Mistral-Large-Instruct-2407-v16-k65536-65536-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": 4.266016960144043,
        "c4": 7.055798530578613,
        "c4-new": 7.898081302642822
    },
    "ctx_4096": {
        "wikitext2": 4.011552333831787,
        "c4": 6.7151970863342285,
        "c4-new": 7.487395763397217
    },
    "ctx_8192": {
        "wikitext2": 3.88692045211792,
        "c4": 5.2052001953125,
        "c4-new": 7.350536346435547
    }
}