license, language, tags, base_model, library_name
| license |
language |
tags |
base_model |
library_name |
| llama3.1 |
|
|
| cognitivecomputations/Dolphin3.0-Llama3.1-8B |
|
transformers |
huihui-ai/Dolphin3.0-Llama3.1-8B-abliterated
This is an uncensored version of cognitivecomputations/Dolphin3.0-Llama3.1-8B created with abliteration (see 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/dolphin3-abliterated directly
