AceMath: Advancing Frontier Math Reasoning with Post-Training and Reward Modeling
Paper • 2412.15084 • Published • 13
GGUF quants of nvidia/AceMath-72B-Instruct
Using llama.cpp b4682 (commit 0893e0114e934bdd0eba0ff69d9ef8c59343cbc3)
The importance matrix was generated with groups_merged-enhancedV3.txt by InferenceIllusionist (later renamed calibration_datav3.txt), an edited version of kalomaze's original groups_merged.txt.
All quants were generated/calibrated with the imatrix, including the K quants.
- Downloads last month
- 382
Hardware compatibility
Log In to add your hardware
1-bit
2-bit
3-bit
4-bit
5-bit
6-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support