Logo

🎯 Sailor2-8B-Chat-Uncensored

An optimized version of Sailor2-8B-Chat focused on removing refusal behaviors

πŸ“Œ Overview

A streamlined implementation that removes refusal behaviors from sail/Sailor2-8B-Chat, based on directional intervention techniques.

πŸ” Key Features

  • Implements directional intervention for behavior modification
  • Fully quantized for resource-efficient deployment

πŸ› οΈ Implementation

Based on research findings from "Refusal in LLMs is Mediated by a Single Direction"

πŸ’« Quantization

Pre-quantized models available in GGFU format:

🀝 Contributors

Developed with ❀️ by BlossomAI


Star ⭐️ this repo if you find it valuable!
Downloads last month
44
Safetensors
Model size
8.55B params
Tensor type
BF16
Β·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for BlossomsAI/Sailor2-8B-Chat-Uncensored

Base model

Qwen/Qwen2.5-7B
Finetuned
sail/Sailor2-8B
Finetuned
(4)
this model
Quantizations
3 models