Quant Infos

• Requires latest master + Rope Scaling PR. Rope scaling is merged, so just a a recent master is required now.
• quants done with an importance matrix for improved quantization loss
• Quantized ggufs & imatrix from hf bf16, through bf16. safetensors bf16 -> gguf bf16 -> quant for optimal quant loss.
• 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, which supposedly leads to better accuracy.
• Imatrix generated with this multi-purpose dataset by bartowski.
  ./imatrix -m $model_name-bf16.gguf -f calibration_datav3.txt -o $model_name.imatrix

Original Model Card: