Instructions to use Aybars/ModelOnWhole with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Aybars/ModelOnWhole 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="Aybars/ModelOnWhole")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("Aybars/ModelOnWhole") model = AutoModelForQuestionAnswering.from_pretrained("Aybars/ModelOnWhole", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download pytorch_model.bin from Aybars/ModelOnWhole: direct link, hf CLI and curl.
- Browser
- Download file 735 MB
-
https://huggingface.co/Aybars/ModelOnWhole/resolve/main/pytorch_model.bin
- Command line
-
hf download hf://Aybars/ModelOnWhole/pytorch_model.bin
-
curl -L -o pytorch_model.bin https://huggingface.co/Aybars/ModelOnWhole/resolve/main/pytorch_model.bin
735 MB
- Xet hash:
- 2bed522c466e2010adf25103c781610586be4726837fadae9f956c2d318f2f4d
- Size of remote file:
- 735 MB
- SHA256:
- 79c7b6ecf07e8ba89c5176ebc257b50a7060d3db551001610dca38565bfb3977
路
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.