huihui-ai/Llama-3.2-1B-Instruct-abliterated
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: huihui-ai/Llama-3.2-1B-Instruct-abliterated
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-13 21:51:15 +08:00
commit bba835346a
12 changed files with 412975 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
README.md Normal file
View File

@@ -0,0 +1,35 @@
---
library_name: transformers
license: llama3.2
base_model: meta-llama/Llama-3.2-1B-Instruct
tags:
- abliterated
- uncensored
---
# 🦙 Llama-3.2-1B-Instruct-abliterated
This is an uncensored version of Llama 3.2 1B Instruct created with abliteration (see [this article](https://huggingface.co/blog/mlabonne/abliteration) to know more about it).
Special thanks to [@FailSpy](https://huggingface.co/failspy) for the original code and technique. Please follow him if you're interested in abliterated models.
## ollama
You can use [huihui_ai/llama3.2-abliterate:1b](https://ollama.com/huihui_ai/llama3.2-abliterate:1b) directly,
```
ollama run huihui_ai/llama3.2-abliterate:1b
```
## Evaluations
The following data has been re-evaluated and calculated as the average for each test.
| Benchmark | Llama-3.2-1B-Instruct | Llama-3.2-1B-Instruct-abliterated |
|-------------|-----------------------|-----------------------------------|
| IF_Eval | **58.50** | 56.88 |
| MMLU Pro | **16.35** | 14.35 |
| TruthfulQA | **43.08** | 38.96 |
| BBH | **33.75** | 31.83 |
| GPQA | 25.96 | **26.39** |
The script used for evaluation can be found inside this repository under /eval.sh, or click [here](https://huggingface.co/huihui-ai/Llama-3.2-1B-Instruct-abliterated/blob/main/eval.sh)