Quantization-Aware Healing: a compressed, 4-bit model that outperforms its full-precision original
Imported from official source
This version
- Version
- 1 of 1
- Recorded
- September 15, 2026 19:08
- Change
- Initial
- Content hash
26f43a49d65971806f598e3d01c1a21d- All versions
- Revision history