metadata
license: other
license_name: mrl
license_link: https://mistral.ai/licenses/MRL-0.1.md
base_model:
- mistralai/Mistral-Large-Instruct-2407
base_model_relation: quantized
tags:
- VPTQ
- Quantized
- Quantization
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
}
}