DeepSeek 资料大全🔥，DeepSeek 使用，指令指南，应用开发指南，精选资源清单，更好的使用 DeepSeek 让你的生产力 10倍提升! 🚀

[COLING 2025]A curated paper list about LLMs for chemistry

Conformalized Credal Set Predictors (NeurIPS 2024)

This is a replicate of DeepSeek-R1-Zero and DeepSeek-R1 training on small models with limited data

AIInfra（AI 基础设施）指AI系统从底层芯片等硬件，到上层软件栈支持AI大模型训练和推理。

Collecting awesome papers of RAG for AIGC. We propose a taxonomy of RAG foundations, enhancements, and applications in paper "Retrieval-Augmented Generation for AI-Generated Content: A Survey".

Sky-T1: Train your own O1 preview model within $450

Finetune Llama 3.3, DeepSeek-R1 & Reasoning LLMs 2x faster with 70% less memory! 🦥

DRT-o1: Optimized Deep Reasoning Translation via Long Chain-of-Thought

Official PyTorch implementation of paper "CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up".

A curated list of awesome LLM Inference-Time Self-Improvement (ITSI, pronounced "itsy") papers from our recent survey: A Survey on Large Language Model Inference-Time Self-Improvement.

[CVPR 2025] TinyFusion: Diffusion Transformers Learned Shallow

[NeurIPS 2024 Best Paper][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ult…

A Survey of Attributions for Large Language Models

The first Object-Oriented Programming (OOP) Evaluaion Benchmark for LLMs

A high-throughput and memory-efficient inference and serving engine for LLMs

Official Implementation of ICLR 2024 paper: "Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning"

[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型

Qwen2.5-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

List of papers on Self-Correction of LLMs.

A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 🍓 and reasoning techniques.

A bibliography and survey of the papers surrounding o1

Large Reasoning Models

[NeurIPS 2024] The official implementation of paper: Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs.

A new dataset of difficult graduate-level applied mathematics problems; evaluations demonstrate that leading LLMs currently exhibit low accuracy in solving these problems.

Repository for the code and dataset for the paper: "Have LLMs Advanced enough? Towards Harder Problem Solving Benchmarks For Large Language Models"

Qwen2.5 is the large language model series developed by Qwen team, Alibaba Cloud.