LLM architectures and implementations including LitGPT, Mamba, NanoGPT, RWKV, and TorchTitan. Use when implementing, training, or understanding transformer and alternative architectures.
No verified skills in this plugin.
GPU cloud and compute orchestration including Modal, Lambda Labs, and SkyPilot. Use when deploying training jobs or managing GPU resources.
No verified skills in this plugin.
Model optimization and quantization including Flash Attention, bitsandbytes, GPTQ, AWQ, GGUF, and HQQ. Use when reducing memory, accelerating inference, or quantizing models.
No verified skills in this plugin.
Vision, audio, and multimodal models including CLIP, Whisper, LLaVA, BLIP-2, Segment Anything, Stable Diffusion, and AudioCraft. Use when working with images, audio, or multimodal tasks.
No verified skills in this plugin.
Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Includes LaTeX templates, citation verification, reviewer guidelines, and writing best practices from top researchers.
No verified skills in this plugin.
Text tokenization for LLMs including HuggingFace Tokenizers and SentencePiece. Use when training custom tokenizers or handling multilingual text.
No verified skills in this plugin.
LLM fine-tuning frameworks including Axolotl, LLaMA-Factory, PEFT, and Unsloth. Use when fine-tuning models with LoRA, QLoRA, or full fine-tuning.
No verified skills in this plugin.
Neural network interpretability tools including TransformerLens, SAELens, NNSight, and pyvene. Use when analyzing model internals, finding circuits, or understanding how models compute.
No verified skills in this plugin.
Data curation and processing at scale including NeMo Curator and Ray Data. Use when preparing training datasets or processing large-scale data.
No verified skills in this plugin.
RLHF and preference alignment including TRL, GRPO, OpenRLHF, SimPO, verl, slime, miles, and torchforge. Use when aligning models with human preferences, training reward models, or large-scale RL training.
No verified skills in this plugin.
AI safety and content moderation including Constitutional AI, LlamaGuard, and NeMo Guardrails. Use when implementing safety filters or content moderation.
No verified skills in this plugin.
Multi-GPU and multi-node training including DeepSpeed, PyTorch FSDP, Accelerate, Megatron-Core, PyTorch Lightning, and Ray Train. Use when training large models across GPUs.
No verified skills in this plugin.
LLM benchmarking and evaluation including lm-evaluation-harness, BigCode Evaluation Harness, and NeMo Evaluator. Use when benchmarking models or measuring performance.
No verified skills in this plugin.
Production LLM inference including vLLM, TensorRT-LLM, llama.cpp, and SGLang. Use when deploying models for production inference.
No verified skills in this plugin.
ML experiment tracking and lifecycle including Weights & Biases, MLflow, and TensorBoard. Use when tracking experiments or managing models.
No verified skills in this plugin.
LLM agent frameworks including LangChain, LlamaIndex, CrewAI, and AutoGPT. Use when building chatbots, autonomous agents, or tool-using systems.
No verified skills in this plugin.
Retrieval-Augmented Generation including Chroma, FAISS, Pinecone, Qdrant, and Sentence Transformers. Use when building semantic search or document retrieval systems.
No verified skills in this plugin.
Structured LLM outputs including DSPy, Instructor, Guidance, and Outlines. Use when extracting structured data or constraining LLM outputs.
No verified skills in this plugin.
LLM application monitoring including LangSmith and Phoenix. Use when debugging LLM apps or monitoring production systems.
No verified skills in this plugin.
Advanced ML techniques including MoE Training, Model Merging, Long Context, Speculative Decoding, Knowledge Distillation, and Model Pruning. Use when implementing cutting-edge optimization or architecture techniques.
No verified skills in this plugin.