Instructions to use AmazonScience/qanlu with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AmazonScience/qanlu 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="AmazonScience/qanlu")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("AmazonScience/qanlu") model = AutoModelForQuestionAnswering.from_pretrained("AmazonScience/qanlu", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download pytorch_model.bin from AmazonScience/qanlu: direct link, hf CLI and curl.
- Browser
- Download file 496 MB
-
https://huggingface.co/AmazonScience/qanlu/resolve/main/pytorch_model.bin
- Command line
-
hf download hf://AmazonScience/qanlu/pytorch_model.bin
-
curl -L -o pytorch_model.bin https://huggingface.co/AmazonScience/qanlu/resolve/main/pytorch_model.bin
496 MB
- Xet hash:
- 5f07755452de0fe0990491eb5d63706bca4f4169cab1d6e2575e517694410828
- Size of remote file:
- 496 MB
- SHA256:
- 77421a2d804c7fed66e6a85f06db65b2c7c62c9ec0c8795f24564c4531903ec9
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.