This model is for the reproduction of results on Safe-RLHF dataset of paper "The crucial role of samplers in online direct preference optimization". You can download it and save it as "models/rlhflow_iter1", and then start the training pipeline. Since we've retrained the models, the results may slightly differ from that reported in the paper, and we will update it later.

Downloads last month
12
Safetensors
Model size
6.74B params
Tensor type
BF16
·
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.

Model tree for zhezi12138/alpaca-7b-iter-1

Finetuned
(4)
this model

Dataset used to train zhezi12138/alpaca-7b-iter-1