Update README.md
Browse files
README.md
CHANGED
|
@@ -34,7 +34,7 @@ The primary intended users of the model are researchers and hobbyists in natural
|
|
| 34 |
## Training Details
|
| 35 |
|
| 36 |
Vicuna v1.5 is fine-tuned from LLaMA with supervised instruction fine-tuning.
|
| 37 |
-
The training data is around
|
| 38 |
See more details in the "Training Details of Vicuna Models" section in the appendix of this [paper](https://arxiv.org/pdf/2306.05685.pdf).
|
| 39 |
|
| 40 |
## Evaluation
|
|
|
|
| 34 |
## Training Details
|
| 35 |
|
| 36 |
Vicuna v1.5 is fine-tuned from LLaMA with supervised instruction fine-tuning.
|
| 37 |
+
The training data is around 125K conversations collected from ShareGPT.com.
|
| 38 |
See more details in the "Training Details of Vicuna Models" section in the appendix of this [paper](https://arxiv.org/pdf/2306.05685.pdf).
|
| 39 |
|
| 40 |
## Evaluation
|