#
Starred repositories
A chess arena for large language models
The 500 AI Agents Projects is a curated collection of AI agent use cases across various industries. It showcases practical applications and provides links to open-source projects for implementation…
Official Implementation of paper "MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion"
Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.
Uses tokenized query returned by python-sqlparse and generates query metadata
Task-based Agentic Framework using StrictJSON as the core
MLLM-Bench: Evaluating Multimodal LLMs with Per-sample Criteria
State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!
Synthesizing Graphics Programs for Scientific Figures and Sketches with TikZ
Use LLM + Advanced RAG to get desired #ROTD (recipe of the day)
FastCRUD is a Python package for FastAPI, offering robust async CRUD operations and flexible endpoint creation utilities.
[ICML 2024] Official repository for "Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models"
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
A C++14-compatible physical units library with no dependencies and a single-file delivery option. Emphasis on safety, accessibility, performance, and developer experience.
pix2tex: Using a ViT to convert images of equations into LaTeX code.
LMDeploy is a toolkit for compressing, deploying, and serving LLMs.
Unsupervised text tokenizer for Neural Network-based text generation.
[ECCV2024] API code for T-Rex2: Towards Generic Object Detection via Text-Visual Prompt Synergy
Python client for Microsoft Exchange Web Services (EWS)
A Python package to stabilize videos using OpenCV
The fundamental package for scientific computing with Python.
[CVPR 2023] DynaCam dataset - 3D human trajectories in global coordinates from videos captured by dynamic cameras
An Open-Ended Embodied Agent with Large Language Models
An extremely fast Python linter and code formatter, written in Rust.
Trio – a friendly Python library for async concurrency and I/O