Instructions to use LucasS/albertABSA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use LucasS/albertABSA 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="LucasS/albertABSA")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("LucasS/albertABSA") model = AutoModelForQuestionAnswering.from_pretrained("LucasS/albertABSA", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tokenizer_config.json from LucasS/albertABSA: direct link, hf CLI and curl.
- Browser
- Download file 469 Bytes
-
https://huggingface.co/LucasS/albertABSA/resolve/main/tokenizer_config.json
- Command line
-
hf download hf://LucasS/albertABSA/tokenizer_config.json
-
curl -L -o tokenizer_config.json https://huggingface.co/LucasS/albertABSA/resolve/main/tokenizer_config.json
469 Bytes
| {"do_lower_case": true, "remove_space": true, "keep_accents": false, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "eAsyle/albertABSA", "tokenizer_class": "AlbertTokenizer"} |