Instructions to use timpal0l/mdeberta-v3-base-squad2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use timpal0l/mdeberta-v3-base-squad2 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="timpal0l/mdeberta-v3-base-squad2")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("timpal0l/mdeberta-v3-base-squad2") model = AutoModelForQuestionAnswering.from_pretrained("timpal0l/mdeberta-v3-base-squad2", device_map="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
Download tokenizer_config.json from timpal0l/mdeberta-v3-base-squad2: direct link, hf CLI and curl.
- Browser
- Download file 453 Bytes
-
https://huggingface.co/timpal0l/mdeberta-v3-base-squad2/resolve/main/tokenizer_config.json
- Command line
-
hf download hf://timpal0l/mdeberta-v3-base-squad2/tokenizer_config.json
-
curl -L -o tokenizer_config.json https://huggingface.co/timpal0l/mdeberta-v3-base-squad2/resolve/main/tokenizer_config.json
453 Bytes
| { | |
| "bos_token": "[CLS]", | |
| "cls_token": "[CLS]", | |
| "do_lower_case": false, | |
| "eos_token": "[SEP]", | |
| "mask_token": "[MASK]", | |
| "model_max_length": 1000000000000000019884624838656, | |
| "name_or_path": "mdeberta-v3-base-squad2/", | |
| "pad_token": "[PAD]", | |
| "sep_token": "[SEP]", | |
| "sp_model_kwargs": {}, | |
| "special_tokens_map_file": null, | |
| "split_by_punct": false, | |
| "tokenizer_class": "DebertaV2Tokenizer", | |
| "unk_token": "[UNK]", | |
| "vocab_type": "spm" | |
| } | |