Mistral-Large-Instruct-2407-v8-k65536-0-woft

Disclaimer:

The model is reproduced based on the paper VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models github and arXiv

The model itself is sourced from a community release.

It is intended only for experimental purposes.

Users are responsible for any consequences arising from the use of this model.

Note:

The PPL test results are for reference only and were collected using GPTQ testing script.

{
    "ctx_2048": {
        "wikitext2": 4.733607292175293,
        "c4": 7.597944736480713,
        "c4-new": 8.575641632080078
    },
    "ctx_4096": {
        "wikitext2": 4.495976448059082,
        "c4": 7.27150297164917,
        "c4-new": 8.283945083618164
    },
    "ctx_8192": {
        "wikitext2": 4.373597621917725,
        "c4": 5.573808670043945,
        "c4-new": 8.310025215148926
    }
}