not made with biprojected norm preservation

regular ablated only

for likely more stable version see https://huggingface.co/vprilepskii/Harbinger-24B-biprojected-norm-preserving-abliterated

harb

Downloads last month
4
GGUF
Model size
24B params
Architecture
llama
Hardware compatibility
Log In to add your hardware

8-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Collection including Naphula/Harbinger-24B-abliterated-Q8_0-GGUF