初始化项目,由ModelHub XC社区提供模型

Model: huihui-ai/EXAONE-3.5-7.8B-Instruct-abliterated
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-04 07:40:13 +08:00
commit 130629b541
21 changed files with 620050 additions and 0 deletions

30
README.md Normal file
View File

@@ -0,0 +1,30 @@
---
license: other
license_name: exaone
license_link: LICENSE
language:
- en
- ko
tags:
- lg-ai
- exaone
- exaone-3.5
- abliterated
- uncensored
base_model: LGAI-EXAONE/EXAONE-3.5-7.8B-Instruct
pipeline_tag: text-generation
library_name: transformers
---
# huihui-ai/EXAONE-3.5-7.8B-Instruct-abliterated
This is an uncensored version of [LGAI-EXAONE/EXAONE-3.5-7.8B-Instruct](https://huggingface.co/LGAI-EXAONE/EXAONE-3.5-7.8B-Instruct) created with abliteration (see [remove-refusals-with-transformers](https://github.com/Sumandora/remove-refusals-with-transformers) to know more about it).
This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens.
## Use with ollama
You can use [huihui_ai/exaone3.5-abliterated](https://ollama.com/huihui_ai/exaone3.5-abliterated) directly,
```
ollama run huihui_ai/exaone3.5-abliterated:7.8b
```