TranslatedMedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. Training medical large models, implementing incremental pre-training (PT), supervised fine-tuning (SFT), RLHF, DPO, ORPO, and GRPO.
Repository Index
58,136 visible repositories in the index
505–528 of 1,941 · Most stars
TranslatedThis repository contains three Skills for academic researchers, covering the complete research workflow from literature reading and paper writing to scientific computing. office-academic-skill handles paper reading reports and the generation of academic PPT/Word documents; research-writing-skill provides assistance with paper writing, polishing, and replies to reviewers; scientific-toolkit-skill integrates MATLAB/Python scientific computing with journal-quality chart generation. All three Skills are designed specifically for Chinese-speaking researchers and can be invoked with one click in Claude Code and codex.
A treasure chest for visual classification and recognition powered by PaddlePaddle
- image-classification
- knowledge-distillation
- autoaugment
- randaugment
Claude skills for LinkedIn. 12 Claude Code and Codex skills that write human-sounding LinkedIn posts, craft comments that get noticed, analyze your feed, and build a publishing cadence, all from your terminal. Content engineering by Creative Content Crafts. MIT.
"Can I take over XYZ?" — a list of services and how to claim (sub)domains with dangling DNS records.
MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.
- llava
- llm
- mlx
- vision-transformer
TranslatedExtremely lightweight | Stops defensive writing in papers | Anti-defensive writing for academic papers — 学术写作原则 Skill + prompt pack (CN/EN)
- academic-writing
- ai-writing
- claude-skill
- paper-writing
AI-powered bug bounty hunting toolkit that works with or without subscription.
- ai-security
- bug-bounty
- bugcrowd
- claude-ai
Python library for converting Python calculations into rendered latex.
See what Claude Code and Codex actually send to the API — and what each part costs.
- claude-code
- codex-cli
- cost-tracking
- observability
MMdnn is a set of tools to help users inter-operate among different deep learning frameworks. E.g. model conversion and visualization. Convert models between Caffe, Keras, MXNet, Tensorflow, CNTK, PyTorch Onnx and CoreML.
- cntk
- visualization
- tensorflow
- model-converter
Local-first healthcare AI: clinical NER and HIPAA PII de-identification on hardware you control. 2,200+ medical models, 35 model-backed PII languages, and Python, MLX, Android and browser runtimes. Apache-2.0 SDK.
- healthcare
- llm
- on-device
- on-premise
Domain name permutation engine for detecting homograph phishing attacks, typo squatting, and brand impersonation
- phishing
- typosquatting
- domains
- dns
XLeRobot: Practical Dual-Arm Mobile Home Robot for $660
🍊 :bar_chart: :bulb: Orange: Interactive data analysis
- data-mining
- data-science
- machine-learning
- data-visualization
OpenClaw-RL: Train any agent simply by talking
- async
- memory-systems
- open-claw
- openclaw-skills
Real-time face detection and emotion/gender classification using fer2013/imdb datasets with a keras CNN model and openCV.
TranslatedChinese text classification, TextCNN, TextRNN, FastText, TextRCNN, BiLSTM_Attention, DPCNN, Transformer, based on pytorch, ready to use out of the box.
Automated Penetration Testing Framework - Open-Source Vulnerability Scanner - Vulnerability Management
- python
- penetration-testing
- penetration-testing-framework
- owasp
Model interpretability and understanding for PyTorch
- interpretability
- interpretable-ai
- interpretable-ml
- feature-importance
SUPIR aims at developing Practical Algorithms for Photo-Realistic Image Restoration In the Wild. Our new online demo is also released at suppixel.ai.
- deep-learning
- diffusion-models
- llava
- sdxl
Convolutional Neural Network for Text Classification in Tensorflow
😎 Finding duplicate images made easy!
- image-deduplication
- neural-network
- hashing
- e-commerce
Dockerized OpenAI-compatible wrapper for Kokoro-82M text-to-speech w/multiplatform CPU, AMD, NVIDIA GPU PyTorch; multi-speaker, clone-tuning, caption timestamps, SSML, websockets, optional readalong web UI