Dean Webb's repositories
Anima
33B Chinese LLM, DPO QLORA, 100K context, AirLLM 70B inference with single 4GB GPU
autodistill-grounded-sam-2
Use Segment Anything 2, grounded with Florence-2, to auto-label data for use in training vision models.
DAPO
An Open-source RL System from ByteDance Seed and Tsinghua AIR
DeepStream-Yolo
NVIDIA DeepStream SDK 6.0.1 configuration for YOLO models
DeepStream-Yolo-Seg
NVIDIA DeepStream SDK 6.3 / 6.2 / 6.1.1 / 6.1 / 6.0.1 / 6.0 implementation for YOLO-Segmentation models
deepstream_tao_apps
Sample apps to demonstrate how to deploy models trained with TAO on DeepStream
Depth-Anything-ONNX
ONNX-compatible Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data
Depth-Anything-V2
Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation
DepthAnything-on-Browser
This repository demonstrates browser based implementation of DepthAnything and DepthAnythingV2 models. It is powered by Onnx and does not require any web servers.
examples
Client code examples & integrations that utilize LM Studio's local inference server
Grounded-SAM-2
Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2
image-quality-issues
FiftyOne Plugin for finding common image quality issues
label-studio-ml-backend
Configs and boilerplates for Label Studio's Machine Learning backend
moderngl
Modern OpenGL binding for Python
mojo
The Mojo Programming Language
OSWorld
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
PaliGemma
This repository contains examples of using PaliGemma for tasks such as object detection, segmentation, image captioning, etc.
Segment-and-Track-Anything
An open-source project dedicated to tracking and segmenting any objects in videos, either automatically or interactively. The primary algorithms utilized include the Segment Anything Model (SAM) for key-frame segmentation and Associating Objects with Transformers (AOT) for efficient tracking and propagation purposes.
TensorRT-LLM
TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.
ToolBench
An open platform for training, serving, and evaluating large language model for tool learning.
ultralytics
YOLOv8 🚀 in PyTorch > ONNX > CoreML > TFLite
UniCL
[CVPR 2022] Official code for "Unified Contrastive Learning in Image-Text-Label Space"
unilm
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
verl
verl: Volcano Engine Reinforcement Learning for LLMs
vipy
Python Tools for Visual Dataset Transformation
YOLO-World
[CVPR 2024] Real-Time Open-Vocabulary Object Detection
yolov12
YOLOv12: Attention-Centric Real-Time Object Detectors
yolov9
Implementation of paper - YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information