Lists (3)
Stars
💡 Control your Logitech Litra light from the command line
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.
A high-throughput and memory-efficient inference and serving engine for LLMs
HDF5 for Python -- The h5py package is a Pythonic interface to the HDF5 binary data format.
Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic workflows.
Convert PDF to markdown + JSON quickly with high accuracy
ExtractThinker is a Document Intelligence library for LLMs, offering ORM-style interaction for flexible and powerful document workflows.
Python tool for converting files and office documents to Markdown.
Plumb a PDF for detailed information about each char, rectangle, line, et cetera — and easily extract text and tables.
The code used to train and run inference with the ColVision models, e.g. ColPali, ColQwen2, and ColSmol.
Python library for Agentic Document Extraction from LandingAI
Get your documents ready for gen AI
A lightweight, powerful framework for multi-agent workflows
High-resolution models for human tasks.
D-FINE: Redefine Regression Task of DETRs as Fine-grained Distribution Refinement [ICLR 2025 Spotlight]
The official Python SDK for Model Context Protocol servers and clients
Application to track proposals and projects from their submission to finalisation
Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding
Robust Speech Recognition via Large-Scale Weak Supervision
A retargetable MLIR-based machine learning compiler and runtime toolkit.
Includes the code for training and testing the CountGD model from the paper CountGD: Multi-Modal Open-World Counting.
[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"
Real-Time and Accurate Full-Body Multi-Person Pose Estimation&Tracking System
Cross-platform, customizable ML solutions for live and streaming media.
[ECCV2024] API code for T-Rex2: Towards Generic Object Detection via Text-Visual Prompt Synergy
Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
Yolov5 model for bottle detection