apple / ml-batchquant
☆19Updated 2 years ago
Related projects ⓘ
Alternatives and complementary repositories for ml-batchquant
- This repository contains the official implementation for the ECCV'22 paper, "SPIN: An Empirical Evaluation on Sharing Parameters of Isotr…☆19Updated last year
- Self-Conditioning Pre-Trained Language Models, ICML 2022☆30Updated 2 years ago
- ☆11Updated 2 years ago
- Export utility for unconstrained channel pruned models☆66Updated last year
- Tune-Mode ConvBN Blocks For Efficient Transfer Learning☆15Updated last year
- Repository accompanying the Interspeech 2022 publication titled "Space-Efficient Representation of Entity-centric Query Language Models" …☆13Updated 2 years ago
- ☆42Updated 2 years ago
- ☆18Updated 3 years ago
- ☆22Updated 2 years ago
- DUET: 2D Structured and Approximately Equivariant Representations, ICML 2023☆16Updated last year
- ☆11Updated last year
- ☆14Updated last year
- A light-weight implementation of ICCV2023 paper "Reinforce Data, Multiply Impact: Improved Model Accuracy and Robustness with Dataset Rei…☆77Updated last year
- ☆43Updated last year
- ☆69Updated 10 months ago
- ☆12Updated 4 months ago
- ☆11Updated 7 months ago
- ☆26Updated last year
- See the device (CPU/GPU/ANE) and estimated cost for every layer in your CoreML model.☆18Updated 5 months ago
- ☆25Updated last year
- Multilingual Knowledge Graph Enhancement (EMNLP 2023)☆14Updated 11 months ago
- Dynamic Neural Architecture Search Toolkit☆29Updated 5 months ago
- Research publication code for "Forward Compatible Training for Large-Scale Embedding Retrieval Systems", CVPR 2022, and "FastFill: Effici…☆53Updated last year
- Research publication code for "Least Squares Binary Quantization of Neural Networks"☆81Updated last year
- Whispering Experts: Neural Interventions for Toxicity Mitigation in Language Models, ICML 2024☆15Updated 4 months ago
- ☆41Updated 7 months ago
- ☆58Updated 8 months ago
- Pre-built copy of the web renderer for Swift-DocC documentation.☆14Updated this week
- VIT inference in triton because, why not?☆19Updated 5 months ago
- A block oriented training approach for inference time optimization.☆30Updated 3 months ago