huihui_ai/Lucie-abliterated

huihui_ai/ Lucie-abliterated:latest

296 Downloads Updated 1 year ago

Lucie-7B is a pretrained 7B parameter causal language model built by LINAGORA and OpenLLM-France.

ollama run huihui_ai/Lucie-abliterated

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

from ollama import chat

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

import ollama from 'ollama'

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

Details

Updated 1 year ago

1 year ago

56230dc436a3 · 4.1GB ·

model

archllama

parameters6.71B

quantizationQ4_K_M

4.1GB

template

{{ if .System }}<|start_header_id|>system<|end_header_id|> {{ .System }}<|eot_id|>{{ end }}{{ if .Pr

254B

license

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

11kB

params

{ "num_ctx": 32000, "seed": 1234, "stop": [ "<|start_header_id|>", "<|en

175B

Readme

This is an uncensored version of OpenLLM-France/Lucie-7B-Instruct 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