Instructions to use dfrees/llama-1b-instruct-dpo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use dfrees/llama-1b-instruct-dpo with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.2-1B-Instruct") model = PeftModel.from_pretrained(base_model, "dfrees/llama-1b-instruct-dpo") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Uploading merged DPO-trained model
Verified signature11e04b0 -
Uploading merged DPO-trained model
Verified signature350e24b -
Uploading merged DPO-trained model
Verified signature411221a -
Uploading merged DPO-trained model
Verified signature5a8bf1d -
Uploading DPO-trained model
Verified signaturefba78d6 -
initial commit
Verified signature44f4e52