🤗 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.
- nlp
- natural-language-processing
- pytorch
- pytorch-transformers
Repository Index
47,133 repositories indexed
1–24 of 28 · Most stars
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
📦 Repomix is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for when you need to feed your codebase to Large Language Models (LLMs) or other AI tools like Claude, ChatGPT, DeepSeek, Perplexity, Gemini, Gemma, Llama, Grok, and more.
Fully open reproduction of DeepSeek-R1
Contexts Optical Compression
Janus-Series: Unified Multimodal Understanding and Generation Models
- any-to-any
- foundation-models
- llm
- multimodal
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.8, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM5.3, Gemma4, Llava, Phi4, ...) (AAAI 2025).
Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node
- speech-recognition
- asr
- voice-recognition
- speech-to-text
Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.
- object-detection
- instance-segmentation
- faster-rcnn
- mask-rcnn
Minimal reproduction of DeepSeek R1-Zero
Project Maya - run GLM-5.3-Flash (321B MoE), DeepSeek-V4.1-Flash-1017 (748B MoE) and MiniMax-M3.1-Flash (428B MoE) privately on your own GPU(s), from one card to 16, NVIDIA or AMD, Linux or Windows. Engine, server, dashboard, OpenAI- and Anthropic-compatible API, quant tools.
Implementation of DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking
- diffusion-models
- docking
- binding
- computational-biology
TranslatedAI image studio for DeepSeek Harness — generate, edit & compare images in chat, with 500+ prompts, gallery, multi-model workflows and ComfyUI.
Machine learning for Ruby
- machine-learning
- rubyml
- automl
The world's cleanest AutoML library ✨ - Do hyperparameter tuning with the right pipeline abstractions to write clean deep learning production pipelines. Let your pipeline steps have hyperparameter spaces. Design steps in your pipeline like components. Compatible with Scikit-Learn, TensorFlow, and most other libraries, frameworks and MLOps environments.
- pipeline
- pipeline-framework
- machine-learning
- deep-learning
TranslatedAI Paper System · AI paper generation, AI paper writing, one-click paper generation, AIGC rate reduction, plagiarism similarity reduction, thesis defense PPT · OEM white-label franchise recruitment
- ai
- ai-humanizer
- ai-ppt
- aigc
Code for the Nature Scientific Reports paper "Pathologist-level classification of histologic patterns on resected lung adenocarcinoma slides with deep neural networks." A sliding window framework for classification of high resolution whole-slide images, often microscopy or histopathology images.
- histopathology-images
- microscopy
- sliding-windows
- medical-image-analysis
Tiny world model generates games and stream ac plays them all on Pico 2W
- rust
- transformers
TranslatedLanpose generates images of the community whale-girl Dafeiyu from pose sketches and costumes, and installs into DeepSeek Harness. (澜姿 (Lanzi, "Lan pose"): from pose line art and costume sets, produce images for the community whale-girl model Dafeiyu, adjust poses and change outfits, and it can also be installed into DeepSeek Harness.)
On-device Vision Model - a fully offline, free vision pipeline that gives text-only models (e.g. DeepSeek) image understanding and multilingual OCR through an OpenAI-compatible local API. Only tokens are needed: no API key, no subscription, no cloud cost. Recommended for native speakers of Chinese, English, Japanese and Korean.
High-performance Piecewise Geometric Model (PGM) learned index implementation in pure Rust with strict epsilon error guarantees
Axon/Myelin segmentation using Deep Learning
- deep-learning
- machine-learning
- myelin
- axon
TranslatedVRS Application Recommendation System (志愿 "zhiyuan", college application choices): FastAPI + Neo4j + DeepSeek, with Zhejiang gaokao (college entrance exam) historical data as an example, including Excel data templates.
Durable execution framework for AI agents in Go. Keeps agent state, tool calls, and execution loops resilient across process crashes.
- agentic-ai
- ai
- ai-agents
- golang