Trending repositories for topic transformer
A high-throughput and memory-efficient inference and serving engine for LLMs
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
🧑🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), ga...
🏆 A ranked list of awesome machine learning Python libraries. Updated weekly.
Translate manga/image 一键翻译各类图片内文字 https://cotrans.touhou.ai/
A framework for few-shot evaluation of language models.
RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, sa...
multispy is a lsp client library in Python intended to be used to build applications around language servers.
SGLang is a fast serving framework for large language models and vision language models.
Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation a...
pix2tex: Using a ViT to convert images of equations into LaTeX code.
🔍 An LLM-based Multi-agent Framework of Web Search Engine (like Perplexity.ai Pro and SearchGPT)
Large Language Model Text Generation Inference
"Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement" (ICCV 2023) & (NTIRE 2024 Challenge)
multispy is a lsp client library in Python intended to be used to build applications around language servers.
[NeurIPS 2024] Knowledge Circuits in Pretrained Transformers
Code for paper: DGR-MIL: Exploring Diverse Global Representation in Multiple Instance Learning for Whole Slide Image Classification [ECCV 2024]
TradeAI: Empowering Algorithmic Trading with Deep Learning for Cryptocurrency Data. Explore the potential of deep learning in cryptocurrency trading through our full-stack algorithmic trading system, ...
Code and Data artifact for NeurIPS 2023 paper - "Monitor-Guided Decoding of Code LMs with Static Analysis of Repository Context". `multispy` is a lsp client library in Python intended to be used to bu...
llm theoretical performance analysis tools and support params, flops, memory and latency analysis.
[ECCV 2024] Official PyTorch implement of paper "ParCo: Part-Coordinating Text-to-Motion Synthesis": http://arxiv.org/abs/2403.18512
Pytorch implementation of "Genie: Generative Interactive Environments", Bruce et al. (2024).
[NeurIPS 2024] Stabilize the Latent Space for Image Autoregressive Modeling: A Unified Perspective
This repository contains the source code for our paper: "NaviSTAR: Socially Aware Robot Navigation with Hybrid Spatio-Temporal Graph Transformer and Preference Learning". For more details, please refe...
"You Only Need One Color Space: An Efficient Network for Low-light Image Enhancement"
Official Implementation of TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters
PyTorch reimplementation of the paper "Swin Transformer V2: Scaling Up Capacity and Resolution" [CVPR 2022].
[WACV 2024] "CVTHead: One-shot Controllable Head Avatar with Vertex-feature Transformer"
"Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement" (ICCV 2023) & (NTIRE 2024 Challenge)
[CoRL'22] PlanT: Explainable Planning Transformers via Object-Level Representations
A high-throughput and memory-efficient inference and serving engine for LLMs
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
🧑🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), ga...
SGLang is a fast serving framework for large language models and vision language models.
pix2tex: Using a ViT to convert images of equations into LaTeX code.
A framework for few-shot evaluation of language models.
RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, sa...
Translate manga/image 一键翻译各类图片内文字 https://cotrans.touhou.ai/
🏆 A ranked list of awesome machine learning Python libraries. Updated weekly.
multispy is a lsp client library in Python intended to be used to build applications around language servers.
《李宏毅深度学习教程》（李宏毅老师推荐👍，苹果书🍎），PDF下载地址：https://github.com/datawhalechina/leedl-tutorial/releases
🔍 An LLM-based Multi-agent Framework of Web Search Engine (like Perplexity.ai Pro and SearchGPT)
Large Language Model Text Generation Inference
Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation a...
This repository contains a reading list of papers on Time Series Forecasting/Prediction (TSF) and Spatio-Temporal Forecasting/Prediction (STF). These papers are mainly categorized according to the typ...
multispy is a lsp client library in Python intended to be used to build applications around language servers.
[NeurIPS 2024] Knowledge Circuits in Pretrained Transformers
[TIP2024] MWFormer: Multi-Weather Image Restoration Using Degradation-Aware Transformers
Code for paper: DGR-MIL: Exploring Diverse Global Representation in Multiple Instance Learning for Whole Slide Image Classification [ECCV 2024]
TradeAI: Empowering Algorithmic Trading with Deep Learning for Cryptocurrency Data. Explore the potential of deep learning in cryptocurrency trading through our full-stack algorithmic trading system, ...
Pytorch implementation of "Genie: Generative Interactive Environments", Bruce et al. (2024).
Code and Data artifact for NeurIPS 2023 paper - "Monitor-Guided Decoding of Code LMs with Static Analysis of Repository Context". `multispy` is a lsp client library in Python intended to be used to bu...
llm theoretical performance analysis tools and support params, flops, memory and latency analysis.
[NeurIPS 2024] Stabilize the Latent Space for Image Autoregressive Modeling: A Unified Perspective
This repository contains the source code for our paper: "NaviSTAR: Socially Aware Robot Navigation with Hybrid Spatio-Temporal Graph Transformer and Preference Learning". For more details, please refe...
Interpretable text embeddings by asking LLMs yes/no questions (NeurIPS 2024)
[CVPR'24 Spotlight] The official implementation of "State Space Models for Event Cameras"
Official Implementation of TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters
Curated list of methods that focuses on improving the efficiency of diffusion models
Official code, datasets and checkpoints for "Timer: Generative Pre-trained Transformers Are Large Time Series Models" (ICML 2024)
[AAAI-2024] HARDVS: Revisiting Human Activity Recognition with Dynamic Vision Sensors
A high-throughput and memory-efficient inference and serving engine for LLMs
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
🧑🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), ga...
SGLang is a fast serving framework for large language models and vision language models.
pix2tex: Using a ViT to convert images of equations into LaTeX code.
Large Language Model Text Generation Inference
🔍 An LLM-based Multi-agent Framework of Web Search Engine (like Perplexity.ai Pro and SearchGPT)
🏆 A ranked list of awesome machine learning Python libraries. Updated weekly.
A framework for few-shot evaluation of language models.
《李宏毅深度学习教程》（李宏毅老师推荐👍，苹果书🍎），PDF下载地址：https://github.com/datawhalechina/leedl-tutorial/releases
Translate manga/image 一键翻译各类图片内文字 https://cotrans.touhou.ai/
RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, sa...
Transformer: PyTorch Implementation of "Attention Is All You Need"
CEO (ceo-py) is an intuitive and modular AI agent framework for task automation.
OpenMMLab Semantic Segmentation Toolbox and Benchmark.
CEO (ceo-py) is an intuitive and modular AI agent framework for task automation.
[TIP2024] MWFormer: Multi-Weather Image Restoration Using Degradation-Aware Transformers
multispy is a lsp client library in Python intended to be used to build applications around language servers.
[NeurIPS 2024] Knowledge Circuits in Pretrained Transformers
Pytorch implementation of "Genie: Generative Interactive Environments", Bruce et al. (2024).
Official Implementation of TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters
Interpretable text embeddings by asking LLMs yes/no questions (NeurIPS 2024)
llm theoretical performance analysis tools and support params, flops, memory and latency analysis.
TradeAI: Empowering Algorithmic Trading with Deep Learning for Cryptocurrency Data. Explore the potential of deep learning in cryptocurrency trading through our full-stack algorithmic trading system, ...
[NeurIPS 2024] Stabilize the Latent Space for Image Autoregressive Modeling: A Unified Perspective
[IEEE J-BHI-2024] A Convolutional Transformer to decode mental states from Electroencephalography (EEG) for Brain-Computer Interfaces (BCI)
DSL-FIQA: Assessing Facial Image Quality via Dual-Set Degradation Learning and Landmark-Guided Transformer (CVPR 2024)
[ECCV 2024] Official PyTorch implementation of RoPE-ViT "Rotary Position Embedding for Vision Transformer"
[ECCV 2024 - Oral] HiT-SR: Hierarchical Transformer for Efficient Image Super-Resolution
A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of vLLM).
[MICCAI 2024] Region Attention Transformer for Medical Image Restoration.
SGLang is a fast serving framework for large language models and vision language models.
🔍 An LLM-based Multi-agent Framework of Web Search Engine (like Perplexity.ai Pro and SearchGPT)
Lumina-T2X is a unified framework for Text to Any Modality Generation
🤖✨ChatMLX is a modern, open-source, high-performance chat application for MacOS based on large language models.
[Mamba-Survey-2024] Paper list for State-Space-Model/Mamba and it's Applications
Official Implementation of TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters
Official code, datasets and checkpoints for "Timer: Generative Pre-trained Transformers Are Large Time Series Models" (ICML 2024)
T-GATE: Temporally Gating Attention to Accelerate Diffusion Model for Free!
[ECCV2024 Oral🔥] Official Implementation of "GiT: Towards Generalist Vision Transformer through Universal Language Interface"
[NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization
[ECCV 2024] Efficient Large-Baseline Radiance Fields, a feed-forward 2DGS model
An awesome repository & A comprehensive survey on interpretability of LLM attention heads.
JetStream is a throughput and memory optimized engine for LLM inference on XLA devices, starting with TPUs (and GPUs in future -- PRs welcome).
[ECCV 2024] Official PyTorch implementation of RoPE-ViT "Rotary Position Embedding for Vision Transformer"
Create-tsi is a generative AI RAG toolkit which generates AI Applications with low code.
Deep learning in motion deblurring: current status, benchmarks and future prospects[J], The Visual Computer, 2024.
A high-throughput and memory-efficient inference and serving engine for LLMs
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
🧑🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), ga...
SGLang is a fast serving framework for large language models and vision language models.
《李宏毅深度学习教程》（李宏毅老师推荐👍，苹果书🍎），PDF下载地址：https://github.com/datawhalechina/leedl-tutorial/releases
🔍 An LLM-based Multi-agent Framework of Web Search Engine (like Perplexity.ai Pro and SearchGPT)
pix2tex: Using a ViT to convert images of equations into LaTeX code.
A framework for few-shot evaluation of language models.
🏆 A ranked list of awesome machine learning Python libraries. Updated weekly.
Large Language Model Text Generation Inference
Translate manga/image 一键翻译各类图片内文字 https://cotrans.touhou.ai/
RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, sa...
Lumina-T2X is a unified framework for Text to Any Modality Generation
Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation a...
SGLang is a fast serving framework for large language models and vision language models.
🔍 An LLM-based Multi-agent Framework of Web Search Engine (like Perplexity.ai Pro and SearchGPT)
📰 Must-read papers and blogs on LLM based Long Context Modeling 🔥
[Mamba-Survey-2024] Paper list for State-Space-Model/Mamba and it's Applications
PyTorch native quantization and sparsity for training and inference
"Structure-Aware Sparse-View X-ray 3D Reconstruction" (CVPR 2024)
A Jax-based library for designing and training transformer models from scratch.
Official Implementation of TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters
[ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache
A collection of the the best ML and AI news every week (research, news, resources)
llm-inference is a platform for publishing and managing llm inference, providing a wide range of out-of-the-box features for model deployment, such as UI, RESTful API, auto-scaling, computing resource...
Learning Language-guided Adaptive Hyper-modality Representation for Multimodal Sentiment Analysis
Deep learning in motion deblurring: current status, benchmarks and future prospects[J], The Visual Computer, 2024.
Space Group Informed Transformer for Crystalline Materials Generation
Offical code of "QKFormer: Hierarchical Spiking Transformer using Q-K Attention" (NeurIPS 2024，Spotlight 3%)
OCR Tamil is a powerful tool that can detect and recognize text in Tamil images with high accuracy on Natural Scenes