Stars
A very simple GRPO implement for reproducing r1-like LLM thinking.
Infinity ∞ : Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis
"LightRAG: Simple and Fast Retrieval-Augmented Generation"
🚀 「大模型」1小时从0训练26M参数的视觉多模态VLM!🌏 Train a 26M-parameter VLM from scratch in just 1 hours!
随机滚动排序:对名单内每个选项进行随机排序,如在答辩中可随机确定答辩顺序,通过人工停止滚动来保证随机的公平性。
从0到1构建一个MiniLLM (pretrain+sft+dpo实践中)
🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT!🌏 Train a 26M-parameter GPT from scratch in just 2h!
用于从头预训练+SFT一个小参数量的中文LLaMa2的仓库;24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.
AAAI 2024 Papers: Explore a comprehensive collection of innovative research papers presented at one of the premier artificial intelligence conferences. Seamlessly integrate code implementations for…
jingyaogong / MCFD-Net
Forked from songhp/MCFD-Net论文:Multi-Cross Sampling and Frequency-Division Reconstruction for Image Compressed Sensing
Multi-Cross Sampling and Frequency-Division Reconstruction for Image Compressed Sensing
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
Collection of reproducible deep learning for compressive sensing
Optimization-Inspired Cross-Attention Transformer for Compressive Sensing (CVPR 2023)
[Android] Verification code and serial number input box