English
llama
text-generation-inference
asedmammad commited on
Commit
1992e85
·
1 Parent(s): f279abd

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -30,7 +30,7 @@ Change `-t 8` to the number of physical CPU cores you have. For example if your
30
 
31
  Change `-ngl 26` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
32
 
33
- If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`, also you can use --interactive-first to also start in interactive mode.
34
 
35
  ## Compatibility
36
 
 
30
 
31
  Change `-ngl 26` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
32
 
33
+ If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`, you can use `--interactive-first` to start in interactive mode.
34
 
35
  ## Compatibility
36