An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.
- chatgpt
- deep-learning
- instruction-following
- language-model
107,098 visible repositories in the index
73–96 of 678 · Most stars
An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.
DoWhy is a Python library for causal inference that supports explicit modeling and testing of causal assumptions. DoWhy is based on a unified language for causal inference, combining causal graphical models and potential outcomes frameworks.
LMDeploy is a toolkit for compressing, deploying, and serving LLMs.
TranslatedA collection of the Android SDK needed for Android development, tools used in development, Android development tutorials, Android design guidelines, free design resources, and more.
PaddlePaddle GAN library, including lots of interesting applications like First-Order motion transfer, Wav2Lip, picture repair, image editing, photo2cartoon, image style transfer, GPEN, and so on.
TranslatedOpen-source manuscript of 《深入理解 AI Infra:量化分析与系统设计》 (In-Depth Understanding of AI Infra: Quantitative Analysis and System Design), by 李博杰 (Li Bojie): starting from hardware constraints and model architecture, it quantitatively derives the system design of LLM inference and training. Includes the full text of the book, a PDF, and companion calculation tools and experiments
Infrastructure for continually self‑improving agents
A framework for efficient model inference with omni-modality models
Open-source implementation of AlphaEvolve
TranslatedAI video note generation tool: let AI take notes for your videos
Skills for threat modeling, scanning, triage, patching, plus an autonomous scanning harness you can /customize
Chromium fork named after radioactive element No. 90. Source code and Linux releases. Windows/MacOS/ARM builds served in different repos, links are towards the top of the README.md.
Efficiently computes derivatives of NumPy code.
Translated💎1MB lightweight face detection model
Home of StarCoder: fine-tuning & inference!
A Python framework for GPU-accelerated simulation, robotics, and machine learning.
Native MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API.
[EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.
Modeling, training, eval, and inference code for OLMo
Genetic Algorithm, Particle Swarm Optimization, Simulated Annealing, Ant Colony Optimization Algorithm,Immune Algorithm, Artificial Fish Swarm Algorithm, Differential Evolution and TSP(Traveling salesman)
TranslatedAI Agent-driven open-source, self-deployable video workspace: turns novels and scripts into character, scene, and prop assets, storyboards, videos, and 剪映 (Jianying) drafts, with support for cross-shot consistency, multiple providers, and cost tracking | Self-hosted AI video workspace for stories, storyboards and short-form video production
Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"
Differentiable ODE solvers with full GPU support and O(1)-memory backpropagation.
An anomaly detection library comprising state-of-the-art algorithms and features such as experiment management, hyper-parameter optimization, and edge inference.