Update README.md
Browse files
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
|