qwp4w3hyb/gemma-2-9b-it-iMat-GGUF

Quant Infos

• quants done with an importance matrix for improved quantization loss
• Requantized ggufs & imatrix from hf bf16
  • initial version was based on f32 gguf provided by google, which had various issues
• Wide coverage of different gguf quant types from Q_8_0 down to IQ1_S
  • experimental custom quant types
    • _L with --output-tensor-type f16 --token-embedding-type f16 (same as bartowski's)
• Quantized with llama.cpp release b3259
• Imatrix generated with this multi-purpose dataset by bartowski.

  ./imatrix -c 512 -m $model_name-bf16.gguf -f calibration_datav3.txt -o $model_name.imatrix
  

Original Model Card

TODO