Could you please relase the model checkponts?

haozheji / exact-optimization

ICML 2024 - Official Repository for EXO: Towards Efficient Exact Optimization of Language Model Alignment

https://arxiv.org/abs/2402.00856

MIT License

44 stars 0 forks source link

Open AGTSAAA opened 4 months ago

AGTSAAA commented 4 months ago

Hi, Thank you very much for your work!

Could you please relase your model checkponts such as SFT model and Reward model for each experimments in Huggingface?

haozheji commented 2 months ago

Sorry for the delay of reply, we are uploading the checkpoints of sft and reward model to https://huggingface.co/collections/ehzoah/efficient-exact-optimization-667995e5a7f87dff7d01a85a Meanwhile, running the training scripts should produce sft and reward models with similar performance