|
--- |
|
library_name: transformers |
|
license: mit |
|
language: |
|
- en |
|
- vi |
|
base_model: |
|
- sail/Sailor2-8B-Chat |
|
--- |
|
|
|
# Model Card for Model ID |
|
|
|
<!-- Provide a quick summary of what the model is/does. --> |
|
|
|
Sailor2-8B-Chat-Uncensored |
|
|
|
|
|
## Model Details |
|
|
|
### Model Description |
|
Abliterated version of [sail/Sailor2-8B-Chat](https://huggingface.co/sail/Sailor2-8B-Chat) |
|
|
|
It based on the technique described in the blog post "[Refusal in LLMs is mediated by a single direction](https://www.alignmentforum.org/posts/jGuXSZgv6qfdhMCuJ/refusal-in-llms-is-mediated-by-a-single-direction)". |
|
|
|
## ⚡ Quantization |
|
|
|
* **GGUF**: https://huggingface.co/BlossomsAI/Sailor2-8B-Chat-Uncensored-GGUF |
