Instructions to use CATIE-AQ/QAmembert with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use CATIE-AQ/QAmembert 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="CATIE-AQ/QAmembert")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("CATIE-AQ/QAmembert") model = AutoModelForQuestionAnswering.from_pretrained("CATIE-AQ/QAmembert", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download model.safetensors from CATIE-AQ/QAmembert: direct link, hf CLI and curl.
- Browser
- Download file 440 MB
-
https://huggingface.co/CATIE-AQ/QAmembert/resolve/main/model.safetensors
- Command line
-
hf download hf://CATIE-AQ/QAmembert/model.safetensors
-
curl -L -o model.safetensors https://huggingface.co/CATIE-AQ/QAmembert/resolve/main/model.safetensors
440 MB
- Xet hash:
- 49b3ed9e3c7b88aa946a5ac3deef5978a88df936ab0a1edd777d732e94e6b3c2
- Size of remote file:
- 440 MB
- SHA256:
- b79654837857bc3efebdb3bb2e51e68f7f4bd7682d40e49b8cdc2b678b57d715
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.