Browse skills

Nemo Mbridge Perf Moe Vlm Training — provides AI agent assistance for software development workflows.

Verl Rl Training — provides AI agent assistance for software development workflows.

Ito Training — provides AI agent assistance for software development workflows.

Pytorch Lightning streamlines PyTorch deep learning workflows by handling boilerplate, boosting training speed & simplifying experiment management.

Human In The Loop Training — provides AI agent assistance for software development workflows.

PyTorch FSDP accelerates large model training by intelligently distributing data across multiple GPUs, boosting efficiency and reducing memory footprint.

Deepspeed optimizes large model training by enabling efficient memory usage and faster execution, boosting productivity for AI developers.

Moe Training simulates realistic conversational interactions for chatbot development, accelerating learning and improving dialogue flow.

This skill integrates TensorBoard for visualizing machine learning metrics during training, aiding in model debugging and performance analysis.

Human In The Loop Training — provides AI agent assistance for software development workflows.

Helps with machine learning, data modeling as part of agent workflows workflows.

Generates optimal AI skill prompts & training data leveraging best practices for improved model performance.

This "Lesson" skill generates structured learning content—text, questions, and answers—to explain concepts clearly and effectively for study or training.

Automatically expands limited training data with synthetic examples generated from web searches, boosting model accuracy.

Training Llms Megatron — provides AI agent assistance for software development workflows.

This AI generates personalized workout programs tailored to your goals and fitness level, maximizing your training efficiency.

Analyzes training logs to identify patterns and insights for improved performance optimization and targeted skill development.

This skill trains large language models like Megatron using orchestra-research techniques for enhanced performance and customization.

Provides LLMs guidance and assistance for building AI and machine learning applications.

This skill trains large language models like Megatron, accelerating AI development and enabling powerful custom LLM creation for diverse applications.

Dynamically adjusts reinforcement learning parameters to accelerate training and improve performance in complex environments.

Generates synthetic training data tailored to your model's needs, improving performance without real-world examples.

Sundial-org's training-data-curation refines datasets by identifying biases, errors, and gaps for improved AI model performance.

Analyzes GPU utilization and identifies performance bottlenecks during AI model training and inference tasks.