-
ami-iit
- Italy
Highlights
- Pro
Stars
Optimized local inference for LLMs with HuggingFace-like APIs for quantization, vision/language models, multimodal agents, speech, vector DB, and RAG.
Weave is a toolkit for developing AI-powered applications, built by Weights & Biases.
Langtrace π is an open-source, Open Telemetry based end-to-end observability tool for LLM applications, providing real-time tracing, evaluations and metrics for popular LLMs, LLM frameworks, vectorβ¦
Build resilient language agents as graphs.
π¦π Build context-aware reasoning applications
π Text-Prompted Generative Audio Model
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
Robust Speech Recognition via Large-Scale Weak Supervision
Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
User-friendly WebUI for LLMs (Formerly Ollama WebUI)
Visualize streams of multimodal data. Fast, easy to use, and simple to integrate. Built in Rust using egui.
π€ LeRobot: Making AI for Robotics more accessible with end-to-end learning
Multibody Dynamics Library designed for Free Floating Robots
yaml-schema-cpp is a C++ library for specification and validation of YAML files. It is a useful tool for C++ applications that use YAML files as user interface.
Massively parallel rigidbody physics simulation on accelerator hardware.
Dear PyGui: A fast and powerful Graphical User Interface Toolkit for Python with minimal dependencies
PyTorch code and models for V-JEPA self-supervised learning from video.
Lightning-fast and Powerful Code Editor written in Rust
An open, modular framework for zero-shot, language conditioned pick-and-drop tasks in arbitrary homes.
[ICLR 2023] DiffMimic: Efficient Motion Mimicking with Differentiable Physics https://arxiv.org/abs/2304.03274
Modular reinforcement learning library (on PyTorch and JAX) with support for NVIDIA Isaac Gym, Omniverse Isaac Gym and Isaac Lab
Multi-Joint dynamics with Contact. A general purpose physics simulator.
An example RLDS dataset builder for X-embodiment dataset conversion.
Octo is a transformer-based robot policy trained on a diverse mix of 800k robot trajectories.
CMake/YCM-based superbuild to simplify the build process of robotology projects.
Set of utilities for exporting/controlling your robot in Blender
Suite of libraries for achieving bipedal locomotion on humanoid robots