isuckatcs / advent-of-code
Advent of Code solutions in C++, Rust, Java, Kotlin, Swift and Mojo 🔥
☆14Updated 3 weeks ago
Related projects: ⓘ
- Tasks as HTTP endpoints☆27Updated 2 months ago
- TCP Service framework for the mojo programming language 🔥☆21Updated last month
- 360M model running in the browser on WebGPU☆18Updated last month
- iterate quickly with llama.cpp hot reloading. use the llama.cpp bindings with bun.sh☆45Updated 10 months ago
- Answer questions against collections stored in LLM using Retrieval Augmented Generation☆22Updated 7 months ago
- An open-source web scraping tool that converts websites into markdown format. Featuring customizable options, LLM-based filtering, and an…☆22Updated last month
- A fast and compact Dict implementation in Mojo 🔥☆32Updated 2 months ago
- A framework for collecting a large human-sourced chain-of-thoughts dataset☆12Updated 2 months ago
- Jim is a simple, beautiful Jupyter notebook editor for macOS☆28Updated last year
- 🛠 Self-hosted, fast, and consistent remote configuration for apps.☆12Updated last year
- SQL function for SQLite to directly query OpenAI's ChatGPT☆29Updated last year
- A Learning Journey: Micrograd in Mojo 🔥☆57Updated 3 months ago
- Streaming markdown à la ChatGPT (WIP)☆27Updated last month
- 🌿 The search engine in your codebase☆20Updated 2 years ago
- Access llamafile localhost models via LLM☆14Updated 4 months ago
- Rust Implementation of micrograd☆51Updated 2 months ago
- Plugin for LLM adding support for Google's PaLM 2 model☆14Updated 11 months ago
- ☆18Updated last month
- LLama implementations benchmarking framework☆10Updated 10 months ago
- Proof of concept for a generative AI application framework powered by WebAssembly and Extism☆14Updated last year
- Run Llama 2 using MLX on macOS☆33Updated 9 months ago
- GGML implementation of BERT model with Python bindings and quantization.☆25Updated 7 months ago
- Maintain a FAISS index for specified Datasette tables☆34Updated 3 months ago
- Access different AI models in a one place☆22Updated last year
- Repair incomplete JSON (e.g. from streaming APIs or AI models) so it can be parsed as it's received.☆28Updated 8 months ago
- Exploration of Vector database Index for fast approximate nearest neighbour search.☆11Updated last month
- Run multiple open source large language models concurrently powered by Ollama☆20Updated 5 months ago
- Powered by SideGuide and GPT-3☆12Updated last year
- a tool to generate and apply binary deltas between Docker images to optimize registry storage☆16Updated last year
- Run embedding models using ONNX☆23Updated 7 months ago