File size: 670 Bytes
d269b02 314568f adb187c 314568f |
1 2 3 4 5 6 7 8 9 10 11 12 13 |
<p align="center"> <img src="https://huggingface.co/Crystalcareai/LlaMoE-Medium/resolve/main/resources/ddb-nye2T3C3vZwJJm1l6A.png" width="auto" title="LlaMoE-Medium model image"> </p>
This is a 4x8b Llama Mixture of Experts (MoE) model. It was trained on OpenHermes Resort from the Dolphin-2.9 dataset.
The model is a combination of 4 Llama fine-tunes, using DeepSpeed-MoE's architecture. All experts are active for every token.
This is a VERY good model, somewhere in between 8B and Llama 70B in capability. Enjoy!
Thank you to:
CrusoeEnergy for sponsoring the compute for this project
My collaborators Eric Hartford and Fernando (has too many names) Neto
|