Instructions to use anyforge/anyparse-models-hub with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use anyforge/anyparse-models-hub with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "image-to-text" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("image-to-text", model="anyforge/anyparse-models-hub", device_map="auto")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("anyforge/anyparse-models-hub", dtype="auto", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "model_type": "pp_ocrv6_small_rec", | |
| "backbone_config": { | |
| "model_type": "pp_lcnet_v4", | |
| "stem_channels": [3, 48, 96], | |
| "stem_type": "large", | |
| "out_features": ["stage1", "stage2", "stage3", "stage4"], | |
| "out_indices": [1, 2, 3, 4], | |
| "block_configs": [ | |
| [[3, 96, 96, 1, true]], | |
| [ | |
| [3, 96, 96, 1, false], | |
| [3, 96, 96, 1, false] | |
| ], | |
| [ | |
| [3, 96, 192, [2, 1], false], | |
| [3, 192, 192, 1, true], | |
| [3, 192, 192, 1, false], | |
| [3, 192, 192, 1, true], | |
| [3, 192, 192, 1, false], | |
| [3, 192, 192, 1, true], | |
| [3, 192, 192, 1, false] | |
| ], | |
| [ | |
| [3, 192, 384, [2, 1], false], | |
| [3, 384, 384, 1, true], | |
| [3, 384, 384, 1, false] | |
| ] | |
| ] | |
| }, | |
| "hidden_act": "silu", | |
| "hidden_size": 120, | |
| "mlp_ratio": 2.0, | |
| "depth": 2, | |
| "head_out_channels": 18710, | |
| "conv_kernel_size": [1, 7] | |
| } |