VPTQ Qwen 2.5 32B Instruct without finetune
Collection
arxiv.org/abs/2409.17066, VPTQ Qwen 2.5 32B Instruct without finetune
•
5 items
•
Updated
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": 6.8947319984436035
},
"ctx_4096": {
"wikitext2": 6.409426689147949
},
"ctx_8192": {
"wikitext2": 6.140383720397949
}
}