Stars
Web2Code: A Large-scale Webpage-to-Code Dataset and Evaluation Framework for Multimodal LLMs
(CVPR2024)A benchmark for evaluating Multimodal LLMs using multiple-choice questions.
Examples of using sparse attention, as in "Generating Long Sequences with Sparse Transformers"
20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
Deita: Data-Efficient Instruction Tuning for Alignment [ICLR2024]
为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, m…
A flexible and efficient codebase for training visually-conditioned language models (VLMs)
VisualRWKV is the visual-enhanced version of the RWKV language model, enabling RWKV to handle various visual tasks.
A collection of visual instruction tuning datasets.
Multilingual Sentence & Image Embeddings with BERT
Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022
Official implementation of our paper "Finetuned Multimodal Language Models are High-Quality Image-Text Data Filters".
Convert avro files to parquet, csv and json format
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
✨ Innovative and open-source visualization application that transforms various data formats, such as JSON, YAML, XML, CSV and more, into interactive graphs.
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,…
Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.
The source code of IJCAI2020 paper "Unsupervised Monocular Visual-inertial Odometry Network".
Code for "Efficient Deep Visual and Inertial Odometry with Adaptive Visual Modality Selection", ECCV 2022
Deep learning algorithms source code for beginners
Top Deep Learning Projects based on their Stars!
Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
Curated list of project-based tutorials