Instructions to use masahiroid/mdeberta-v3-base-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use masahiroid/mdeberta-v3-base-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download masahiroid/mdeberta-v3-base-mlx --local-dir mdeberta-v3-base-mlx
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download config.json from masahiroid/mdeberta-v3-base-mlx: direct link, hf CLI and curl.
- Browser
- Download file 777 Bytes
-
https://huggingface.co/masahiroid/mdeberta-v3-base-mlx/resolve/main/config.json
- Command line
-
hf download hf://masahiroid/mdeberta-v3-base-mlx/config.json
-
curl -L -o config.json https://huggingface.co/masahiroid/mdeberta-v3-base-mlx/resolve/main/config.json
777 Bytes
| { | |
| "attention_probs_dropout_prob": 0.1, | |
| "dtype": "float32", | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "layer_norm_eps": 1e-07, | |
| "legacy": true, | |
| "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, | |
| "pooler_dropout": 0, | |
| "pooler_hidden_act": "gelu", | |
| "pooler_hidden_size": 768, | |
| "pos_att_type": [ | |
| "p2c", | |
| "c2p" | |
| ], | |
| "position_biased_input": false, | |
| "position_buckets": 256, | |
| "relative_attention": true, | |
| "share_att_key": true, | |
| "transformers_version": "4.57.3", | |
| "type_vocab_size": 0, | |
| "vocab_size": 251000 | |
| } | |