Update README.md
Browse files
README.md
CHANGED
|
@@ -82,6 +82,17 @@ print(f"Assistant: {response}")
|
|
| 82 |
|
| 83 |
While the AstroLLaMA-2-70B-Base_AIC model demonstrated significant improvements over its baseline LLaMA-2-70B model, the chat version (AstroLLaMA-2-70B-Chat_AIC) experiences performance degradation due to limitations in the SFT process. Here's a performance comparison:
|
| 84 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 85 |
|
| 86 |
Key limitations:
|
| 87 |
|
|
|
|
| 82 |
|
| 83 |
While the AstroLLaMA-2-70B-Base_AIC model demonstrated significant improvements over its baseline LLaMA-2-70B model, the chat version (AstroLLaMA-2-70B-Chat_AIC) experiences performance degradation due to limitations in the SFT process. Here's a performance comparison:
|
| 84 |
|
| 85 |
+
| Model | Score (%) |
|
| 86 |
+
|-------|-----------|
|
| 87 |
+
| **<span style="color:green">AstroLLaMA-2-70B-Base (AstroMLab)</span>** | **<span style="color:green">76.0</span>** |
|
| 88 |
+
| LLaMA-3.1-8B | 73.7 |
|
| 89 |
+
| LLaMA-2-70B | 70.7 |
|
| 90 |
+
| Gemma-2-9B | 71.5 |
|
| 91 |
+
| Qwen-2.5-7B | 70.4 |
|
| 92 |
+
| Yi-1.5-9B | 68.4 |
|
| 93 |
+
| InternLM-2.5-7B | 64.5 |
|
| 94 |
+
| Mistral-7B-v0.3 | 63.9 |
|
| 95 |
+
| ChatGLM3-6B | 50.4 |
|
| 96 |
|
| 97 |
Key limitations:
|
| 98 |
|