31 lines
982 B
Markdown
31 lines
982 B
Markdown
|
---
|
||
|
|
library_name: transformers
|
||
|
|
license: apache-2.0
|
||
|
|
base_model: open-thoughts/OpenThinker-7B
|
||
|
|
tags:
|
||
|
|
- llama-factory
|
||
|
|
- full
|
||
|
|
- generated_from_trainer
|
||
|
|
- abliterated
|
||
|
|
- uncensored
|
||
|
|
---
|
||
|
|
|
||
|
|
# huihui-ai/OpenThinker-7B-abliterated
|
||
|
|
|
||
|
|
|
||
|
|
This is an uncensored version of [open-thoughts/OpenThinker-7B](https://huggingface.co/open-thoughts/OpenThinker-7B) 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/openthinker-abliterated](https://ollama.com/huihui_ai/openthinker-abliterated) directly
|
||
|
|
```
|
||
|
|
ollama run huihui_ai/openthinker-abliterated
|
||
|
|
```
|
||
|
|
### Donation
|
||
|
|
##### Your donation helps us continue our further development and improvement, a cup of coffee can do it.
|
||
|
|
- bitcoin:
|
||
|
|
```
|
||
|
|
bc1qqnkhuchxw0zqjh2ku3lu4hq45hc6gy84uk70ge
|
||
|
|
```
|