Daniel Ji's starred repositories
Efficient-Multimodal-LLMs-Survey
Efficient Multimodal Large Language Models: A Survey
MedLLMsPracticalGuide
A curated list of practical guide resources of Medical LLMs (Medical LLMs Tree, Tables, and Papers)
visualize-accepted-papers
Statistics and Visualization of acceptance information, main keyword of CVPR 2022 accepted papers for the main Computer Vision conferences (CVPR/ICCV/WACV...)
RWKV-LM
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, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.
tensor-book
张量计算系列教程 (Tensor Computations Tutorials)
Perplexica
Perplexica is an AI-powered search engine. It is an Open source alternative to Perplexity AI
medimeta-pytorch
The medical imaging meta-learning toolbox allows to build models that learn to learn in a setting with diverse tasks. It also provides code for working with the MIMeta Dataset as well as simple baselines.
VLM_survey
Collection of AWESOME vision-language models for vision tasks
Open-Sora-Plan
This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.
TinyLLaVA_Factory
A Framework of Small-scale Large Multimodal Models
accelerate
🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support
MedicalGPT
MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型,实现了包括增量预训练(PT)、有监督微调(SFT)、RLHF、DPO、ORPO。