Update README.md
Browse files
README.md
CHANGED
|
@@ -74,4 +74,9 @@ Minotaur was built with [Axolotl](https://github.com/OpenAccess-AI-Collective/ax
|
|
| 74 |
Minotaur has not been aligned to human preferences with techniques like RLHF or deployed with in-the-loop filtering of responses like ChatGPT, so the model can produce problematic outputs (especially when prompted to do so).
|
| 75 |
Minotaur was fine-tuned from the base model MPT-7B, please refer to its model card's Limitations Section for relevant information. (included below)
|
| 76 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 77 |
## Examples - results may vary based on temperature and other settings
|
|
|
|
|
|
| 74 |
Minotaur has not been aligned to human preferences with techniques like RLHF or deployed with in-the-loop filtering of responses like ChatGPT, so the model can produce problematic outputs (especially when prompted to do so).
|
| 75 |
Minotaur was fine-tuned from the base model MPT-7B, please refer to its model card's Limitations Section for relevant information. (included below)
|
| 76 |
|
| 77 |
+
## Benchmarks
|
| 78 |
+
|
| 79 |
+
|
| 80 |
+
|
| 81 |
## Examples - results may vary based on temperature and other settings
|
| 82 |
+
|