": "hgnet_v2", | |
| "arch": "L", | |
| "return_idx": [0, 1, 2, 3], | |
| "freeze_stem_only": true, | |
| "freeze_at": 0, | |
| "freeze_norm": true, | |
| "lr_mult_list": [1.0, 1.0, 1.0, 1.0, 1.0], | |
| "out_features": ["stage1", "stage2", "stage3", "stage4"], | |
| "stage_downsample": [true, true, true, true], | |
| "stem_strides": [2, 1, 1, 1, 1], | |
| "stage_downsample_strides": [[2, 1], [1, 2], [2, 1], [2, 1]] | |
| }, | |
| "hidden_act": "silu", | |
| "hidden_size": 120, | |
| "mlp_ratio": 2.0, | |
| "depth": 2, | |
| "head_out_channels": 18385, | |
| "conv_kernel_size": [1, 3], | |
| "qkv_bias": true, | |
| "num_attention_heads": 8, | |
| "attention_dropout": 0.0 | |
| } |