46 lines
1.3 KiB
Markdown
46 lines
1.3 KiB
Markdown
---
|
|
library_name: transformers
|
|
license: mit
|
|
language:
|
|
- en
|
|
- vi
|
|
base_model:
|
|
- Qwen/Qwen2.5-Coder-7B-Instruct
|
|
---
|
|
|
|
<div align="center">
|
|
<img src="https://github.com/bloomifycafe/blossomsAI/blob/main/assets/logo.png?raw=true" alt="Logo"/>
|
|
</div>
|
|
</br>
|
|
<div align="center">
|
|
|
|
# 🎯 Qwen2.5-Coder-7B-Instruct-Uncensored
|
|
|
|
### An optimized version of Qwen2.5-Coder-7B-Instruct focused on removing refusal behaviors
|
|
</div>
|
|
|
|
## 📌 Overview
|
|
|
|
A streamlined implementation that removes refusal behaviors from [Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct), based on directional intervention techniques.
|
|
|
|
## 🔍 Key Features
|
|
- Implements directional intervention for behavior modification
|
|
- Fully quantized for resource-efficient deployment
|
|
|
|
## 🛠️ Implementation
|
|
|
|
Based on research findings from ["Refusal in LLMs is Mediated by a Single Direction"](https://www.alignmentforum.org/posts/jGuXSZgv6qfdhMCuJ/refusal-in-llms-is-mediated-by-a-single-direction)
|
|
|
|
## 💫 Quantization
|
|
|
|
Pre-quantized models available in [GGFU](https://huggingface.co/BlossomsAI/Qwen2.5-Coder-7B-Instruct-Uncensored-GGUF) format:
|
|
|
|
## 🤝 Contributors
|
|
|
|
Developed with ❤️ by [BlossomAI](https://huggingface.co/BlossomsAI)
|
|
|
|
---
|
|
|
|
<div align="center">
|
|
<sub>Star ⭐️ this repo if you find it valuable!</sub>
|
|
</div> |