Instructions to use team-lucid/deberta-v3-base-korean with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use team-lucid/deberta-v3-base-korean with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("team-lucid/deberta-v3-base-korean", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from team-lucid/deberta-v3-base-korean: direct link, hf CLI and curl.
- Browser
- Download file 599 Bytes
-
https://huggingface.co/team-lucid/deberta-v3-base-korean/resolve/main/config.json
- Command line
-
hf download hf://team-lucid/deberta-v3-base-korean/config.json
-
curl -L -o config.json https://huggingface.co/team-lucid/deberta-v3-base-korean/resolve/main/config.json
599 Bytes
| { | |
| "attention_probs_dropout_prob": 0.1, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "layer_norm_eps": 1e-07, | |
| "max_position_embeddings": 512, | |
| "max_relative_positions": -1, | |
| "model_type": "deberta-v2", | |
| "norm_rel_ebd": "layer_norm", | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 12, | |
| "pad_token_id": 0, | |
| "pos_att_type": "p2c|c2p", | |
| "position_biased_input": false, | |
| "position_buckets": 256, | |
| "relative_attention": true, | |
| "share_att_key": true, | |
| "type_vocab_size": 0, | |
| "vocab_size": 64100 | |
| } |