Label Studio is a multi-type data labeling and annotation tool with standardized output format

Ongoing research training transformer models at scale

Puzzles for learning Triton

👀

My personal homepage

Memory optimized finetuning scripts for CogVideoX using TorchAO and DeepSpeed

[ECCV 2024] official code for "Long-CLIP: Unlocking the Long-Text Capability of CLIP"

InstantID : Zero-shot Identity-Preserving Generation in Seconds 🔥

[NeurIPS 2023] Reflexion: Language Agents with Verbal Reinforcement Learning

PPTC Benchmark: Evaluating Large Language Models for PowerPoint Task Completion

Tk-Instruct is a Transformer model that is tuned to solve many NLP tasks by following instructions.

Accompanying repo for the RLPrompt paper

Progressive Prompts: Continual Learning for Language Models

EMNLP'2021: SimCSE: Simple Contrastive Learning of Sentence Embeddings https://arxiv.org/abs/2104.08821

MetaFormer Baselines for Vision

Code for CodeT5: a new code-aware pre-trained encoder-decoder model.

Models and examples built with TensorFlow

PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more

CVNets: A library for training computer vision networks

A pre-trained GPT model for Python code completion and generation

[ECCV 2022] Source code of "EdgeFormer: Improving Light-weight ConvNets by Learning from Vision Transformers"

Dense Passage Retriever - is a set of tools and models for open domain Q&A task.