1lyogavin / airllm
AirLLM 2.8T LLM inference with single 4GB GPU
+837 stars
from 40,670 · score 6.73
Trending repositories
Ranked by Attention Score: stars gained over the last 7 complete days
46 repositories by Attention Score · Oct 27, 2026 – Nov 2, 2026 (UTC)
2FinanceFlash / unvibecode
Complex code hides connections, workflows, and business risks.Unvibe complex code. Trace business workflows.
+759 stars
from 175 · score 6.63
3datawhalechina / self-llm
《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程
+91 stars
from 32,577 · score 4.52
4HandsOnLLM / Hands-On-Large-Language-Models
Official code repo for the O'Reilly Book - "Hands-On Large Language Models"
+74 stars
from 29,912 · score 4.32
5google-research / google-research
Google Research
+63 stars
from 39,025 · score 4.16
6Infrasys-AI / AISystem
AISystem 主要是指AI系统，包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术
+62 stars
from 18,035 · score 4.14
7jpmorganchase / python-training
Python training for business analysts and traders
+54 stars
from 14,268 · score 4.01
8QwenLM / Qwen3-VL
Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
+38 stars
from 20,118 · score 3.66
9ageron / handson-ml3
A series of Jupyter notebooks that walk you through the fundamentals of Machine Learning and Deep Learning in Python using Scikit-Learn, Keras and TensorFlow 2.
+34 stars
from 14,386 · score 3.56
10langgptai / LangGPT
LangGPT: Empowering everyone to become a prompt expert! 🚀 📌 结构化提示词（Structured Prompt）提出者 📌 元提示词（Meta-Prompt）发起者 📌 最流行的提示词落地范式 | Language of GPT The pioneering framework for structured & meta-prompt design 10,000+ ⭐ | Battle-tested by thousands of users worldwide Created by 云中江树
+34 stars
from 12,631 · score 3.56
11facebookresearch / sam2
The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
+28 stars
from 20,057 · score 3.37
12google-gemini / cookbook
Examples and guides for using the Gemini API
+26 stars
from 17,867 · score 3.30
13GoogleCloudPlatform / generative-ai
Sample code and notebooks for Generative AI on Google Cloud, with Gemini Enterprise Agent Platform
+23 stars
from 17,813 · score 3.18
14alphacep / vosk-api
Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node
+23 stars
from 15,201 · score 3.18
15facebookresearch / dinov2
PyTorch code and models for the DINOv2 self-supervised learning method.
+22 stars
from 13,470 · score 3.14
16facebookresearch / segment-anything
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
+21 stars
from 55,062 · score 3.09
17fastai / fastai
The fastai deep learning library
+21 stars
from 28,235 · score 3.09
18evidentlyai / evidently
Evidently is an open-source ML and LLM observability framework. Evaluate, test, and monitor any AI-powered system or data pipeline. From tabular data to Gen AI. 100+ metrics.
+19 stars
from 8,010 · score 3.00
19google-deepmind / deepmind-research
This repository contains implementations and illustrative code to accompany DeepMind publications
+16 stars
from 15,248 · score 2.83
20quantopian / alphalens
Performance analysis of predictive (alpha) stock factors
+16 stars
from 4,479 · score 2.83
21IDEA-Research / Grounded-Segment-Anything
Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything
+10 stars
from 17,782 · score 2.40
22google-gemini / gemini-fullstack-langgraph-quickstart
Get started with building Fullstack Agents using Gemini 2.5 and LangGraph
+8 stars
from 18,352 · score 2.20
23Vaibhavs10 / insanely-fast-whisper
No description provided by the repository host.
+7 stars
from 13,053 · score 2.08
24advimman / lama
🦙 LaMa Image Inpainting, Resolution-robust Large Mask Inpainting with Fourier Convolutions, WACV 2022
+7 stars
from 10,346 · score 2.08
25google / flax
Flax is a neural network library for JAX that is designed for flexibility.
+7 stars
from 7,356 · score 2.08
26kubernetes / community
Kubernetes Community Documentation
+5 stars
from 13,045 · score 1.79
27mistralai / mistral-inferenceArchived
Official inference library for Mistral models
+5 stars
from 10,821 · score 1.79
28h2oai / h2o-3
H2O is an Open Source, Distributed, Fast & Scalable Machine Learning Platform: Deep Learning, Gradient Boosting (GBM) & XGBoost, Random Forest, Generalized Linear Modeling (GLM with Elastic Net), K-Means, PCA, Generalized Additive Models (GAM), RuleFit, Support Vector Machine (SVM), Stacked Ensembles, Automatic Machine Learning (AutoML), etc.
+5 stars
from 7,515 · score 1.79
29apache / hamilton
Apache Hamilton helps data scientists and engineers define testable, modular, self-documenting dataflows, that encode lineage/tracing and metadata. Runs and scales everywhere python does.
+5 stars
from 2,617 · score 1.79
30ShusenTang / Dive-into-DL-PyTorch
本项目将《动手学深度学习》(Dive into Deep Learning)原书中的MXNet实现改为PyTorch实现。
+3 stars
from 19,518 · score 1.39
31aws / amazon-sagemaker-examples
Example 📓 Jupyter notebooks that demonstrate how to build, train, and deploy machine learning models using 🧠 Amazon SageMaker.
+3 stars
from 10,998 · score 1.39
32stanfordmlgroup / ngboost
Natural Gradient Boosting for Probabilistic Prediction
+3 stars
from 1,897 · score 1.39
33Mikoto10032 / DeepLearning
深度学习入门教程, 优秀文章, Deep Learning Tutorial
+2 stars
from 17,868 · score 1.10
34neonbjb / tortoise-tts
A multi-voice TTS system trained with an emphasis on quality
+2 stars
from 14,890 · score 1.10
35google-research / vision_transformer
No description provided by the repository host.
+2 stars
from 12,762 · score 1.10
36huseinzol05 / Stock-Prediction-ModelsArchived
Gathers machine learning and deep learning models for Stock forecasting including trading bots and simulations
+2 stars
from 9,510 · score 1.10
37mlc-ai / web-stable-diffusion
Bringing stable diffusion models to web browsers. Everything runs inside the browser with no server support.
+2 stars
from 3,730 · score 1.10
38Qiskit / qiskit-tutorialsArchived
A collection of Jupyter notebooks showing how to use the Qiskit SDK
+2 stars
from 2,542 · score 1.10
39google / dopamine
Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.
+1 stars
from 10,929 · score 0.69
40quantopian / pyfolio
Portfolio and risk analytics in Python
+1 stars
from 6,437 · score 0.69
41tensorflow / lucidArchived
A collection of infrastructure and tools for research in neural network interpretability.
+1 stars
from 4,704 · score 0.69
42unslothai / hyperlearn
2-2000x faster ML algos, 50% less memory usage, works on all hardware - new and old.
+1 stars
from 2,528 · score 0.69
43gnn4dr / DRKG
A knowledge graph and a set of tools for drug repurposing
+1 stars
from 703 · score 0.69
+1 stars
from 419 · score 0.69
45fastlib / fCWT
The fast Continuous Wavelet Transform (fCWT) is a library for fast calculation of CWT.
+1 stars
from 403 · score 0.69
46osPlanning / omx
Open Matrix (OMX)
+1 stars
from 55 · score 0.69