🧊 Open source LLM observability platform. One line of code to monitor, evaluate, and experiment. YC W23 🍓

[EMNLP 2024 Industry Track] This is the official PyTorch implementation of "LLMC: Benchmarking Large Language Model Quantization with a Versatile Compression Toolkit".

[NeurIPS 2024] A task generation and model evaluation system for multimodal language models.

Preferred Generation Benchmark

Here we will keep track of the latest AI Game Development Tools, including LLM, Agent, Code, Writer, Image, Texture, Shader, 3D Model, Animation, Video, Audio, Music, Singing Voice and Analytics. 🔥

🤗 smolagents: a barebones library for agents. Agents write python code to call tools and orchestrate other agents.

A Python toolbox for conformal prediction research on deep learning models, using PyTorch.

Dockershrink is an Open Source, AI-powered tool to reduce the size of your Docker Images

A custom ComfyUI node designed to create seamless motion effects from single images by integrating with Hunyuan Video through latent space manipulation.

This repository introduces PIXIU, an open-source resource featuring the first financial large language models (LLMs), instruction tuning data, and evaluation benchmarks to holistically assess finan…

Agent Framework / shim to use Pydantic with LLMs

DINO-X: The World's Top-Performing Vision Model for Open-World Object Detection and Understanding

A framework to convert any 2D videos to immersive stereoscopic 3D

Aria-UI: Visual Grounding for GUI Instructions

A powerful coding assistant application that integrates with the DeepSeek API to process user conversations and generate structured JSON responses. Through an intuitive command-line interface, it c…

The official implementation of paper "ColorFlow: Retrieval-Augmented Image Sequence Colorization"

Aivis Voice Model File (.aivm/.aivmx) Generator / Editor

FastVideo is an open-source framework for accelerating large video diffusion model.

A curated list of awesome embedding models tutorials, projects and communities.

🌸 fastText + Bloom embeddings for compact, full-coverage vectors with spaCy

A minimal and universal controller for FLUX.1.

Large-Scale Multimodal Dataset of Astronomical Data

Optimizing inference proxy for LLMs

An Efficient LLM Fine-Tuning Factory Optimized for MoE PEFT

State-of-the-art Parameter-Efficient MoE Fine-tuning Method

An LLM token streaming server for a grammar assistant app

Automating the Search for Artificial Life with Foundation Models!

A Python library for converting Streamlit applications into standalone desktop applications using pywebview.