Instructions to use jsm33/d4-adaptation with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jsm33/d4-adaptation with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, RobertaForSequenceClassificationWithLayeredSentiment tokenizer = AutoTokenizer.from_pretrained("jsm33/d4-adaptation") model = RobertaForSequenceClassificationWithLayeredSentiment.from_pretrained("jsm33/d4-adaptation", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download pytorch_model.bin from jsm33/d4-adaptation: direct link, hf CLI and curl.
- Browser
- Download file 547 MB
-
https://huggingface.co/jsm33/d4-adaptation/resolve/main/pytorch_model.bin
- Command line
-
hf download hf://jsm33/d4-adaptation/pytorch_model.bin
-
curl -L -o pytorch_model.bin https://huggingface.co/jsm33/d4-adaptation/resolve/main/pytorch_model.bin
547 MB
- Xet hash:
- 88b513878ecc11ca4218c54dcbfb1ee1ed2dbbba0954239aa7ccaefc0496e052
- Size of remote file:
- 547 MB
- SHA256:
- 3a597f51babf14c41f0c417b315b21e6acd682a2071bc1386a90f32e946a3ec1
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.