Instructions to use jmajkutewicz/Llama-3.1-Tulu-3-8B-DPO_ultrafeedback with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use jmajkutewicz/Llama-3.1-Tulu-3-8B-DPO_ultrafeedback with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("allenai/Llama-3.1-Tulu-3-8B-SFT") model = PeftModel.from_pretrained(base_model, "jmajkutewicz/Llama-3.1-Tulu-3-8B-DPO_ultrafeedback") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 288e3735e4698878db8e41bb53fcefe625e8ff7864e0bed8b17cdf85c47357d5
- Size of remote file:
- 336 MB
- SHA256:
- a312a2c7623ec7570b2ca1b720c2ff3d5a447d53e7db6effffb49c836ffff44e
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.