NaniDAO/Meta-Llama-3.1-8B-Instruct-ablated-v1
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: NaniDAO/Meta-Llama-3.1-8B-Instruct-ablated-v1
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-25 05:55:13 +08:00
commit b9e68df099
13 changed files with 413054 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
README.md Normal file
View File

@@ -0,0 +1,12 @@
---
library_name: transformers
tags: []
---
# Model Card for Model ID
[Llama 3.1 instruct 8b 128k](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) context with [ablation](https://www.lesswrong.com/posts/jGuXSZgv6qfdhMCuJ/refusal-in-llms-is-mediated-by-a-single-direction).
This means it will refuse less of your valid requests for an uncensored UX. This version is an improvement on the [v0](https://huggingface.co/NaniDAO/Meta-Llama-3.1-8B-Instruct-ablated). Use this 8b for best results.
Use responsibly and at your own discretion. We do not take any responsibility for how you apply this intelligence, just as we do not for how you apply your own.