Stars
On-device AI across mobile, embedded and edge for PyTorch
The state-of-the-art image restoration model without nonlinear activation functions.
Framework agnostic sliced/tiled inference + interactive ui + error analysis plots
Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)
OpenLLaMA, a permissively licensed open source reproduction of Meta AI’s LLaMA 7B trained on the RedPajama dataset
An implementation of WaveNet with fast generation
深度学习入门教程, 优秀文章, Deep Learning Tutorial
Convert JSON annotations into YOLO format.
Image Polygonal Annotation with Python (polygon, rectangle, circle, line, point and image-level flag annotation).
Qwen2.5 is the large language model series developed by Qwen team, Alibaba Cloud.
Effortless AI-assisted data labeling with AI support from YOLO, Segment Anything (SAM+SAM2), MobileSAM!!
PyTorch extension for emulating FP8 data formats on standard FP32 Xeon/GPU hardware.
Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation
PyTorch implementation of MAR+DiffLoss https://arxiv.org/abs/2406.11838
[NeurIPS 2024 Oral][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-sim…
[ECCV 2022] This is the official implementation of BEVFormer, a camera-only framework for autonomous driving perception, e.g., 3D object detection and semantic map segmentation.
Superpoint Implemented in PyTorch: https://arxiv.org/abs/1712.07629
Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2
stable diffusion webui colab
An open source implementation of CLIP.
A gradio web UI demo for Stable Diffusion XL 1.0, with refiner and MultiGPU support
The official PyTorch implementation of Google's Gemma models
AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:
Curated tutorials and resources for Large Language Models, Text2SQL, Text2DSL、Text2API、Text2Vis and more.
⛷️ LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training (EMNLP 2024)
Accessible large language models via k-bit quantization for PyTorch.
Skywork series models are pre-trained on 3.2TB of high-quality multilingual (mainly Chinese and English) and code data. We have open-sourced the model, training data, evaluation data, evaluation me…