Model Card for Model ID
SeaLLMs-v3-1.5B-Chat Uncensored
Model Details
Model Description
Abliterated version of SeaLLMs/SeaLLMs-v3-1.5B-Chat
It based on the technique described in the blog post "Refusal in LLMs is mediated by a single direction".
âš¡ Quantization
- Downloads last month
- 172
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.