File size: 205 Bytes
da7bc3d
 
 
 
 
1
2
3
4
5
## Language Model Learns to Mislead Humans via RLHF

This repository contains the RLHF'ed code generation model in our paper: https://arxiv.org/pdf/2409.12822.

It's initialized based on deepseek-coder-7B.