Giters
jiaohuix
/
ppllama
The paddle implementation of meta's LLaMA.
Geek Repo:
Geek Repo
Github PK Tool:
Github PK Tool
Stargazers:
43
Watchers:
1
Issues:
3
Forks:
8
jiaohuix/ppllama Issues
AssertionError: Variable dtype not match, Variable [ vocab_parallel_embedding_0.w_0 ] need tensor with dtype paddle.float32 but load tensor with dtype paddle.float16
Closed
a year ago
Comments count
6
Error running the prompt on 2 Nvidia GPU - A100
Closed
a year ago
Comments count
1
use more cpu cores
Closed
8 months ago
Comments count
1