2.5 bit quantization of airoboros 70b 1.4.1 (https://huggingface.co/jondurbin/airoboros-l2-70b-gpt4-1.4.1), using exllama2.
Updated as 21 of September 2023, which should fix the bad ppl results.
I suggest, if using Ubuntu, to use it with flash-attn. It reduces VRAM usage by a good margin, and is specially useful for this case (70B model on a single 24GB VRAM GPU)
- Downloads last month
- 22
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.