This is an importance matrix (imatrix) generated from 4 million tokens for Ornith-1.0-9B.
During testing, the imatrix-quantized model significantly outperformed the standard quantized model.
It was generated using a patched version of llama-imatrix to properly respect chunking boundaries.
Chunking was performed at both 512 and 16k.
- Downloads last month
- 11
Hardware compatibility
Log In to add your hardware
We're not able to determine the quantization variants.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for aney/Ornith-1.0-9B-imatrix-only
Base model
deepreinforce-ai/Ornith-1.0-9B