This repository is the official companion code for the book "Build a Reasoning Model (From Scratch)" by Sebastian Raschka (Manning, 2025). It is primarily a data_research codebase focused on building, evaluating, and training reasoning LLMs from scratch using the Qwen3 0.6B model as a base. The code covers inference-time scaling (temperature/top-p sampling, self-consistency), reinforcement learning from verifiable rewards (GRPO/RLVR), self-refinement, and knowledge distillation from larger teachers (DeepSeek-R1, Qwen3 235B). It includes a full custom Qwen3 implementation with KV cache, RoPE, and grouped-query attention, plus training scripts, notebooks, benchmark evaluations (MATH-500, MMLU), and Hugging Face export adapters. While educational in nature, it demonstrates production-quality engineering for research experiments. The repository is hybrid: it provides a reusable Python package for text generation and training, but its dominant character is data_research due to its notebook-driven, experimental, and benchmark-focused workflow.
This repository provides a comprehensive, production-grade training framework for fine-tuning the Qwen-VL family of vision-language models (Qwen2-VL, Qwen2.5-VL, Qwen3-VL, Qwen3.5) using HuggingFace Transformers, Liger-Kernel, and DeepSpeed. It supports Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), Group Relative Policy Optimization (GRPO), and classification fine-tuning. The architecture is modular: dataset loaders handle mixed-modality (image/video/text) data with reasoning field support, custom trainer subclasses optimize memory and enable generation-based evaluation, and model wrappers provide sequence classification heads with configurable MLP bridges. Key engineering achievements include monkey-patched vision transformer forward passes for reduced memory usage, robust handling of DeepSpeed ZeRO-3 with dummy vision inputs for text-only batches, and a workaround for PEFT/DeepSpeed compatibility. The codebase is actively maintained, dependencies are pinned, and the project demonstrates strong craftsmanship with several reusable components.
AgentFlow is a framework for building and training agentic LLM systems using reinforcement learning, specifically Flow-GRPO (Flow-based Group Refined Policy Optimization). It provides a modular architecture with four core roles—Planner, Executor, Verifier, and Generator—that coordinate via evolving memory and tool calls over multiple turns. The system supports both inference (via a Solver) and distributed RL training (via a Trainer/Client/Server architecture built on verl, vLLM, and Ray). It includes a multi-provider LLM engine abstraction (OpenAI, Anthropic, Gemini, DeepSeek, etc.), a tool system with metadata-driven discovery, and instrumentation for tracing and reward collection. The repository is heavily research-oriented, with benchmark datasets (AIME24, GPQA, GAIA, HotPotQA, etc.) and training pipelines for optimizing agent planners. While primarily an application framework, it has strong data/research components, making it a hybrid project with a focus on reproducible agentic reasoning experiments.
LLaVA-NeXT is a large multimodal model (LMM) research codebase that extends the LLaVA family to support single-image, multi-image, video, and interleaved tasks. It provides training pipelines for supervised fine-tuning (SFT), direct preference optimization (DPO), and reinforcement learning (PPO, GRPO) with custom vision encoders (CLIP, SigLIP, EVA-CLIP, MLCD) and modular projector/resampler components. The repository also includes a full RL training framework (EasyR1/verl) for large-scale GRPO training using Ray, FSDP, and vLLM, as well as evaluation scripts for video and interleaved benchmarks. While primarily a research codebase with extensive training configurations and experimental scripts, it also contains serving infrastructure (Gradio, SGLang, controller-worker) for deployment. The code is well-structured with reusable vision encoder wrappers, data protocols, and RL algorithm implementations, but suffers from hardcoded internal paths, multiple overlapping RL implementations, and legacy training pipelines that increase maintenance burden.
This repository is an educational book/course (DataWhale 'diy-llm') that teaches building and training LLMs from scratch. It spans the full pipeline: tokenizer, Transformer architecture, GPU high-performance programming, scaling laws, data engineering, distributed training, alignment (including GRPO/RLVR), evaluation, and multimodal models. The content is primarily Chinese, with Jupyter notebooks and code snippets embedded in markdown chapters. It is not a production library or application; it is a tutorial/textbook with homework assignments.
Open-R1 is a research-focused application for reproducing DeepSeek-R1's training and evaluation pipeline. It provides scripts for supervised fine-tuning (SFT) and group relative policy optimization (GRPO), along with tools for synthetic data generation using teacher models, dataset filtering based on pass rates, and evaluation on reasoning and code benchmarks (AIME, MATH, GPQA, LiveCodeBench). The project is a collection of CLI scripts and Python modules rather than a deployed service. It integrates tightly with Hugging Face Hub, Weights & Biases, and external code execution providers (E2B, Morph, Piston) for reward computation. The codebase exhibits good modularity in its reward functions and code execution provider abstractions, but is now deprecated in favor of upstream TRL. The repo is primarily a training/evaluation application, though aspects like dataset filtering and decontamination make it hybrid with data-research characteristics.
This repository is a comprehensive educational resource focused on large language models (LLMs), reinforcement learning (RL), and related training algorithms. It contains over 100 original diagrams (SVG/PNG/PDF) covering topics such as LLM architecture, SFT, DPO, RLHF, PPO, GRPO, policy gradient, and reasoning optimization. The repo also includes a curated index of open-source LLMs and VLMs with links to papers, code, and configs. While not a traditional software application or data pipeline, it serves as a visual knowledge base for researchers and practitioners in AI alignment and model training. The only executable code is a few utility scripts for image processing; the main value lies in the meticulously crafted diagrams that explain complex concepts with clarity. The repo is actively maintained and frequently updated with new content.