Pretrained models

Chronos is a family of pretrained transformer models for time series forecasting, including univariate, multivariate, and covariate-informed tasks....

The official Python client library for interacting with Hugging Face Hub, enabling users to download/upload models, datasets, and inference APIs. It...

PaddleClas is a comprehensive toolkit for image classification and recognition built on PaddlePaddle, offering pre-trained models, specialized...

LightlyTrain is a specialized framework for computer vision model development, covering pretraining (DINOv2/v3), fine-tuning (YOLO, ViTs, RT-DETR),...

wtpsplit is a Python toolkit for segmenting text into sentences or semantic units across 85 languages, with state-of-the-art models (SaT and WtP)...

Hugging Face Transformers is the de facto standard Python library for accessing, fine-tuning, and deploying state-of-the-art pretrained models across...

OpenCLIP is an open-source implementation of CLIP (Contrastive Language-Image Pre-training) that enables training and inference with vision-language...

Superduper is an end-to-end framework for building AI applications and agents integrated directly with databases (MongoDB, SQL, Snowflake, Redis). It...

PyTorch Image Models (timm) is a comprehensive library providing thousands of pretrained image encoders and backbones including ResNet, Vision...

Spleeter is Deezer's Python library for music source separation using pretrained TensorFlow models, enabling extraction of vocals, drums, bass,...

PINTO_model_zoo is a specialized model repository providing pre-converted deep learning models across 8+ frameworks (TensorFlow, PyTorch, ONNX,...

This is a curated index and reference collection of pretrained Chinese NLP models, including foundation models, chat models, multimodal models, and...

MMF is a modular PyTorch-based framework for vision and language multimodal research, specifically designed for researchers building models that...

Qwen is Alibaba Cloud's family of large language models optimized for both chat and general pretraining tasks, available in multiple sizes (1.8B–72B...

InternLM is an official open-source series of large language models (InternLM, InternLM2, InternLM2.5, InternLM3) developed by Alibaba's Intern-AI...

LMFlow is an extensible toolkit for finetuning and inference of large language models, designed to make advanced model customization accessible to...

PaddleNLP is a comprehensive LLM and SLM development toolkit built on PaddlePaddle that enables efficient training, compression, and inference of...