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 2 of DPO-mixp algorithm, trained on https://huggingface.co/zhezi12138/llama-3b-iter-1.

Downloads last month
4
Safetensors
Model size
3.32B params
Tensor type
F32
·
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and HF Inference API was unable to determine this model's library.

Dataset used to train zhezi12138/llama-3b-iter-2-mixp