Highlights
- Pro
Stars
Command-line program to download videos from YouTube.com and other video sites
Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)
Graph Neural Network Library for PyTorch
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
A resource for learning about Machine learning & Deep Learning
PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO
Modeling, training, eval, and inference code for OLMo
3D ResNets for Action Recognition (CVPR 2018)
PyTorch for Semantic Segmentation
PyTorch native quantization and sparsity for training and inference
[ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models
Implementation of 🦩 Flamingo, state-of-the-art few-shot visual question answering attention net out of Deepmind, in Pytorch
ReFT: Representation Finetuning for Language Models
PyTorch Re-Implementation of "The Sparsely-Gated Mixture-of-Experts Layer" by Noam Shazeer et al. https://arxiv.org/abs/1701.06538
Official repository for "AM-RADIO: Reduce All Domains Into One"
A Pytorch implementation of Sparsely-Gated Mixture of Experts, for massively increasing the parameter count of language models
[ICML2024 (Oral)] Official PyTorch implementation of DoRA: Weight-Decomposed Low-Rank Adaptation
FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.
[NeurIPS 2020] "Graph Contrastive Learning with Augmentations" by Yuning You, Tianlong Chen, Yongduo Sui, Ting Chen, Zhangyang Wang, Yang Shen
Code for KDD'20 "Generative Pre-Training of Graph Neural Networks"
Official implementation for NIPS'17 paper: PredRNN: Recurrent Neural Networks for Predictive Learning Using Spatiotemporal LSTMs.
QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving