digitous commited on
Commit
92b955a
1 Parent(s): b79adb6

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -1
README.md CHANGED
@@ -1,3 +1,8 @@
 
 
 
 
 
1
  GPT-R [Ronin]
2
 
3
  GPT-R is an experimental model containing a parameter-wise 60/40 blend (weighted average) of the weights of ppo_hh_gpt-j and GPT-JT-6B-v1.
@@ -69,4 +74,7 @@ Datasets:
69
  https://huggingface.co/datasets/the_pile
70
  https://huggingface.co/datasets/bigscience/P3
71
  https://github.com/allenai/natural-instructions
72
- https://ai.googleblog.com/2022/05/language-models-perform-reasoning-via.html
 
 
 
 
1
+ ---
2
+ license: bigscience-openrail-m
3
+ language:
4
+ - en
5
+ ---
6
  GPT-R [Ronin]
7
 
8
  GPT-R is an experimental model containing a parameter-wise 60/40 blend (weighted average) of the weights of ppo_hh_gpt-j and GPT-JT-6B-v1.
 
74
  https://huggingface.co/datasets/the_pile
75
  https://huggingface.co/datasets/bigscience/P3
76
  https://github.com/allenai/natural-instructions
77
+ https://ai.googleblog.com/2022/05/language-models-perform-reasoning-via.html
78
+
79
+ Weight merge Script credit to Concedo:
80
+ https://huggingface.co/concedo