Instructions to use Xenova/mt5-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers.js
How to use Xenova/mt5-base with Transformers.js:
// ⚠️ Unknown pipeline tag
Download config.json from Xenova/mt5-base: direct link, hf CLI and curl.
- Browser
- Download file 804 Bytes
-
https://huggingface.co/Xenova/mt5-base/resolve/main/config.json
- Command line
-
hf download hf://Xenova/mt5-base/config.json
-
curl -L -o config.json https://huggingface.co/Xenova/mt5-base/resolve/main/config.json
804 Bytes
| { | |
| "_name_or_path": "google/mt5-base", | |
| "architectures": [ | |
| "MT5ForConditionalGeneration" | |
| ], | |
| "classifier_dropout": 0.0, | |
| "d_ff": 2048, | |
| "d_kv": 64, | |
| "d_model": 768, | |
| "decoder_start_token_id": 0, | |
| "dense_act_fn": "gelu_new", | |
| "dropout_rate": 0.1, | |
| "eos_token_id": 1, | |
| "feed_forward_proj": "gated-gelu", | |
| "initializer_factor": 1.0, | |
| "is_encoder_decoder": true, | |
| "is_gated_act": true, | |
| "layer_norm_epsilon": 1e-06, | |
| "model_type": "mt5", | |
| "num_decoder_layers": 12, | |
| "num_heads": 12, | |
| "num_layers": 12, | |
| "output_past": true, | |
| "pad_token_id": 0, | |
| "relative_attention_max_distance": 128, | |
| "relative_attention_num_buckets": 32, | |
| "tie_word_embeddings": false, | |
| "tokenizer_class": "T5Tokenizer", | |
| "transformers_version": "4.33.0.dev0", | |
| "use_cache": true, | |
| "vocab_size": 250112 | |
| } | |