Instructions to use Ulangi/checkpoints with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Ulangi/checkpoints with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "question-answering" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("question-answering", model="Ulangi/checkpoints")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("Ulangi/checkpoints") model = AutoModelForQuestionAnswering.from_pretrained("Ulangi/checkpoints", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tokenizer_config.json from Ulangi/checkpoints: direct link, hf CLI and curl.
- Browser
- Download file 403 Bytes
-
https://huggingface.co/Ulangi/checkpoints/resolve/main/tokenizer_config.json
- Command line
-
hf download hf://Ulangi/checkpoints/tokenizer_config.json
-
curl -L -o tokenizer_config.json https://huggingface.co/Ulangi/checkpoints/resolve/main/tokenizer_config.json
403 Bytes
| { | |
| "added_tokens_decoder": { | |
| "40030": { | |
| "content": "[PAD]", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| } | |
| }, | |
| "clean_up_tokenization_spaces": true, | |
| "extra_special_tokens": {}, | |
| "model_max_length": 1000000000000000019884624838656, | |
| "pad_token": "[PAD]", | |
| "tokenizer_class": "PreTrainedTokenizerFast" | |
| } | |