The calflops is designed to calculate FLOPs、MACs and Parameters in all various neural networks, such as Linear、 CNN、 RNN、 GCN、Transformer(Bert、LlaMA etc Large Language Model)
- flops-counter
- large-language-models
- pytorch
- calflops
107,098 visible repositories in the index
553–576 of 645 · Most stars
The calflops is designed to calculate FLOPs、MACs and Parameters in all various neural networks, such as Linear、 CNN、 RNN、 GCN、Transformer(Bert、LlaMA etc Large Language Model)
Transform unstructured documents into validated, rich and queryable knowledge graphs.
Official Repository for "DrEureka: Language Model Guided Sim-To-Real Transfer" (RSS 2024)
Repository of Vision Transformer with Deformable Attention (CVPR2022) and DAT++: Spatially Dynamic Vision Transformerwith Deformable Attention
Code for "Heterogeneous Graph Transformer" (WWW'20), which is based on pytorch_geometric
SOTA Semantic Segmentation Models in PyTorch
轻量级 LLM Post-training 框架,支持 SFT、RLVR、On-Policy KD、Guide KD 及混合训练;实现单轮/多轮 Guide 蒸馏、多教师蒸馏、Reward 混合训练与自动化数据分流👩🎓👨🎓
Autonomous CTF solver that races multiple AI models in parallel. 1st place BSidesSF 2026.
CTR prediction models based on deep learning(基于深度学习的广告推荐CTR预估模型)
A parallel implementation of "graph2vec: Learning Distributed Representations of Graphs" (MLGWorkshop 2017).
Manage the release notes for your project.
[ICLR 2026] On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification.
Custom component for HA that enables the creation of scheduler entities
Deep research agent to help you find the best GitHub repositories 🕵️!
Deepdrive is a simulator that allows anyone with a PC to push the state-of-the-art in self-driving
Open data and scalable training for long-horizon video world models.
Vchitect-2.0: Parallel Transformer for Scaling Up Video Diffusion Models
MindSpore + 🤗Huggingface: Run any Transformers/Diffusers model on MindSpore with seamless compatibility and acceleration.
This repo contains a PyTorch implementation of a pretrained BERT model for multi-label text classification.
A minimalist SOTA LaTeX OCR model with only 20M parameters, running in browser. Full training pipeline available for self-reproduction. | 超轻量SOTA LaTeX公式识别模型,仅20M参数量,可在浏览器中运行。训练全流程代码开源,以便自学复现。
Four landmark detection algorithms, implemented in PyTorch.
Implementation of Muse: Text-to-Image Generation via Masked Generative Transformers, in Pytorch
Implementation of "FLUX-Text: A Simple and Advanced Diffusion Transformer Baseline for Scene Text Editing"
Software that can perform photorealistic style transfer without the need of any post-processing steps.