Model Training skills

M

Megatron Bridge Recipe Recommender

nvidia

Streamline your model training with tailored recipe suggestions.

P

Parallelism Strategy Selection

nvidia

Optimize parallelism for Megatron Bridge models effectively.

Activation Recompute

nvidia

Optimize GPU memory usage with activation recompute.

M

MoE Optimization Workflow

nvidia

Streamline MoE model training with systematic guidance.

GRPO & RLVR Training

wshobson

Enhance model reasoning with verifiable rewards.

T

Trace To Training Data

wshobson

Transform evaluation traces into training data efficiently.

Hugging Face LLM Trainer

huggingface

Train and fine-tune models on Hugging Face Jobs effortlessly.

Uni-Mol Tools

hkuds

Interactive CLI for molecular property prediction workflows.

Simple Preference Optimization

nousresearch

Optimize preferences without reference models.

Cloud Backtest for Neural Trader

ruvnet

Run intensive trading simulations in the cloud.

Megatron FSDP

nvidia

Optimize distributed training with Megatron FSDP.

A

Add Training Support

civitai

Integrate ecosystems into LoRA training seamlessly.

U

Unsloth

nousresearch

Accelerate LoRA/QLoRA fine-tuning with less VRAM.

Masked Auto-Encoder (MAE) for self-supervised pretraining and fine-tuning. Masks random patches and reconstructs them to learn visual representations; supports pretrain and finetune stages. Use when training, evaluating, exporting, or running inference for a TAO MAE backbone. Trigger phrases include "pretrain MAE", "self-supervised vision pretraining", "Masked Autoencoder", "Mask Auto-Encoder", "MAE fine-tune".

Deep learning framework (PyTorch Lightning / lightning package). Organize PyTorch code into LightningModules, configure Trainers for multi-GPU/TPU, implement data pipelines, callbacks, logging (W&B, TensorBoard, MLflow), distributed training (DDP, FSDP, DeepSpeed), for scalable neural network training.

Use when fine-tuning LLMs, training custom models, or adapting foundation models for specific tasks. Invoke for configuring LoRA/QLoRA adapters, preparing JSONL training datasets, setting hyperparameters for fine-tuning runs, adapter training, transfer learning, finetuning with Hugging Face PEFT, OpenAI fine-tuning, instruction tuning, RLHF, DPO, or quantizing and deploying fine-tuned models. Trigger terms include: LoRA, QLoRA, PEFT, finetuning, fine-tuning, adapter tuning, LLM training, model training, custom model.

Train and fine-tune transformer language models using TRL (Transformers Reinforcement Learning). Supports SFT, DPO, GRPO, KTO, RLOO and Reward Model training via CLI commands.

Train or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder; dense or static embedding model; for retrieval, similarity, clustering, classification, paraphrase mining, dedup, multimodal), `CrossEncoder` (reranker; pair scoring for two-stage retrieval / pair classification), and `SparseEncoder` (SPLADE, sparse embedding model; for learned-sparse retrieval). Covers loss selection, hard-negative mining, evaluators, distillation, LoRA, Matryoshka, and Hugging Face Hub publishing. Use for any sentence-transformers training task.