Instructions to use SaitejaJate/GRPO_Reward_Model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use SaitejaJate/GRPO_Reward_Model with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/qwen2.5-3b-instruct-unsloth-bnb-4bit") model = PeftModel.from_pretrained(base_model, "SaitejaJate/GRPO_Reward_Model") - Notebooks
- Google Colab
- Kaggle
Download optimizer.pt from SaitejaJate/GRPO_Reward_Model: direct link, hf CLI and curl.
- Browser
- Download file 61.4 MB
-
https://huggingface.co/SaitejaJate/GRPO_Reward_Model/resolve/main/optimizer.pt
- Command line
-
hf download hf://SaitejaJate/GRPO_Reward_Model/optimizer.pt
-
curl -L -o optimizer.pt https://huggingface.co/SaitejaJate/GRPO_Reward_Model/resolve/main/optimizer.pt
61.4 MB
- Xet hash:
- d88afcf18d7e758b5ef24062e7394beb9e870f5ec38d1fa49e9c8c88bae7cc28
- Size of remote file:
- 61.4 MB
- SHA256:
- 465f5cf75fe273956ed243952a7e5988994af16bbe5e9f45ee5489bcd0bd0339
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.