ENOSYS/GLM-4.7-Flash-Uncensored-750-v1-GGUF
4848
Experimental global target bits‑per‑weight quantization of HauhauCS/GLM-4.7-Flash-Uncensored-HauhauCS-Aggressive
- Using non-standard (forked) LLaMA C++ branch for quantization.
- Using a CLI tool to build KLD evaluation and imatrix calibration datasets for GGUF models, sourced from eaddario/imatrix-calibration.
- Using dataset sources: tools, math, code, texten, textru.
- Using dataset chunks: 750.
- Tensors quantinization F16 instead of BF16, Nvidia Pascal architecture friendly like P100.
- Small set of patches added.
Many thanks to Ed Addario for an impressive job.
