Transformers: open-source projects on GitHub
50 repositories on Transformers, picked by the REDDYX AI agent. Each has a summary, key features and a breakdown. Sorted by stars.
// RELATED TOPICS
21 Generative AI Lessons
Free course from Microsoft: 21 lessons to start in the world of generative AI. Over 111 thousand stars on GitHub!
★ 111,765 · Jupyter NotebookBuilding LLM from Scratch
Step-by-step implementation of a ChatGPT-like model in PyTorch: tokenizer, architecture, training, and text generation.
★ 93,387 · Jupyter NotebookLlamaFactory: Unified LLM Tuning
LlamaFactory offers a unified library for efficient fine‑tuning of 100+ LLMs and VLMs, with support for LoRA, QLoRA and distributed multi‑GPU training.
★ 71,186 · PythonHaystack: AI Framework for LLM
An open framework for building production-ready LLM applications with modular control over search, routing, memory, and generation.
★ 25,289 · MDXPEFT: Efficient AI Training
The PEFT library provides state-of-the-art parameter-efficient fine-tuning methods for models, reducing resources and training time.
★ 21,199 · PythonML-ENGINEERING OPEN BOOK
Open book on ML engineering with practical materials and examples in Python.
★ 19,717 · PythonDocsGPT: Private AI Assistant
Private AI platform for agents, assistants, and enterprise search with support for multiple models.
★ 17,882 · PythonTXTAI — AI All-in-One
An algorithmic framework for semantic search, LLM orchestration, and language-model workflows. All in one!
★ 12,620 · PythonOPTIMIZATION AND DEPLOYMENT OF AI MODELS
Toolkit for optimizing and deploying deep learning models. Supports conversion from PyTorch, TensorFlow, ONNX and inference on CPU, GPU, and Intel NPU.
★ 11,656 · C++Soup: Train LLM Easily
Soup fine-tunes an LLM from a single YAML using a streaming layer — enabling an 8B model to run on a laptop with 4 GB VRAM.
★ 10,552 · PythonMLX-AUDIO: SPEECH ON APPLE SILICON
mlx-audio — library for TTS, STT and STS on Apple's MLX framework. Runs efficiently on Apple Silicon. 8192 stars on GitHub.
★ 8,267 · PythonAI engineering from scratch
Learn, build it, and deliver it to others.
★ 7,884 · PythonSpeech Tools for MLX
A text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX framework, providing efficient speech analysis on Apple Silicon.
★ 7,115 · PythonCHRONOS-FORECASTING - SMART TIME SERIES FORECASTING
Chronos provides a set of pretrained models for accurate time series forecasting out of the box in Python.
★ 6,310 · PythonTRAIN LLM FROM SCRATCH
A simple path from loading data to text generation with your own LLM.
★ 4,188 · Jupyter NotebookSPARK-NLP - REVOLUTION IN NLP
Spark NLP provides state-of-the-art NLP models and ready-to-use pipelines for scalable text processing in Scala.
★ 4,163 · ScalaSWANLAB: TRACKING AND VISUALIZATION
SwanLab is an open-source tool for tracking and visualizing AI model training, compatible with PyTorch, Transformers, and other frameworks.
★ 3,981 · PythonMAESTRO - Simplifying Model Fine-tuning
The project simplifies fine-tuning of multimodal models PaliGemma 2, Florence‑2, and Qwen2.5‑VL, saving developers time and resources.
★ 2,696 · PythonDETIKZIFY DRAWS LATEX DIAGRAMS FAST
DeTikZify turns textual descriptions or hand‑drawn sketches into ready‑to‑use TikZ code for LaTeX. The project leverages HuggingFace and Llama models for inverse graphics
★ 1,831 · PythonPRACTICAL COURSE ON LLM IN JUPYTER
The course consists of Jupyter notebooks teaching how to build chat‑bots, fine‑tune LLMs and work with Hugging Face, LangChain and RAG. Each block provides ready code and
★ 1,828 · Jupyter NotebookANYJEV TURNS LLM INTO JEV-MODEL
AnyJev converts any LLM into a Jev‑style decision model, outputting typed decisions and real probabilities without requiring retraining. The project is actively developed
★ 1,609 · PythonOpenAdapt - Boundless AI Process
OpenAdapt — an open platform for generative process automation based on LLM, LAM, and VLM models. Python, 1.6k stars, AI-first approach to RPA.
★ 1,608 · PythonPRUNA - ACCELERATING MODELS
Pruna — a Python framework for model optimization that speeds up inference and reduces resource usage without losing accuracy.
★ 1,391 · PythonRIZZO PII: Document Anonymization
A local Python utility that removes personal data from files before sending them to an LLM. Protect your privacy without leaving your computer.
★ 1,271 · PythonKVPRESS: LLM CACHE COMPRESSION
Library for easy compression of LLM KV‑cache, accelerating generation and reducing GPU memory consumption.
★ 1,254 · PythonNNCFF - ACCELERATING MODEL INFERENCE
NNCFF is a neural network compression framework for accelerated inference in OpenVINO™. It reduces model size while preserving accuracy.
★ 1,221 · PythonDOWNLOAD HUGGINGFACE MODELS EASILY
Go utility for downloading models and datasets from HuggingFace. Supports CLI call and work via API, caches files locally.
★ 1,213 · GoHow to Train Your LLM
Build a modern LLM from scratch — every line of code is commented and explained simply, as if for a five-year-old.
★ 984 · Jupyter NotebookDEEPGIT: GITHUB HUNTER
DeepGit — a Python agent for finding the best GitHub repositories by topic. It uses LangChain and LangGraph to perform deep code and documentation analysis. Returns a sor
★ 929 · PythonHALO: FRAMEWORK FOR LLM TRAINING
Halo is an open-source framework from White Circle for training large language and multimodal models. It supports agent-based training, async-RL, distributed training, an
★ 862 · PythonRISC-V CPU COMPILED INTO QWEN3.5 WEIGHTS
Qwen3.5-4B with a 32-bit RISC-V CPU compiled directly into model weights. CPU uses Gated DeltaNet state as RAM and executes code inside model forward pass.
★ 814 · PythonTENSORSHARP - POWERFUL .NET LLM
A library for quickly launching GGUF models on .NET with GPU support, console app, web chat, and an API compatible with Ollama and OpenAI.
★ 679 · C#OPTIMUM-INTEL - ACCELERATE INFERENCE WITH INTEL
Optimum Intel provides Intel tools to accelerate AI model inference, simplifying deployment and boosting performance.
★ 630 · Jupyter NotebookRandOpt: Task Experts Optimization
Code for ICML 2026: diverse task experts are densest around pretrained weights.
★ 590 · PythonOPEN-SOURCE AIaaS PLATFORM
RESTai — an AIaaS platform with Ollama/vLLM support, built-in image and audio generation, visual block programming, and analytics.
★ 520 · PythonPYTORCH REPLICATIONS OF SOTA PAPERS
429 stars. From-scratch implementations of transformers, diffusion, GAN, CLIP, LoRA, MoE in Jupyter Notebook. Includes SFT and GRPO post-training experiments.
★ 430 · Jupyter NotebookPMETAL: THE ACCEL LLM ON APPLE SILICON
PMetal — Rust framework for high‑performance LLM inference on Apple Silicon. Supports local inference, LoRA/QLoRA fine‑tuning, serving, quantization, and MLX/Metal accele
★ 333 · RustNEURALGRAFFITI: LIVE LLM OUTPUT CONTROL
NeuralGraffiti is a tool for live transformation of foundation model outputs directly at the neural network level. Works in real time without retraining.
★ 274 · Jupyter NotebookInteractive AI Learning App
A TypeScript-based desktop application offering 51 hands‑on labs that teach ML basics, transformers, RAG, agents, fine‑tuning, and quantization.
★ 256 · TypeScriptSUBTEXT: BEHIND THE MODEL
A tool for analyzing hidden representations of AI models, revealing their internal logic.
★ 248 · HTMLJ-WASH: LLM TOOL
Tool for manual alignment of large language models using Jacobian Lens, with results exported.
★ 242 · PythonInference Engine for Cybersecurity
High-performance inference engine in Rust with safe memory handling for cybersecurity tasks.
★ 240 · RustZOTSEEK AI SEARCH IN ZOTERO
ZotSeek adds semantic search to your Zotero library using vector embeddings. The built-in MCP server lets you connect Claude Code and Codex as AI agents for meaning‑based
★ 239 · TypeScriptTOKEN-PRINT 3D VISUALIZATION
Token-Print is an interactive platform for 3D visualization of transformer models, tensors, and real-time LLM inference. It supports loading models from Hugging Face and
★ 226 · TypeScriptLLM Alignment Tuning
Automatic calibration of the language model's censorship layer via direct weight modification and the use of LoRA and MoE experts.
★ 221 · PythonAI IN BROWSER WITHOUT SERVER
Library of providers for Vercel AI SDK runs models directly in the browser. Simplifies client-side AI integration and unifies work across vendors. 205 stars on GitHub.
★ 207 · TypeScriptBilingual Urdu-English Legal RAG
RAG system for Pakistani government and legal documents with Urdu-English OCR, hybrid retrieval, and citation grounding.
★ 130 · PythonRose — PyTorch Optimizer
Stateless PyTorch optimizer that normalizes gradients for stable and balanced model training.
★ 60 · PythonLabLLM on macOS
LabLLM is a native macOS app where you can build the architecture of a tiny language model, train its weights, and see the model emerge from scratch on Apple Silicon usin
★ 39 · SwiftCan I finetune this?
Tool to check whether a Hugging Face model fits in your GPU memory and can be fine-tuned locally.
★ 31 · PythonNew projects on this topic in Telegram
Telegram →