4.65 bit/bpw quantization of Synthia-70B-v1.2b (https://huggingface.co/migtissera/Synthia-70B-v1.2), using exllamav2.

Update on 21/09/2023: Re-quantized with latest exllamav2 update, which fixes some measurement issues.

Downloads last month: 18

Inference Examples

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.