This model is for the reproduction of results on Iterative-Prompt 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.
- Downloads last month
- 4
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for zhezi12138/llama-3b-iter-1
Base model
openlm-research/open_llama_3b_v2