vineeths96 / Compressed-TransformersLinks
In this repository, we explore model compression for transformer architectures via quantization. We specifically explore quantization aware training of the linear layers and demonstrate the performance for 8 bits, 4 bits, 2 bits and 1 bit (binary) quantization.
☆24Updated 4 years ago
Alternatives and similar repositories for Compressed-Transformers
Users that are interested in Compressed-Transformers are comparing it to the libraries listed below
Sorting:
- [ICASSP'22] Integer-only Zero-shot Quantization for Efficient Speech Recognition☆34Updated 3 years ago
- Position-based Scaled Gradient for Model Quantization and Pruning Code (NeurIPS 2020)☆26Updated 4 years ago
- OTOv1-v3, NeurIPS, ICLR, TMLR, DNN Training, Compression, Structured Pruning, Erasing Operators, CNN, Diffusion, LLM☆46Updated 9 months ago
- Post-training sparsity-aware quantization☆34Updated 2 years ago
- [ICML 2022] "Coarsening the Granularity: Towards Structurally Sparse Lottery Tickets" by Tianlong Chen, Xuxi Chen, Xiaolong Ma, Yanzhi Wa…☆33Updated 2 years ago
- This repository containts the pytorch scripts to train mixed-precision networks for microcontroller deployment, based on the memory contr…☆50Updated last year
- An 8bit automated quantization conversion tool for the pytorch (Post-training quantization based on KL divergence)☆33Updated 5 years ago
- ☆28Updated 3 years ago
- PyTorch Quantization Aware Training Example☆138Updated last year
- Implementation of NeurIPS 2019 paper "Normalization Helps Training of Quantized LSTM"☆31Updated last year
- Code for High-Capacity Expert Binary Networks (ICLR 2021).☆27Updated 3 years ago
- ☆205Updated 3 years ago
- Implementation of a Quantized Transformer Model☆19Updated 6 years ago
- [ICLR 2022 Oral] F8Net: Fixed-Point 8-bit Only Multiplication for Network Quantization☆95Updated 3 years ago
- PyTorch implementation of "Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference"☆56Updated 5 years ago
- Code repo for the paper BiT Robustly Binarized Multi-distilled Transformer☆110Updated 2 years ago
- Binarize convolutional neural networks using pytorch☆147Updated 3 years ago
- ☆12Updated last year
- Prune DNN using Alternating Direction Method of Multipliers (ADMM)☆98Updated 5 years ago
- The collection of training tricks of binarized neural networks.☆72Updated 4 years ago
- Awesome Quantization Paper lists with Codes☆11Updated 4 years ago
- Quantize pytorch model, support post-training quantization and quantization aware training methods☆14Updated 2 years ago
- ☆17Updated 2 years ago
- A collection of research papers on efficient training of DNNs☆70Updated 3 years ago
- [TMLR] Official PyTorch implementation of paper "Quantization Variation: A New Perspective on Training Transformers with Low-Bit Precisio…☆45Updated 10 months ago
- BitSplit Post-trining Quantization☆50Updated 3 years ago
- [ICML'21 Oral] I-BERT: Integer-only BERT Quantization☆255Updated 2 years ago
- [ICLR 2022] "Unified Vision Transformer Compression" by Shixing Yu*, Tianlong Chen*, Jiayi Shen, Huan Yuan, Jianchao Tan, Sen Yang, Ji Li…☆54Updated last year
- A Out-of-box PyTorch Scaffold for Neural Network Quantization-Aware-Training (QAT) Research. Website: https://github.com/zhutmost/neuralz…☆26Updated 2 years ago
- PyTorch implementation for the APoT quantization (ICLR 2020)☆277Updated 7 months ago