Edit model card

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": 3.484158515930176,
        "c4": 6.430262088775635,
        "c4-new": 7.119498252868652
    },
    "ctx_4096": {
        "wikitext2": 3.2934534549713135,
        "c4": 6.052966594696045,
        "c4-new": 6.734064102172852
    },
    "ctx_8192": {
        "wikitext2": 3.1873176097869873,
        "c4": 4.763023376464844,
        "c4-new": 6.607855796813965
    }
}
Downloads last month
13
Safetensors
Model size
12.6B params
Tensor type
I32
·
BF16
·
I16
·
Inference API
Unable to determine this model's library. Check the docs .

Model tree for VPTQ-community/Mistral-Large-Instruct-2407-v8-k65536-256-woft

Quantized
(19)
this model

Collection including VPTQ-community/Mistral-Large-Instruct-2407-v8-k65536-256-woft