Mistral 7B Uncensored

Community · January 2024

activeOpen Weightdecoder onlytext
Parameters7B
Context Window32K tokens

Description

Community-modified version of Mistral 7B with content restrictions removed using abliteration — a technique that mathematically identifies and removes the model's built-in refusal responses without retraining. Among the most popular models for running AI locally without content filters, thanks to its small size and strong instruction-following abilities.

Key Innovations

Abliteration
AbliterationRemoving safety guardrails from a model through targeted fine-tuning or weight manipulation. Controversial but popular in open-source community.
Open Weight
Open WeightModel weights are publicly released but training data/code may not be. Enables fine-tuning but not full reproduction.

Family Tree

Built On

Lineage

Mistral 7BMistral 7B Uncensored