Performance Models (Old and MoE merge)
Collection
7 items
•
Updated
•
1
This is MoE(Mixture of Experts) model base on those model:
- Sao10K/Fimbulvetr-11B-v2
- BlueNipples/SnowLotus-v2-10.7B
You may want see this: https://huggingface.co/Alsebay/My_LLMs_Leaderboard
Done testing :D
I have test only Quantization version, good enough for Roleplay(RP), that what I want when make this model. But have many strange behavious (maybe I don't have enough Vram?)
GGUF version?
Alsebay/SunnyRain-2x10.7B-GGUF
Want more? Check this, he doing a great job
- Downloads last month
- 1
This model does not have enough activity to be deployed to Inference API (serverless) yet.
Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.