lymdlut's Projects
Simple Realization of Several Classic Deep Learning Model
A universal Stable-Diffusion toolbox
Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding
InternLM has open-sourced a 7 billion parameter base model, a chat model tailored for practical scenarios and the training system.
The official Meta Llama 3 GitHub site
Fast OneDrive Index,OneDrive 秒级列表程序
MiniGPT-4: Enhancing Vision-language Understanding with Advanced Large Language Models
Personal Project: MPP-Qwen(Multimodal Pipeline Parallel-Qwen). Align ViT+ BLIP2 Qformer with Qwen-Chat LLM and scale up to Qwen-14B-Chat via DeepSpeed Pipeline Parallel. Just fine-tune the projection layer using 585k llava-pretrain data and 18.8k high-quality instruction-tuning data(Bi-lingual, from minigpt4 and llava).
Code for paper titled "Towards the Law of Capacity Gap in Distilling Language Models"
OpenMMLab Multimodal Advanced, Generative, and Intelligent Creation Toolbox. Unlock the magic 🪄: Generative-AI (AIGC), easy-to-use APIs, awsome model zoo, diffusion models, for text-to-image generation, image/video restoration/enhancement, etc.
OpenMMLab Computer Vision Foundation
OpenMMLab Detection Toolbox and Benchmark
mmdetection最小学习版
llm deploy project based mnn.
An Easy-to-use, Scalable and High-performance RLHF Framework (Support 70B+ full tuning & LoRA & Mixtral & KTO)
Latest paper about small object detection
2022中山大学模式识别
Pix2Seq - A general framework for turning RGB pixels into semantically meaningful sequences
convert dataset to coco/voc format
The official PyTorch implementation of "Adversarially-Aware Robust Object Detector"