Update README.md
Browse files
README.md
CHANGED
|
@@ -31,6 +31,9 @@ For more information about AceInstruct, check our [website](https://research.nvi
|
|
| 31 |
| MMLU Pro | 32.40 | 33.78 | 56.30 | 54.50 | 71.10 | 66.10 |
|
| 32 |
| Average | 57.33 | 61.94 | 76.99 | 76.40 | 84.91 | 84.02 |
|
| 33 |
|
|
|
|
|
|
|
|
|
|
| 34 |
## All Resources
|
| 35 |
### AceMath Instruction Models
|
| 36 |
- [AceMath-1.5B-Instruct](https://huggingface.co/nvidia/AceMath-1.5B-Instruct), [AceMath-7B-Instruct](https://huggingface.co/nvidia/AceMath-7B-Instruct), [AceMath-72B-Instruct](https://huggingface.co/nvidia/AceMath-72B-Instruct)
|
|
|
|
| 31 |
| MMLU Pro | 32.40 | 33.78 | 56.30 | 54.50 | 71.10 | 66.10 |
|
| 32 |
| Average | 57.33 | 61.94 | 76.99 | 76.40 | 84.91 | 84.02 |
|
| 33 |
|
| 34 |
+
We compare AceInstruct to Qwen2.5-Instruct across coding, mathematics, and general knowledge tasks. We find that AceInstruct-1.5B outperforms Qwen2.5-1.5B-Instruct (61.94 vs. 57.33), while AceInstruct-7B and AceInstruct-72B perform similarly to Qwen2.5-7B-Instruct and Qwen2.5-72B-Instruct.
|
| 35 |
+
|
| 36 |
+
|
| 37 |
## All Resources
|
| 38 |
### AceMath Instruction Models
|
| 39 |
- [AceMath-1.5B-Instruct](https://huggingface.co/nvidia/AceMath-1.5B-Instruct), [AceMath-7B-Instruct](https://huggingface.co/nvidia/AceMath-7B-Instruct), [AceMath-72B-Instruct](https://huggingface.co/nvidia/AceMath-72B-Instruct)
|