Neko-Institute-of-Science
/

LLaMA-30B-4bit-32g

Text Generation

Inference Endpoints

Model card Files Files and versions Community

Neko-Institute-of-Science commited on Apr 9, 2023

Commit

ac6320b

•

1 Parent(s): 270f2e5

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -1,5 +1,5 @@
 ```
-30B
 wikitext2 4.100694179534912 (stock 16bit)
 wikitext2 4.179347991943359 (32g)
 wikitext2 4.222894191741943 (128g)

 ```
+30B (act-order true-sequential groupsize)
 wikitext2 4.100694179534912 (stock 16bit)
 wikitext2 4.179347991943359 (32g)
 wikitext2 4.222894191741943 (128g)