Instructions to use uzaaft/quant_bart_eli5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use uzaaft/quant_bart_eli5 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("uzaaft/quant_bart_eli5") model = AutoModelForSeq2SeqLM.from_pretrained("uzaaft/quant_bart_eli5", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download decoder_with_past_model_quantized.onnx from uzaaft/quant_bart_eli5: direct link, hf CLI and curl.
- Browser
- Download file 282 MB
-
https://huggingface.co/uzaaft/quant_bart_eli5/resolve/main/decoder_with_past_model_quantized.onnx
- Command line
-
hf download hf://uzaaft/quant_bart_eli5/decoder_with_past_model_quantized.onnx
-
curl -L -o decoder_with_past_model_quantized.onnx https://huggingface.co/uzaaft/quant_bart_eli5/resolve/main/decoder_with_past_model_quantized.onnx
282 MB
- Xet hash:
- 81b1520914cbd5a2791c212b1cf024459ed8d72b9c32998ad1a577594aba4d06
- Size of remote file:
- 282 MB
- SHA256:
- 775c6fc9b570e83f526cf095c0d9622cb1b19521ab7eabe5fc6cf963808b6637
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.