rehmi

rehmi's Stars

• Codium-ai/AlphaCodium

  Official implementation for the paper: "Code Generation with AlphaCodium: From Prompt Engineering to Flow Engineering""

  Language:Python3.7k277

• JuliaPluto/computational-thinking-template

  Template to build a course webpage like the *Introduction to computational thinking with Julia* course tought at MIT

  Language:Julia344

• hhk7734/python3-gpiod

  gpiod Python library with almost the same usage as libgpiodcxx

  Language:Python5918

• coqui-ai/TTS

  🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

  Language:Python36.6k4.5k

• ml-explore/mlx-examples

  Examples in the MLX framework

  Language:Python6.5k922

• me-no-dev/ESPAsyncWebServer

  Async Web Server for ESP8266 and ESP32

  Language:C++3.9k1.2k

• thelastoutpostworkshop/gpio_viewer

  GPIOViewer Arduino Library to see live GPIO Pins on ESP32 boards

  Language:C++1.1k110

• amscotti/local-LLM-with-RAG

  Running local Language Language Models (LLM) to perform Retrieval-Augmented Generation (RAG)

  Language:Python19035

• comfyanonymous/ComfyUI

  The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

  Language:Python62.4k6.7k

• justinchiu/openlogprobs

  Extract full next-token probabilities via language model APIs

  Language:Python23013

• tlienart/Xranklin.jl

  Experimental repo for a refactoring of Franklin.jl

  Language:Julia421

• mit-han-lab/llm-awq

  [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

  Language:Python2.6k218

• GenericMappingTools/GMTjl_doc

  GMT.jl documentation site

  Language:HTML51

• state-spaces/mamba

  Mamba SSM architecture

  Language:Python13.7k1.2k

• gitbls/sdm

  Raspberry Pi SD Card Image Manager

  Language:Shell50155

• BlinkDL/RWKV-LM

  RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.

  Language:Python13k880

• karpathy/nanoGPT

  The simplest, fastest repository for training/finetuning medium-sized GPTs.

  Language:Python38.3k6.2k

• BlinkDL/nanoRWKV

  RWKV in nanoGPT style

  Language:Python18311

• jart/cosmopolitan

  build-once run-anywhere c library

  Language:C18.6k648

• superduper-io/superduper

  Superduper: Build end-to-end AI applications and agent workflows on your existing data infrastructure and preferred tools - without migrating your data.

  Language:Python4.9k471

• nomic-ai/gpt4all

  GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.

  Language:C++71.5k7.8k

• mistralai/mistral-inference

  Official inference library for Mistral models

  Language:Jupyter Notebook9.8k874

• ise-uiuc/magicoder

  [ICML'24] Magicoder: Empowering Code Generation with OSS-Instruct

  Language:Python2k163

• open-webui/open-webui

  User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

  Language:JavaScript54.6k6.7k

• lobehub/lobe-chat

  🤯 Lobe Chat - an open-source, modern-design AI chat framework. Supports Multi AI Providers( OpenAI / Claude 3 / Gemini / Ollama / Qwen / DeepSeek), Knowledge Base (file upload / knowledge management / RAG ), Multi-Modals (Vision/TTS/Plugins/Artifacts). One-click FREE deployment of your private ChatGPT/ Claude application.

  Language:TypeScript51k11k

• huggingface/chat-ui

  Open source codebase powering the HuggingChat app

  Language:TypeScript7.8k1.2k

• intel/intel-extension-for-transformers

  ⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Platforms⚡

  Language:Python2.1k210

• Qualcomm-AI-research/geometric-algebra-transformer

  Language:Python16126

• Mozilla-Ocho/llamafile

  Distribute and run LLMs with a single file.

  Language:C++21.1k1.1k

• nihalsid/mesh-gpt

  MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers

  63313