huihui_ai/marco-o1-abliterated:7b-q4_K

huihui_ai/ marco-o1-abliterated:7b-q4_K_M

1,234 Downloads Updated 1 year ago

An open large reasoning model for real-world solutions by the Alibaba International Digital Commerce Group (AIDC-AI).

ollama run huihui_ai/marco-o1-abliterated:7b-q4_K_M

curl http://localhost:11434/api/chat \
  -d '{
    "model": "huihui_ai/marco-o1-abliterated:7b-q4_K_M",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='huihui_ai/marco-o1-abliterated:7b-q4_K_M',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'huihui_ai/marco-o1-abliterated:7b-q4_K_M',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 1 year ago

1 year ago

baaa675e9b97 · 4.7GB ·

model

archqwen2

parameters7.62B

quantizationQ4_K_M

4.7GB

system

你是一个经过良好训练的AI助手，你的名字是Marco-o1.由阿里国际数字商业集�

465B

license

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

11kB

template

{{- range $i, $_ := .Messages }} {{- $last := eq (len (slice $.Messages $i)) 1 -}} <|im_start|>{{ .R

244B

Readme

This is an uncensored version of AIDC-AI/Marco-o1 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