Best deep learning skills, page 8

Guide for selecting and configuring distributed training strategies in NeMo AutoModel, including FSDP2, Megatron FSDP, DDP, and parallelism settings.

NVIDIA/skills

Validate and use CUDA graph capture in Megatron Bridge, including local full-iteration graphs and Transformer Engine scoped graphs for attention, MLP, and MoE modules.

NVIDIA/skills

Operational guide for enabling Megatron FSDP in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification.

NVIDIA/skills

Practical guidance for training MoE VLMs in Megatron Bridge.

NVIDIA/skills

Guidance for building and training with the Caffe deep learning framework on CIFAR-10 dataset.

lazyFrogLOL/Harness_Engineering

A skill your agent uses when building or extending a Java service with Quarkus - layered architecture, JAX-RS resources, CDI beans, Panache persistence, and native-friendly patterns

makifbaysal/tasktrooper

PyTorch-native Graph Neural Network framework for molecules and proteins.

aipoch/medical-research-skills

Shallow, text-only triage of a GitHub issue on pytorch or torch-xpu-ops.

intel/torch-xpu-ops

Optimize transformer attention with Flash Attention — 2-4x speedup, 10-20x memory reduction for long sequences on CUDA GPUs.

AlexAI-MCP/hermes-CCC

Run distributed GPU training jobs on CoreWeave with multi-node PyTorch.

jeremylongshore/tons-of-skills-marketplace

Configure distributed training setup operations. An agent skill from jeremylongshore/tons-of-skills-marketplace.

jeremylongshore/tons-of-skills-marketplace

Create tensorflow savedmodel creator operations. An agent skill from jeremylongshore/tons-of-skills-marketplace.

jeremylongshore/tons-of-skills-marketplace

Configure tensorflow serving setup operations. An agent skill from jeremylongshore/tons-of-skills-marketplace.

jeremylongshore/tons-of-skills-marketplace

Annotated deep learning paper implementations with code walkthroughs

wentorai/research-plugins

Run and manage Google Colab notebooks for Python and ML research

wentorai/research-plugins

Conference papers on graph neural networks and graph learning

wentorai/research-plugins

Build and debug deep learning models with Keras and TensorFlow backend

wentorai/research-plugins

Build a ChatGPT-like LLM from scratch using PyTorch step by step

wentorai/research-plugins

Medical image analysis with deep learning for research applications

wentorai/research-plugins

Avoid common PyTorch mistakes and apply robust training patterns

wentorai/research-plugins

PyTorch Lightning framework for scalable model training and research

wentorai/research-plugins

TensorFlow best practices for tf.function, GPU memory, and deployment

wentorai/research-plugins

书/长文/研报/论文的深度消化，产出结构笔记+原子笔记+知识网络连接。关键词：深度阅读、深度学习、结构笔记、deep learning。

LeoYeAI/openclaw-master-skills

GPU optimization for consumer NVIDIA GPUs (8-24GB VRAM) covering mixed precision, gradient checkpointing, XGBoost GPU, CuPy/cuDF migration, and torch.compile.

Mathews-Tom/armory

A skill your agent uses when selecting Sentence Transformers inference backends or exporting/optimizing models for PyTorch, ONNX, or OpenVINO.

VectorSpaceLab/AREX-Skill

Use this DeepCTR repo skill for CTR/recommender feature columns, Keras models, sequence/session models, multitask models, and legacy TensorFlow Estimator workflows.

VectorSpaceLab/AREX-Skill

Use torchsummary.summary and torchsummary.summarystring to inspect PyTorch nn.Module shapes, parameter counts, devices, dtypes, and memory estimates.

VectorSpaceLab/AREX-Skill

Use this sub-skill for MLAlgorithms NeuralNet construction, activations, losses, parameters, constraints, regularizers, optimizers, convolutional/recurrent layers, and DQN wiring.

VectorSpaceLab/AREX-Skill

Use this operating sub-skill to create, adapt, and troubleshoot ManimML neural-network scenes: NeuralNetwork containers, feed-forward and convolutional layers…

VectorSpaceLab/AREX-Skill

A skill your agent uses for PaddleViT's DINO self-supervised vision-transformer pretraining, multi-crop data contracts, teacher/student configuration, single- or multi-GPU launch planning…

VectorSpaceLab/AREX-Skill

Build and review OpenRLHF supervised/preference training plans for SFT, reward models, DPO, IPO, and cDPO.

VectorSpaceLab/AREX-Skill

Use Torch Points3D for point-cloud deep learning APIs, datasets/transforms, Hydra training/evaluation, checkpoints, sparse backend decisions, and registration workflows.

VectorSpaceLab/AREX-Skill

A skill your agent uses for Torch-TensorRT tasks: compiling PyTorch models with TensorRT, dynamic-shape/export workflows, runtime optimization, Triton/C++/distributed deployment, debugging…

VectorSpaceLab/AREX-Skill

Use TorchMetrics to choose, inspect, and combine metric families for PyTorch evaluation, including core API, domain metrics, model-based metrics, and wrappers.

VectorSpaceLab/AREX-Skill

Use Towhee's optional PyTorch Trainer, TrainingConfig YAML, NNOperator training bridge, and towhee.models package boundaries safely.

VectorSpaceLab/AREX-Skill

Compose timm API-level training loops with optimizer and scheduler factories, loss selection, task wrappers, EMA, AMP scaling, metrics, checkpoint state, and safe CPU smoke checks.

VectorSpaceLab/AREX-Skill

Guide safe video-file, webcam, and optional half-precision demo use for pytorch-yolo-v3.

VectorSpaceLab/AREX-Skill

Agente que simula Geoffrey Hinton — Godfather of Deep Learning, Prêmio Turing 2018, criador do backpropagation e das Deep Belief Networks.

majiayu000/claude-skill-registry

A skill your agent uses to classify tabular data end-to-end in MATLAB — load a dataset, prepare and clean it, select promising classifiers, train them, and compare accuracies with cross-validation…

majiayu000/claude-skill-registry

Paddle-based deep learning workflows from the course materials, including DNN/RNN text-style baselines and the CNN/LeNet image classification case using folder-labeled digit images.

Drchronx/ai-agent-research-starter-kit

Ankh 蛋白质语言模型昇腾 NPU 迁移 Skill，适用于 Ankh base/large、Ankh3 large/XL 以及同类基于 HuggingFace Transformers 与 PyTorch 的蛋白模型从 CUDA/GPU 到华为 Ascend NPU 的环境检查、代码适配、权重加载、验证脚本补齐与文档沉淀。

ascend-ai-coding/awesome-ascend-skills

昇腾 TensorFlow Community 迁移适配 Skill，适用于将基于 TensorFlow 2.x 的模型原生部署到华为 Ascend NPU，而不经过 TF 到 PyTorch 转换，覆盖 aarch64 源码编译 TF 2.6.5、tfplugin 安装、自动迁移工具使用、手动适配与精度验证。

ascend-ai-coding/awesome-ascend-skills

DeepFRI 的 TensorFlow 到 PyTorch 转换与昇腾 NPU 迁移 Skill，适用于蛋白质功能预测场景下的 TF 模型分析、PyTorch 重写、权重逐层映射、NPU 推理与精度验证，尤其适合需要在 Ascend 上运行 DeepFRI CNN 或 GCN 路径时使用。

ascend-ai-coding/awesome-ascend-skills

DeepFRI TensorFlow 原生昇腾 NPU 迁移 Skill，适用于不做 TF 到 PyTorch 转换、而是直接使用 TensorFlow 2.6.5 与 npudevice 在华为 Ascend 上运行 DeepFRI 的场景，覆盖源码编译、tfplugin 安装、代码适配、推理与 CPU 对比验证。

ascend-ai-coding/awesome-ascend-skills

DiffSBDD 昇腾 NPU 迁移 Skill，适用于将基于等变扩散模型的结构化药物设计项目从 CUDA 迁移到华为 Ascend NPU，覆盖环境搭建、依赖安装、torchscatter 源码编译、代码适配以及 de novo 推理验证。

ascend-ai-coding/awesome-ascend-skills

OligoFormer 昇腾 NPU 迁移 Skill，适用于将基于 PyTorch Transformer 的 siRNA 效能预测模型迁移到华为 Ascend NPU，覆盖环境搭建、RNA-FM 依赖安装、代码适配、推理验证与可选训练流程。

ascend-ai-coding/awesome-ascend-skills

ProteinBERT 昇腾 NPU 部署与迁移 Skill，适用于将 TensorFlow 或 Keras 版 ProteinBERT 转成基于 PyTorch 与 torchnpu 的实现，覆盖权重转换、embedding 提取、微调训练、注意力可视化和 GPU 与 NPU 精度验证。

ascend-ai-coding/awesome-ascend-skills

TensorFlow 或 Keras 模型改写到 PyTorch 的通用 Skill，适用于在华为 Ascend NPU 或其他依赖 PyTorch 生态的平台上完成层级映射、权重转换、逐层数值验证和端到端精度对比，尤其适合 ProteinBERT、DeepFRI 这类科学模型的跨框架迁移。

ascend-ai-coding/awesome-ascend-skills