Mistral-Large-Instruct-2407-v16-k65536-1024-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": 6.874824523925781,
        "c4": 10.510944366455078,
        "c4-new": 12.159836769104004
    },
    "ctx_4096": {
        "wikitext2": 6.375296592712402,
        "c4": 9.913671493530273,
        "c4-new": 11.587206840515137
    },
    "ctx_8192": {
        "wikitext2": 6.131728172302246,
        "c4": 7.288276672363281,
        "c4-new": 11.48729133605957
    }
}