Instructions to use HiTZ/medical_en-eu with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use HiTZ/medical_en-eu with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("HiTZ/medical_en-eu") model = AutoModelForSeq2SeqLM.from_pretrained("HiTZ/medical_en-eu", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tokenizer_config.json from HiTZ/medical_en-eu: direct link, hf CLI and curl.
- Browser
- Download file 400 Bytes
-
https://huggingface.co/HiTZ/medical_en-eu/resolve/main/tokenizer_config.json
- Command line
-
hf download hf://HiTZ/medical_en-eu/tokenizer_config.json
-
curl -L -o tokenizer_config.json https://huggingface.co/HiTZ/medical_en-eu/resolve/main/tokenizer_config.json
400 Bytes
| {"source_lang": "eu", "target_lang": "en", "unk_token": "<unk>", "eos_token": "</s>", "pad_token": "<pad>", "model_max_length": 512, "sp_model_kwargs": {}, "separate_vocabs": false, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "/gscratch4/users/idelaiglesia004/mt_qe/final_assignment/models/monolingual_en-eu/vocab_8000_shared/model", "tokenizer_class": "MarianTokenizer"} |