This model is for the reproduction of results on Iterative-Prompt dataset of paper "The crucial role of samplers in online direct preference optimization". Iteration 3 of DPO-mixp algorithm, trained on https://huggingface.co/zhezi12138/llama-3b-iter-2-mixp.

Downloads last month
0
Safetensors
Model size
3.32B params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Dataset used to train zhezi12138/llama-3b-iter-3-mixp