Instructions to use hchang/reward_modeling with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use hchang/reward_modeling with PEFT:
from peft import PeftModel from transformers import AutoModelForSequenceClassification base_model = AutoModelForSequenceClassification.from_pretrained("meta-llama/Meta-Llama-3-8B") model = PeftModel.from_pretrained(base_model, "hchang/reward_modeling") - Notebooks
- Google Colab
- Kaggle
Download checkpoint-1000/optimizer.pt from hchang/reward_modeling: direct link, hf CLI and curl.
- Browser
- Download file 1.2 MB
-
https://huggingface.co/hchang/reward_modeling/resolve/main/checkpoint-1000/optimizer.pt
- Command line
-
hf download hf://hchang/reward_modeling/checkpoint-1000/optimizer.pt
-
curl -L -o optimizer.pt https://huggingface.co/hchang/reward_modeling/resolve/main/checkpoint-1000/optimizer.pt
1.2 MB
- Xet hash:
- e1cd723ccc640244b0a45839d820a17c07f5d8738ae35a6ee72f007c96d40fe0
- Size of remote file:
- 1.2 MB
- SHA256:
- d8cceb896033a02c9a5a8a91109d190488a1f91c73af6d0eb1b5ace57e2901f5
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.