ros/LLaMA-Factory
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

support full-parameter PPO

Browse Source 
Former-commit-id: 4af967d69475e1c9fdf1a7983cd6b83bd431abff
This commit is contained in:
hiyouga
2023-11-16 02:08:04 +08:00
parent 8263b2d32d
commit 7a3a0144a5
19 changed files with 280 additions and 140 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/llmtuner/model/__init__.py
View File

@@ -1,3 +1,3 @@
from llmtuner.model.loader import load_model_and_tokenizer
from llmtuner.model.parser import get_train_args, get_infer_args, get_eval_args
from llmtuner.model.utils import dispatch_model, generate_model_card
from llmtuner.model.utils import create_ref_model, create_reward_model, dispatch_model, generate_model_card