423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-16 20:00:36 +08:00
Code Issues Packages Projects Releases Wiki Activity

improve KTO impl., replace datasets

Browse Source 
Former-commit-id: e56a57ddcf061de6e4acc8679f7dbf0b68364986
This commit is contained in:
hiyouga
2024-05-18 03:44:56 +08:00
parent 65715cab9d
commit d24969bb7e
61 changed files with 39218 additions and 440 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
data/hh_rlhf_en/hh_rlhf_en.py
View File

@@ -79,5 +79,5 @@ class HhRlhfEn(datasets.GeneratorBasedBuilder):
break
prompt = prompt[:human_idx]
yield key, {"instruction": query, "output": [r_accept, r_reject], "history": history}
yield key, {"instruction": query, "chosen": r_accept, "rejected": r_reject, "history": history}
key += 1