Instructions to use grsilva/pt_rebel with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use grsilva/pt_rebel with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("grsilva/pt_rebel") model = AutoModelForSeq2SeqLM.from_pretrained("grsilva/pt_rebel", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tokenizer_config.json from grsilva/pt_rebel: direct link, hf CLI and curl.
- Browser
- Download file 401 Bytes
-
https://huggingface.co/grsilva/pt_rebel/resolve/refs%2Fpr%2F1/tokenizer_config.json
- Command line
-
hf download hf://grsilva/pt_rebel@refs/pr/1/tokenizer_config.json
-
curl -L -o tokenizer_config.json https://huggingface.co/grsilva/pt_rebel/resolve/refs%2Fpr%2F1/tokenizer_config.json
401 Bytes
| {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 1024, "additional_special_tokens": ["<obj>", "<subj>", "<triplet>", "<head>", "</head>", "<tail>", "</tail>"], "special_tokens_map_file": null, "name_or_path": "facebook/bart-large"} |