Instructions to use alibaba-damo/mgp-str-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use alibaba-damo/mgp-str-base 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="alibaba-damo/mgp-str-base")# Load model directly from transformers import AutoProcessor, AutoModel processor = AutoProcessor.from_pretrained("alibaba-damo/mgp-str-base") model = AutoModel.from_pretrained("alibaba-damo/mgp-str-base", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "_name_or_path": "alibaba-damo/mgp-str-base", | |
| "architectures": | |
| [ | |
| "MGPSTRModel" | |
| ], | |
| "image_size": [32, 128], | |
| "patch_size": 4, | |
| "num_channels": 3, | |
| "max_token_length": 27, | |
| "num_character_labels": 38, | |
| "num_bpe_labels": 50257, | |
| "num_wordpiece_labels": 30522, | |
| "hidden_size": 768, | |
| "num_hidden_layers": 12, | |
| "num_attention_heads": 12, | |
| "mlp_ratio": 4, | |
| "qkv_bias": true, | |
| "drop_rate": 0.0, | |
| "attn_drop_rate": 0.0, | |
| "drop_path_rate": 0.0, | |
| "output_a3_attentions": false, | |
| "model_type": "mgp-str", | |
| "torch_dtype": "float32", | |
| "transformers_version": null | |
| } |