ros/LlamaFactory
1
0
Fork 0
mirror of https://github.com/hiyouga/LlamaFactory.git synced 2026-02-02 08:33:38 +00:00
Code Issues Packages Projects Releases Wiki Activity

support ORPO

Browse Source 
Former-commit-id: f44a4c27e2461cdaa1b16865f597a31033c0e6d9
This commit is contained in:
hiyouga
2024-03-31 18:29:50 +08:00
parent 526111a303
commit d764cd8736
22 changed files with 395 additions and 47 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
src/llmtuner/extras/constants.py
View File

@@ -39,9 +39,12 @@ TRAINING_STAGES = {
"Reward Modeling": "rm",
"PPO": "ppo",
"DPO": "dpo",
"ORPO": "orpo",
"Pre-Training": "pt",
}
STAGES_USE_PAIR_DATA = ["rm", "dpo", "orpo"]
V_HEAD_WEIGHTS_NAME = "value_head.bin"
V_HEAD_SAFE_WEIGHTS_NAME = "value_head.safetensors"