Instructions to use Rifky/Indobert-QA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Rifky/Indobert-QA 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="Rifky/Indobert-QA")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("Rifky/Indobert-QA") model = AutoModelForQuestionAnswering.from_pretrained("Rifky/Indobert-QA", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tokenizer_config.json from Rifky/Indobert-QA: direct link, hf CLI and curl.
- Browser
- Download file 532 Bytes
-
https://huggingface.co/Rifky/Indobert-QA/resolve/e3bb9a54de04844970c4a8140fc5d999580c5ae6/tokenizer_config.json
- Command line
-
hf download hf://Rifky/Indobert-QA@e3bb9a54de04844970c4a8140fc5d999580c5ae6/tokenizer_config.json
-
curl -L -o tokenizer_config.json https://huggingface.co/Rifky/Indobert-QA/resolve/e3bb9a54de04844970c4a8140fc5d999580c5ae6/tokenizer_config.json
532 Bytes
| {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": "/root/.cache/huggingface/transformers/0d67a06ab0513afc9134e37589e146c1ca823a21a00c36d3fc0c1646a69ce972.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "name_or_path": "./drive/MyDrive/KOPSI/bert-squad-trained", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"} |