huihui_ai/
Lucie-abliterated:7b-instruct-fp16

286 11 months ago

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

7b

11 months ago

5c4861a796b1 · 13GB ·

model
llama
·
6.71B
·
F16
license
Apache License Version 2.0, January 2004 http://www.apache.org/licenses/ TERMS AND CONDITIONS FOR US
params
{ "num_ctx": 32000, "seed": 1234, "stop": [ "<|start_header_id|>", "<|en
template
{{ if .System }}<|start_header_id|>system<|end_header_id|> {{ .System }}<|eot_id|>{{ end }}{{ if .Pr

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