Edit model card

This EXL2 quant matches the same bpw as mmnga's q4_K_M GGUF Like TheBloke, used shisa-en-ja-dpo-v1 dataset for calibration.

Main model: https://huggingface.co/augmxnt/shisa-7b-v1

For other quants (EXL2, AWQ, GGUF, etc) see: https://huggingface.co/augmxnt/shisa-7b-v1/discussions/2

Downloads last month
3
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.

Datasets used to train augmxnt/shisa-7b-v1-exl2-h6-4.63bpw