Spark001
Follow
Stars
ไธบGPT/GLM็ญLLMๅคง่ฏญ่จๆจกๅๆไพๅฎ็จๅไบคไบๆฅๅฃ๏ผ็นๅซไผๅ่ฎบๆ้ ่ฏป/ๆถฆ่ฒ/ๅไฝไฝ้ช๏ผๆจกๅๅ่ฎพ่ฎก๏ผๆฏๆ่ชๅฎไนๅฟซๆทๆ้ฎ&ๅฝๆฐๆไปถ๏ผๆฏๆPythonๅC++็ญ้กน็ฎๅๆ&่ช่ฏ่งฃๅ่ฝ๏ผPDF/LaTex่ฎบๆ็ฟป่ฏ&ๆป็ปๅ่ฝ๏ผๆฏๆๅนถ่ก้ฎ่ฏขๅค็งLLMๆจกๅ๏ผๆฏๆchatglm3็ญๆฌๅฐๆจกๅใๆฅๅ ฅ้ไนๅ้ฎ, deepseekcoder, ่ฎฏ้ฃๆ็ซ, ๆๅฟไธ่จ, llama2, rwkv, claude2, mโฆ
High-Resolution Image Synthesis with Latent Diffusion Models
Official Code for DragGAN (SIGGRAPH 2023)
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
OpenMMLab Detection Toolbox and Benchmark
NEW - YOLOv8 ๐ in PyTorch > ONNX > OpenVINO > CoreML > TFLite
๐ค Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.
Generative Models by Stability AI
State-of-the-art 2D and 3D Face Analysis Project
Open-Sora: Democratizing Efficient Video Production for All
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"
Fast and memory-efficient exact attention
The official repo of Qwen (้ไนๅ้ฎ) chat & pretrained large language model proposed by Alibaba Cloud.
A paper list of object detection using deep learning.
Code to accompany "A Method for Animating Children's Drawings of the Human Figure"
Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
A collaboration friendly studio for NeRFs
Pretrained ConvNets for pytorch: NASNet, ResNeXt, ResNet, InceptionV4, InceptionResnetV2, Xception, DPN, etc.
Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML!
Text-to-3D & Image-to-3D & Mesh Exportation with NeRF + Diffusion.
tensorboard for pytorch (and chainer, mxnet, numpy, ...)
ModelScope: bring the notion of Model-as-a-Service to life.
[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation
Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.