Undi95/BagelMix-8x7B 3.5bpw

Exllama quant of Undi95/BagelMix-8x7B

You will need 24gb of vram to run this model at about half context (16k, you can probably go a bit higher too)

Prompt format:

ChatML? maybe? Unclear

<|im_start|>system
{sysprompt}<|im_end|>
<|im_start|>user
{input}<|im_end|>
<|im_start|>assistant
{output}<|im_end|>

Contact

Kooten on discord.

Downloads last month
2
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

Model tree for Kooten/BagelMix-8x7B-3.5bpw-exl2