Ido Amit's Projects
"Boom" app to manage recorded lectures for courses
A package to evaluate factuality of long-form generation. Original implementation the EMNLP 2023 paper "FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation"
Final project in adversarial training course
introduction to GitHub
Config files for my GitHub profile.
AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration
A library for researching neural networks compression and acceleration methods.
PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more
SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models
š¤ Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.