My GGUF-IQ-Imatrix quants for Sao10K/MN-BackyardAI-Party-12B-v1.

"For best results, set both <|im_end|> and [INST] as stopping strings. Recommended Temperature is <1 , min_p of at least 0.1."

"This does require a lot of tinkering to fit within SillyTavern / other frontends."

Prompting:

Similar to Mistral for group chats (please read the original model page for information on this)

ChatML for one-on-one chats

Downloads last month: 184

GGUF

Model size

12.2B params

Architecture

llama

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

View +2 files

Inference Providers NEW

This model is not currently available via any of the supported third-party Inference Providers, and HF Inference API was unable to determine this model’s pipeline type.

Model tree for Lewdiculous/MN-BackyardAI-Party-12B-v1-GGUF-IQ-ARM-Imatrix

Base model

Sao10K/MN-BackyardAI-Party-12B-v1

Quantized

(13)

this model

Collection including Lewdiculous/MN-BackyardAI-Party-12B-v1-GGUF-IQ-ARM-Imatrix

Quantized Models (GGUF, IQ, Imatrix)

Collection

Various quantizations of models in the GGUF format. Models with a "checkmark" are personal favorites. An "orange arrow" means it's being uploaded. • 93 items • Updated 29 days ago • 51