jon-tow commited on
Commit
56d19ee
1 Parent(s): 58a8c9b

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -0
README.md ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ language:
4
+ - en
5
+ ---
6
+
7
+ GPT-J (with value head weights) trained on HH with PPO following @reciprocate's `trlx` example https://github.com/CarperAI/trlx/blob/2f90ba0ecd640ae18cd62adb5e934a4b779f534b/examples/hh/ppo_hh.py
8
+ Logs: https://wandb.ai/jon-tow/trlx/reports/hh-gpt-j--VmlldzozODE1NjAw
9
+