exl2 quantization of Senku-70B-Full at 6bpw, to be used with exllamav2.
Original model card:
Finetune of miqu-70b-sf dequant of miqudev's leak of Mistral-70B (allegedly an early mistral medium). My diffs are available under CC-0, this is a merge with the leaked model, you can use the other repository to save bandwidth.
EQ-Bench: 84.89
Will run more benches later.
- Downloads last month
- 7
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.