procedural reasoning datasets

Simple GRPO scripts and configurations.

Open Thoughts: Fully Open Data Curation for Thinking Models

The source code for the blog post The 37 Implementation Details of Proximal Policy Optimization

streamline the fine-tuning process for multimodal models: PaliGemma 2, Florence-2, and Qwen2.5-VL

DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding

Reproduce R1 Zero on Logic Puzzle

The official repo for "AceCoder: Acing Coder RL via Automated Test-Case Synthesis"

Witness the aha moment of VLM with less than $3.

Make any LLM to think like OpenAI o1 and deepseek R1

A library for advanced large language model reasoning

🐭 A tiny single-file implementation of Group Relative Policy Optimization (GRPO) as introduced by the DeepSeekMath paper

s1: Simple test-time scaling

RAG Web UI is an intelligent dialogue system based on RAG (Retrieval-Augmented Generation) technology.

Everything you need to build state-of-the-art foundation models, end-to-end.

Open replication of DeepSeek R1 for text-to-graph extraction.

Automatic Evals for LLMs

🌾 OAT: A research-friendly framework for LLM online alignment, including preference learning, reinforcement learning, etc.

Code for "Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate"

DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

RAGEN is the first open-source reproduction of DeepSeek-R1 on AGENT training.

Synthetic Data curation for post-training and structured data extraction

This repository offers a comprehensive collection of tutorials on state-of-the-art computer vision models and techniques. Explore everything from foundational architectures like ResNet to cutting-e…

主要记录大语言大模型（LLMs） 算法（应用）工程师相关的知识及面试题

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

Fully open reproduction of DeepSeek-R1