huihui_ai/mistral-small-abliterated:24b

huihui_ai/ mistral-small-abliterated:24b

7,174 Downloads Updated 12 months ago

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

tools 24b

ollama run huihui_ai/mistral-small-abliterated:24b

curl http://localhost:11434/api/chat \
  -d '{
    "model": "huihui_ai/mistral-small-abliterated:24b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='huihui_ai/mistral-small-abliterated:24b',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'huihui_ai/mistral-small-abliterated:24b',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 12 months ago

12 months ago

87ab165db808 · 14GB ·

model

archllama

parameters23.6B

quantizationQ4_K_M

14GB

system

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

644B

license

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

11kB

params

{ "temperature": 0.15 }

21B

template

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

695B

Readme

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.

References

HuggingFace