A curated list for Efficient Large Language Models

[ICML 2023] This project is the official implementation of our accepted ICML 2023 paper BiBench: Benchmarking and Analyzing Network Binarization.

[NeurIPS 2023 Spotlight] This project is the official implementation of our accepted NeurIPS 2023 (spotlight) paper QuantSR: Accurate Low-bit Quantization for Efficient Image Super-Resolution.

The official implementation of the ICML 2023 paper OFQ-ViT

Chat to LLaMa 2 that also provides responses with reference documents over vector database. Locally available model using GPTQ 4bit quantization.

A tutorial of model quantization using TensorFlow

PyTorch implementation of "BiDense: Binarization for Dense Prediction," A binary neural network for dense prediction tasks.

This project distills a ViT model into a compact CNN, reducing its size to 1.24MB with minimal accuracy loss. ONNXRuntime with CUDA boosts inference speed, while FastAPI and Docker simplify deployment.

🔬 Curiosity-Driven Quantized Mixture of Experts

模型压缩的技术文档与项目实践

Fine-tuning Llama models with QLoRA using Unsloth for supervised instruction tasks

Replication package for the paper "Aggregating empirical evidence from data strategies studies: a case on model quantization" published in the 19th ACM/IEEE International Symposium on Empirical Software Engineering and Measurement (ESEM).

This project explores generating high-quality images using depth maps and conditioning techniques like Canny edges, leveraging Stable Diffusion and ControlNet models. It focuses on optimizing image generation with different aspect ratios, inference steps to balance speed and quality.

Unofficial implementation of NCNet using flax and jax