---
license: llama3.3
language:
- en
- zh
base_model:
- Orion-zhen/llama-3.3-70b-instruct-abliterated
pipeline_tag: text-generation
---

# Llama-3.3-70B-Instruct-abliterated

Made with [Orion-zhen/abliteration](https://github.com/Orion-zhen/abliteration).

Please... give my repo a star if you find it helpful. I will do whatever you want...

---

使用 [Orion-zhen/abliteration](https://github.com/Orion-zhen/abliteration) 进行的 abliteration 操作. 校准集中包含中文, 可以减少对模型中文能力的损害. 模型使用 bitsandbytes 量化为 4bit 格式以减少显存占用.

求你了, 给我的仓库一个 star 吧, 我什么都会做的...

![i-will-do-anything](i-will-do-anything.png)