huihui_ai/mistral-small-abliterated:24b-instruct-2501-q4_K

huihui_ai/

mistral-small-abliterated:24b-instruct-2501-q4_K_M

5,565 Downloads Updated 8 months ago

Mistral Small 3 sets a new benchmark in the “small” Large Language Models category below 70B.

tools 24b

Updated 8 months ago

8 months ago

87ab165db808 · 14GB ·

archllama

parameters23.6B

quantizationQ4_K_M

14GB

{{- range $index, $_ := .Messages }} {{- if eq .Role "system" }}[SYSTEM_PROMPT]{{ .Content }}[/SYSTE

695B

You are Mistral Small 3, a Large Language Model (LLM) created by Mistral AI, a French startup headqu

644B

Apache License Version 2.0, January 2004 http://www.apache.org/licenses/ TERMS AND CONDITIONS FOR US

11kB

{ "temperature": 0.15 }

21B

This is an uncensored version of mistralai/Mistral-Small-24B-Instruct-2501 created with abliteration (see remove-refusals-with-transformers to know more about it).
This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens.