qwp4w3hyb's picture
Update README.md
85e74c5 verified
metadata
language:
  - en
  - de
  - fr
  - it
  - pt
  - hi
  - es
  - th
license: llama3.1
pipeline_tag: text-generation
tags:
  - facebook
  - meta
  - pytorch
  - llama
  - llama-3
  - gguf
  - imatrix
base_model: meta-llama/Meta-Llama-3.1-70B-Instruct

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