TehVenom
/

GPT-J-Pyg_PPO-6B-Dev-V8p4

Text Generation

Inference Endpoints

Model card Files Files and versions Community

TehVenom commited on Mar 27, 2023

Commit

930dc82

•

1 Parent(s): b1fa04a

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -5,7 +5,7 @@ language:
 ---
 GPT-J-Pyg_PPO-6B [GPT-J Pygmalion Dev V8p4 + GPT-J PPO_HH]
-GPT-J-Pyg_PPO-6B is an experimental model containing a parameter-wise 50/50 blend (weighted average) of the weights of ppo_hh_gpt-j and Pygmalion-6b Dev V8p4.
 -Intended Merge Value-

 ---
 GPT-J-Pyg_PPO-6B [GPT-J Pygmalion Dev V8p4 + GPT-J PPO_HH]
+GPT-J-Pyg_PPO-6B is an experimental model containing a parameter-wise 40/60 blend (weighted average PPO_HH:Pygmalion) of the weights of ppo_hh_gpt-j and Pygmalion-6b Dev V8p4.
 -Intended Merge Value-