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:

TODO

Downloads last month
453
GGUF
Model size
70.6B params
Architecture
llama

1-bit

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Examples
Unable to determine this model's library. Check the docs .

Model tree for qwp4w3hyb/Meta-Llama-3.1-70B-Instruct-iMat-GGUF

Quantized
(95)
this model