raphaelsty

raphaelsty's Stars

• sgl-project/sglang

  SGLang is a fast serving framework for large language models and vision language models.

  Language:Python17.9k1173.2k2.9k

• microsoft/pyright

  Static Type Checker for Python

  Language:Python14.8k1347.2k1.7k

• Jiayi-Pan/TinyZero

  Minimal reproduction of DeepSeek R1-Zero

  Language:Python12.2k128851.5k

• FlagOpen/FlagEmbedding

  Retrieval and Retrieval-augmented LLMs

  Language:Python10.5k531.2k782

• EleutherAI/lm-evaluation-harness

  A framework for few-shot evaluation of language models.

  Language:Python10.1k441.5k2.7k

• lightpanda-io/browser

  Lightpanda: the headless browser designed for AI and automation

  Language:Zig9.7k32150259

• arcee-ai/mergekit

  Tools for merging pretrained large language models.

  Language:Python6.3k57364609

• gusye1234/nano-graphrag

  A simple, easy-to-hack GraphRAG implementation

  Language:Python3.3k19109348

• willccbb/verifiers

  Verifiers for LLM Reinforcement Learning

  Language:Python3k29162335

• roboflow/maestro

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

  Language:Python2.6k3442216

• Goldziher/kreuzberg

  Document intelligence framework for Python - Extract text, metadata, and structured data from PDFs, images, Office documents, and more. Built on Pandoc, PDFium, and Tesseract.

  Language:Python2.4k125197

• WLiK/LLM4Rec-Awesome-Papers

  A list of awesome papers and resources of recommender system on large language model (LLM).

  2k249152

• MinishLab/model2vec

  Fast State-of-the-Art Static Embeddings

  Language:Python1.8k124199

• wasiahmad/Awesome-LLM-Synthetic-Data

  A reading list on LLM based Synthetic Data Generation 🔥

  1.4k15185

• beam-cloud/beta9

  Ultrafast serverless GPU inference, sandboxes, and background jobs

  Language:Go1.3k415114

• goodreasonai/ScrapeServ

  A self-hosted API that takes a URL and returns a file with browser screenshots.

  Language:Python1k5673

• PrunaAI/pruna

  Pruna is a model optimization framework built for developers, enabling you to deliver faster, more efficient models with minimal overhead.

  Language:Python84342

• kiwix/kiwix-apple

  Kiwix for iOS & macOS

  Language:Swift6292456187

• pirate/wikipedia-mirror

  🌐 Guide and tools to run a full offline mirror of Wikipedia.org with three different approaches: Nginx caching proxy, Kiwix + ZIM dump, and MediaWiki/XOWA + XML dump

  Language:PLpgSQL4918433

• sparkfish/augraphy

  Augmentation pipeline for rendering synthetic paper printing, faxing, scanning and copy machine processes

  Language:Python458913948

• coree/awesome-rag

  A curated list of retrieval-augmented generation (RAG) in large language models

  3133021

• 567-labs/systematically-improving-rag

  Language:Jupyter Notebook1738077

• oxideai/mlx-rs

  Unofficial Rust bindings to Apple's mlx framework

  Language:Rust1474658

• ivanleomk/kura

  Kura is a simple reproduction of the CLIO paper which uses language models to label user behaviour before clustering them based on embeddings recursively. This helps us understand user behaviour on a higher level without sacrificing PII.

  Language:TypeScript972013

• openzim/python-libzim

  Libzim binding for Python: read/write ZIM files in Python

  Language:Python80811427

• mistralai/mistral-evals

  Language:Python682428

• KGrewal1/candle-optimisers

  A collection of optimisers for use with candle

  Language:Rust34322

• tomsanbear/candle-einops

  Language:Rust28211

• nphdang/FS-BBT

  Black-box Few-shot Knowledge Distillation

  Language:Python13111

• lintool/history-of-open-source-ir-systems

  History of Open-Source IR Systems

  1120