Mistral-Large-Instruct-2407-v16-k65536-4096-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": 5.553011894226074,
        "c4": 8.652666091918945,
        "c4-new": 9.73157024383545
    },
    "ctx_4096": {
        "wikitext2": 5.211401462554932,
        "c4": 8.188929557800293,
        "c4-new": 9.296350479125977
    },
    "ctx_8192": {
        "wikitext2": 5.047763824462891,
        "c4": 6.175860404968262,
        "c4-new": 9.237408638000488
    }
}