4bit variants quantizations of airoboros 70b 1.4.1 (https://huggingface.co/jondurbin/airoboros-l2-70b-gpt4-1.4.1), using exllama2.

You can find 4.25bpw (main branch), 4.5bpw and 4.75bpw in each branch.

Update 21/09/2023

Re-quanted all variants with latest exllamav2 version, which fixed some measurement issues.

Downloads last month: 3

Text Generation

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.