Best Open Source pretrained models Libraries
A curated list of the most popular GitHub repositories tagged with pretrained models. Select any project to visualize its architecture and dive into the codebase using RepoMind's AI engine.
#1huggingface/transformers
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
#2huggingface/pytorch-image-models
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more
#3deezer/spleeter
Deezer source separation library including pretrained models.
#4QwenLM/Qwen
The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.
#5mlfoundations/open_clip
An open source implementation of CLIP.
#6PaddlePaddle/PaddleNLP
Easy-to-use and powerful LLM and SLM library with awesome model zoo.
#7bigscience-workshop/petals
🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
#8pyannote/pyannote-audio
Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding
#9zai-org/CodeGeeX
CodeGeeX: An Open Multilingual Code Generation Model (KDD 2023)
#10zai-org/CogVLM
a state-of-the-art-level open visual language model | 多模态预训练模型