基于 Tensorflow，仿 Scikit-Learn 设计的深度学习自然语言处理框架。支持 40 余种模型类，涵盖语言模型、文本分类、NER、MRC、知识蒸馏等各个领域
nlp deep-learning tensorflow mrc language-modeling transformer classification bert distillation gpu-training
- Updated
- Python
#
gpu-training
Here are 20 public repositories matching this topic...
Fine-Tuning Google's Vision Transformer LoRA technique. Two different LoRA adapters are tuned for separate classification (food and human actions). A simple Gradio interface is implemented to run the inference.
- Updated
- Jupyter Notebook
Final project for the UPC Postgrau in Artificial Intelligence & Deep Learning, showcasing a SELF-DRIVING demo built around lane detection and object detection models. Integrates LaneNet (with ENet backbone and BDD100K transforms), a custom Mask R-CNN segmentation pipeline, and Faster R-CNN with ResNet50-FPN.
deep-learning faster-rcnn object-detection transfer-learning autonomous-driving lane-detection semantic-segmentation evaluation-metrics mask-rcnn lanenet bdd100k gpu-training self-driving-simulation
- Updated
- Python
This repository features an image sharpening pipeline using Knowledge Distillation. A high-capacity Restormer acts as the teacher model, while a lightweight Mini-UNet is trained as the student to mimic its performance.
computer-vision deep-learning image-processing python3 ssim knowledge-distillation image-restoration model-compression motion-deblurring unet-pytorch vgg-loss training-pipeline div2k image-sharpening perceptual-loss gpu-training restormer real-time-inference
- Updated
- Jupyter Notebook
AI-Farm is a distributed deep learning training framework that enables efficient model training across multiple machines. It provides a scalable infrastructure with real-time monitoring through a web admin panel, adaptive task distribution, and support for both CPU and GPU training.
python machine-learning deep-learning websockets pytorch distributed-training federated-learning gpu-training
- Updated
- Python
A full-stack platform for designing reinforcement learning environments, running GPU-backed training, and monitoring agents in real-time.
- Updated
- TypeScript
Production-ready PyTorch framework for distributed deep learning training with Ray & Horovod backends. Optimized for computer vision and time series on Kubernetes clusters.
kubernetes machine-learning computer-vision deep-learning time-series distributed-computing inference pytorch high-performance-computing temporal-networks ray distributed-training horovod defect-detection mixed-precision mlops production-ml vision-transformer gpu-training scalable-ml
- Updated
- Python
This repo documents my participation in the Kaggle red-teaming competition focused on probing OpenAI's newly released gpt-oss-20b model for previously undiscovered vulnerabilities and harmful behaviors. The goal is to identify, document, and report up to five distinct issues, contributing to the safety and alignment of open-source AI models.
- Updated
- Jupyter Notebook
MetaClaw fork: self-hosted GPU training (GRPO + LoRA + vLLM), per-agent skill isolation, multi-agent mode routing, training engine bug fixes. Train your AI agent on your own A100s. No cloud dependency.
reinforcement-learning multi-agent lora meta-learning peft fastapi gpu-training ai-agent llm vllm qwen grpo agent-isolation openclaw metaclaw skill-evolution per-agent-skills self-hosted-training
- Updated
- Python
PyTorch implementation of DDPM (Denoising Diffusion Probabilistic Models) for image generation. Includes U-Net with attention, DDIM sampling, EMA training, and CelebA dataset support.
deep-learning pytorch image-generation attention-mechanism celeba generative-models diffusion-model denoising-diffusion gpu-training ddpm ddim
- Updated
- Python
Autonomous AI research agents for single-GPU nanochat training — automated experiment design, execution, and analysis
- Updated
- Python
Data processing, Machine Learning codes and Training scripts on Jean Zay High Performance Computing (HPC) remote GPUs
- Updated
- Python
Developed an end-to-end LLM pipeline that extracts Python code from GitHub, builds a high-quality dataset, fine-tunes CodeGen, and performs advanced code generation with DeepSeek. Demonstrates strong capabilities in LLM training, data engineering, and model optimization.
python api machine-learning pytorch pygithub dataset-creation githubapi fine-tuning model-optimization huggingface-transformers gpu-training pythonautomation llm deepseek
- Updated
- Python
Medical X-ray image classifier fine-tuning ResNet-18 with PyTorch.
python computer-vision deep-learning pytorch medical-imaging image-classification resnet transfer-learning healthcare-ai gpu-training mlops-ready
- Updated
- Python
Fine-Tuning Google's Vision Transformer LoRA technique. Two different LoRA adapters are tuned for Separate Classification (Food and Human actions). A simple Gradio interface is implemented to run the Inference.
- Updated
- Jupyter Notebook
1D CNN for customer complaint text classification using PyTorch.
nlp machine-learning deep-learning sentiment-analysis text-classification cnn pytorch sequence-modeling 1d-cnn gpu-training python-classification
- Updated
- Python
Kaggle Competition for MAP Charting Student Math Mistunderstanding
python machine-learning ai transformers pytorch kaggle classification jupyter-notebooks gpu-training llm-training lora-fine-tuning
- Updated
- Jupyter Notebook
Public OpenClaw and Codex skills for reproducible CV experimentation and SOTA campaign management across Colab, Kaggle, browser automation, and GPU VMs.
benchmarking data-science computer-vision kaggle reproducibility browser-automation google-colab mlops gpu-training llm-agents agentic-workflows openclaw clawhub
- Updated
- Python
Whatsapp Assistant using FastAPI, Google Gemini, WhisperAI, Twilio and Ngrok
- Updated
- Python
EGM is a deep learning tool that learns your image editing style from raw/edited pairs and applies it to new images. It uses a Pix2Pix (conditional GAN) architecture.
machine-learning computer-vision deep-learning pytorch image-editing gan style-transfer neural-networks image-generation photo-editing pix2pix image-to-image conditional-gan ml-model gpu-training model-inference dataset-processing
- Updated
- Python
Improve this page
Add a description, image, and links to the gpu-training topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the gpu-training topic, visit your repo's landing page and select "manage topics."