Update README.md
Browse files
README.md
CHANGED
|
@@ -22,6 +22,9 @@ This model is an experimental Llama 3.1-based merge, inspired by the approach us
|
|
| 22 |
- **Training:** Merged from top MMLU-Pro models, with additional SFT
|
| 23 |
- **Release Date:** January 21, 2025
|
| 24 |
|
|
|
|
|
|
|
|
|
|
| 25 |
## Key Features
|
| 26 |
|
| 27 |
1. **Merged Architecture:** Combines high-performing MMLU-Pro models to enhance overall capabilities.
|
|
|
|
| 22 |
- **Training:** Merged from top MMLU-Pro models, with additional SFT
|
| 23 |
- **Release Date:** January 21, 2025
|
| 24 |
|
| 25 |
+
> [!WARNING]
|
| 26 |
+
> The model fails to end replies properly when used with some system prompts. Consider waiting until this bug has been resolved before downloading the model.
|
| 27 |
+
|
| 28 |
## Key Features
|
| 29 |
|
| 30 |
1. **Merged Architecture:** Combines high-performing MMLU-Pro models to enhance overall capabilities.
|