lmzheng commited on
Commit
a0283b9
1 Parent(s): 7900eeb

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -33,7 +33,7 @@ The primary intended users of the model are researchers and hobbyists in natural
33
  ## Training Details
34
 
35
  Vicuna v1.3 is fine-tuned from LLaMA with supervised instruction fine-tuning.
36
- The training data is around 140K conversations collected from ShareGPT.com.
37
  See more details in the "Training Details of Vicuna Models" section in the appendix of this [paper](https://arxiv.org/pdf/2306.05685.pdf).
38
 
39
  ## Evaluation
 
33
  ## Training Details
34
 
35
  Vicuna v1.3 is fine-tuned from LLaMA with supervised instruction fine-tuning.
36
+ The training data is around 125K conversations collected from ShareGPT.com.
37
  See more details in the "Training Details of Vicuna Models" section in the appendix of this [paper](https://arxiv.org/pdf/2306.05685.pdf).
38
 
39
  ## Evaluation