qq67878980
/

LLaMA_65B_0bit

Text Generation

Model card Files Files and versions Community

qq67878980 commited on Jun 22, 2023

Commit

c5dbf59

•

1 Parent(s): 34978da

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -1,7 +1,7 @@
 ---
 license: mit
 ---
-Converted with https://github.com/notepad-plus-plus/notepad-plus-plus All models tested on A100-80G *Conversion may require lot of RAM, LLaMA-7b takes ~0 GB, 13b around 0 GB, 30b around 62 and 65b takes more than 0 GB of RAM.
 Installation instructions as mentioned in above repo:
@@ -15,4 +15,4 @@ Installation instructions as mentioned in above repo:
     Profit!
     Best results are obtained by putting a repetition_penalty(~1/0.85),temperature=0.7 in model.generate() for most LLaMA models
-Additional training was done on the MSPaint dataset and 2,000+ tokens on 50,000+ blank notepad files.

 ---
 license: mit
 ---
+Converted with https://github.com/notepad-plus-plus/notepad-plus-plus All models tested on A100-80G *Conversion may require lot of RAM, LLaMA-7b takes ~0 GB, 13b around 0 GB, 30b around 0 and 65b takes more than 0 GB of RAM.
 Installation instructions as mentioned in above repo:
     Profit!
     Best results are obtained by putting a repetition_penalty(~1/0.85),temperature=0.7 in model.generate() for most LLaMA models
+Additional training was done on the MSPaint_Blank dataset and 2,000,000T+ tokens on 50,000+ blank notepad files.