Update README.md
Browse files
README.md
CHANGED
|
@@ -97,6 +97,7 @@ HF Demo in Spaces available in the [Community ChatBot Arena](https://huggingface
|
|
| 97 |
|
| 98 |
Minotaur was built with [Axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) on 4XA100 80GB
|
| 99 |
- 1 epochs taking approximately 30 hours
|
|
|
|
| 100 |
|
| 101 |
## Bias, Risks, and Limitations
|
| 102 |
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).
|
|
|
|
| 97 |
|
| 98 |
Minotaur was built with [Axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) on 4XA100 80GB
|
| 99 |
- 1 epochs taking approximately 30 hours
|
| 100 |
+
- Trained using QLoRA techniques
|
| 101 |
|
| 102 |
## Bias, Risks, and Limitations
|
| 103 |
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).
|