Instructions to use microsoft/mdeberta-v3-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/mdeberta-v3-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="microsoft/mdeberta-v3-base")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("microsoft/mdeberta-v3-base", device_map="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
Download config.json from microsoft/mdeberta-v3-base: direct link, hf CLI and curl.
- Browser
- Download file 579 Bytes
-
https://huggingface.co/microsoft/mdeberta-v3-base/resolve/main/config.json
- Command line
-
hf download hf://microsoft/mdeberta-v3-base/config.json
-
curl -L -o config.json https://huggingface.co/microsoft/mdeberta-v3-base/resolve/main/config.json
579 Bytes
| { | |
| "model_type": "deberta-v2", | |
| "attention_probs_dropout_prob": 0.1, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "max_position_embeddings": 512, | |
| "relative_attention": true, | |
| "position_buckets": 256, | |
| "norm_rel_ebd": "layer_norm", | |
| "share_att_key": true, | |
| "pos_att_type": "p2c|c2p", | |
| "layer_norm_eps": 1e-7, | |
| "max_relative_positions": -1, | |
| "position_biased_input": false, | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 12, | |
| "type_vocab_size": 0, | |
| "vocab_size": 251000 | |
| } | |