Update README.md
Browse files
README.md
CHANGED
|
@@ -21,6 +21,10 @@ The Wizard Mega 13B SFT model is being released after two epochs as the eval los
|
|
| 21 |
|
| 22 |
Wizard Mega was built with [Axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) on 8xA100 80GB for 15 hours. The configuration to duplicate this build is provided in this repo's [/config folder](https://huggingface.co/openaccess-ai-collective/wizard-mega-13b/tree/main/configs).
|
| 23 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
## Examples
|
| 25 |
|
| 26 |
````
|
|
|
|
| 21 |
|
| 22 |
Wizard Mega was built with [Axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) on 8xA100 80GB for 15 hours. The configuration to duplicate this build is provided in this repo's [/config folder](https://huggingface.co/openaccess-ai-collective/wizard-mega-13b/tree/main/configs).
|
| 23 |
|
| 24 |
+
## Bias, Risks, and Limitations
|
| 25 |
+
Wizard Mega 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).
|
| 26 |
+
Wizard Mega was fine-tuned from the base model LlaMa 13B, please refer to its model card's Limitations Section for relevant information.
|
| 27 |
+
|
| 28 |
## Examples
|
| 29 |
|
| 30 |
````
|