Kooten's picture
Update README.md
b52e609 verified
|
raw
history blame
528 Bytes
metadata
license: cc-by-nc-4.0

Noromaid-v0.4-Mixtral-Instruct-8x7b-Zloss 3.5bpw

Exllama quant of NeverSleep/Noromaid-v0.4-Mixtral-Instruct-8x7b-Zloss

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

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

Contact

Kooten on discord.