AQLM
Model compressor
An implementation of a method to compress large language models using additive quantization and fine-tuning.
Official Pytorch repository for Extreme Compression of Large Language Models via Additive Quantization https://arxiv.org/pdf/2401.06118.pdf and PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression https://arxiv.org/abs/2405.14852
1k stars
19 watching
180 forks
Language: Python
last commit: almost 2 years agoLinked from 1 awesome list
amrzv/awesome-colab-notebooksRelated projects:
| Repository | Description | Stars |
|---|---|---|
 huggingface/optimum-quanto | A PyTorch quantization backend for models. | 847 |
 intel/neural-compressor | Tools and techniques for optimizing large language models on various frameworks and hardware platforms. | 2,257 |
 quant-aq/py-smps | A Python library for analyzing and visualizing data from various aerosol sizing instruments | 34 |
 opengvlab/omniquant | A software framework for accurately quantizing large language models using a novel technique | 739 |
 ist-daslab/gptq | An implementation of post-training quantization algorithm for transformer models to reduce memory usage and improve inference speed | 1,964 |
 locuslab/qpth | A solver for optimizing quadratic programs in deep learning and other fields. | 691 |
 jvalegre/aqme | Automated workflows for quantum mechanical environments using Python. | 100 |
 pasqal-io/pyqtorch | A PyTorch-based simulator for quantum machine learning | 45 |
 kefirski/pytorch_rvae | A deep learning implementation of a recurrent variational autoencoder for generating sequential data. | 357 |
 oscarhiggott/pymatching | A software library for decoding quantum error-correcting codes using a minimum-weight perfect matching algorithm | 195 |
 zlatko-minev/pyepr | Automated design and analysis of quantum microwave circuits | 169 |
 jmtomczak/vae_vpflows | A PyTorch implementation of volume-preserving flows for variational autoencoders. | 90 |
 karpathy/pytorch-made | An implementation of a masked autoencoder density estimation model in PyTorch | 541 |
 vprusso/toqito | A Python library providing numerical tools for studying quantum information objects | 157 |
 adgt/qonduit | A Python library providing visualization tools and workflows for quantum computing | 13 |