Added the format to be able to finetune Vicuna1.1 models (#3037)
This commit is contained in:
parent
ff45317032
commit
1f540fa4f8
1 changed files with 3 additions and 0 deletions
3
training/formats/vicuna-format.json
Normal file
3
training/formats/vicuna-format.json
Normal file
|
@ -0,0 +1,3 @@
|
||||||
|
{
|
||||||
|
"instruction,output": "A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.\n\nUSER: %instruction%\n\nASSISTANT: %output%"
|
||||||
|
}
|
Loading…
Add table
Add a link
Reference in a new issue