Update README.md

README.md

@@ -20,12 +20,11 @@ Our ongoing projects include:
 
 ## Models and Performance
 
-We have developed several models, including AstroSage-8B, AstroLLaMA-2-70B, and AstroLLaMA-3-8B. Our AstroSage-8B model has demonstrated strong performance in astronomy Q&A tasks ([Ting et al. 2024](https://arxiv.org/abs/2407.11194), Pan et al. 2024):
+We have developed several models, including AstroSage-LLaMA-3.1-8B, AstroLLaMA-2-70B, and AstroLLaMA-3-8B. Our AstroSage-8B model has demonstrated strong performance in astronomy Q&A tasks ([Ting et al. 2024](https://arxiv.org/abs/2407.11194), Pan et al. 2024):
 
 | Model | Score (%) |
 |-------|-----------|
-| **AstroSage-8B (AstroMLab)** | **80.9** |
-| **AstroLLaMA-2-70B-Base (AstroMLab)** | **76.0** |
+| **AstroSage-LLaMA-3.1-8B (AstroMLab)** | **80.9** |
 | LLaMA-3.1-8B | 73.7 |
 | Phi-3.5-4B | 72.8 |
 | Gemma-2-9B | 71.5 |
@@ -37,7 +36,7 @@ We have developed several models, including AstroSage-8B, AstroLLaMA-2-70B, and
 | ChatGLM3-6B | 50.4 |
 | AstroLLaMA-2-7B (UniverseTBD) | 44.3 |
 
-AstroSage-8B, our lightweight model, currently achieves the highest score among the ~7B parameter models in its astronomy knowledge recall ability.
+AstroSage-8B, our lightweight model, currently achieves the highest score among the ~8B parameter models in its astronomy knowledge recall ability.
 
 ![Cost and performance trade-off in astronomical Q&A](https://cdn-uploads.huggingface.co/production/uploads/643f1ddce2ea47d170103537/ip0Bk-LZRrCArimets4H7.png)