GGUF importance matrix (imatrix) quants for https://huggingface.co/mlabonne/AlphaMonarch-7B
The importance matrix was trained for ~50K tokens (105 batches of 512 tokens) using a general purpose imatrix calibration dataset.
| Layers | Context | Template |
|---|---|---|
32 |
32768 |
<s>user |
- Downloads last month
- 9
Hardware compatibility
Log In
to view the estimation
3-bit
4-bit
8-bit