GanjinZero / RRHF

[NIPS2023] RRHF & Wombat
780 stars 49 forks source link

How to use it. Is there some code examples? #28

Open Mr-IT007 opened 1 year ago

Mr-IT007 commented 1 year ago

How to use it. Is there some code examples?

GanjinZero commented 1 year ago

For training:

Training with RRHF You can train your own model with generated or released datasets using the script train.sh, please note that the training process requires 8*A100 80GB GPUs, bf16 and FSDP. In the future, we will try efficient training methods such as LoRA or Prefix-tuning or Adapter to lower the computational resource requirements.

bash ./train.sh

For using Wombat: Use recover_wombat_7b.sh and single_sentence_inference.py