ai-research-skills

LLM architectures and implementations including LitGPT, Mamba, NanoGPT, RWKV, and TorchTitan. Use when implementing, training, or understanding transformer and alternative architectures.

LLM architectures and implementations including LitGPT, Mamba, NanoGPT, RWKV, and TorchTitan. Use when implementing, training, or understanding transformer and alternative architectures.

LLM architectures and implementations including LitGPT, Mamba, NanoGPT, RWKV, and TorchTitan. Use when implementing, training, or understanding transformer and alternative architectures.

LLM architectures and implementations including LitGPT, Mamba, NanoGPT, RWKV, and TorchTitan. Use when implementing, training, or understanding transformer and alternative architectures.

LLM architectures and implementations including LitGPT, Mamba, NanoGPT, RWKV, and TorchTitan. Use when implementing, training, or understanding transformer and alternative architectures.

Text tokenization for LLMs including HuggingFace Tokenizers and SentencePiece. Use when training custom tokenizers or handling multilingual text.

Text tokenization for LLMs including HuggingFace Tokenizers and SentencePiece. Use when training custom tokenizers or handling multilingual text.

LLM fine-tuning frameworks including Axolotl, LLaMA-Factory, PEFT, and Unsloth. Use when fine-tuning models with LoRA, QLoRA, or full fine-tuning.

LLM fine-tuning frameworks including Axolotl, LLaMA-Factory, PEFT, and Unsloth. Use when fine-tuning models with LoRA, QLoRA, or full fine-tuning.

LLM fine-tuning frameworks including Axolotl, LLaMA-Factory, PEFT, and Unsloth. Use when fine-tuning models with LoRA, QLoRA, or full fine-tuning.

LLM fine-tuning frameworks including Axolotl, LLaMA-Factory, PEFT, and Unsloth. Use when fine-tuning models with LoRA, QLoRA, or full fine-tuning.

Neural network interpretability tools including TransformerLens, SAELens, NNSight, and pyvene. Use when analyzing model internals, finding circuits, or understanding how models compute.

Neural network interpretability tools including TransformerLens, SAELens, NNSight, and pyvene. Use when analyzing model internals, finding circuits, or understanding how models compute.

Neural network interpretability tools including TransformerLens, SAELens, NNSight, and pyvene. Use when analyzing model internals, finding circuits, or understanding how models compute.

Neural network interpretability tools including TransformerLens, SAELens, NNSight, and pyvene. Use when analyzing model internals, finding circuits, or understanding how models compute.

Data curation and processing at scale including NeMo Curator and Ray Data. Use when preparing training datasets or processing large-scale data.

Data curation and processing at scale including NeMo Curator and Ray Data. Use when preparing training datasets or processing large-scale data.

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.

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.

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.

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.

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.

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.

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.

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.

AI safety and content moderation including Constitutional AI, LlamaGuard, NeMo Guardrails, and Prompt Guard. Use when implementing safety filters, content moderation, or prompt injection detection.

AI safety and content moderation including Constitutional AI, LlamaGuard, NeMo Guardrails, and Prompt Guard. Use when implementing safety filters, content moderation, or prompt injection detection.

AI safety and content moderation including Constitutional AI, LlamaGuard, NeMo Guardrails, and Prompt Guard. Use when implementing safety filters, content moderation, or prompt injection detection.

AI safety and content moderation including Constitutional AI, LlamaGuard, NeMo Guardrails, and Prompt Guard. Use when implementing safety filters, content moderation, or prompt injection detection.

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.

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.

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.

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.

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.

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.

GPU cloud and compute orchestration including Modal, Lambda Labs, and SkyPilot. Use when deploying training jobs or managing GPU resources.

GPU cloud and compute orchestration including Modal, Lambda Labs, and SkyPilot. Use when deploying training jobs or managing GPU resources.

GPU cloud and compute orchestration including Modal, Lambda Labs, and SkyPilot. Use when deploying training jobs or managing GPU resources.

Model optimization and quantization including Flash Attention, bitsandbytes, GPTQ, AWQ, GGUF, and HQQ. Use when reducing memory, accelerating inference, or quantizing models.

Model optimization and quantization including Flash Attention, bitsandbytes, GPTQ, AWQ, GGUF, and HQQ. Use when reducing memory, accelerating inference, or quantizing models.

Model optimization and quantization including Flash Attention, bitsandbytes, GPTQ, AWQ, GGUF, and HQQ. Use when reducing memory, accelerating inference, or quantizing models.

Model optimization and quantization including Flash Attention, bitsandbytes, GPTQ, AWQ, GGUF, and HQQ. Use when reducing memory, accelerating inference, or quantizing models.

Model optimization and quantization including Flash Attention, bitsandbytes, GPTQ, AWQ, GGUF, and HQQ. Use when reducing memory, accelerating inference, or quantizing models.

Model optimization and quantization including Flash Attention, bitsandbytes, GPTQ, AWQ, GGUF, and HQQ. Use when reducing memory, accelerating inference, or quantizing models.

LLM benchmarking and evaluation including lm-evaluation-harness, BigCode Evaluation Harness, and NeMo Evaluator. Use when benchmarking models or measuring performance.

LLM benchmarking and evaluation including lm-evaluation-harness, BigCode Evaluation Harness, and NeMo Evaluator. Use when benchmarking models or measuring performance.

LLM benchmarking and evaluation including lm-evaluation-harness, BigCode Evaluation Harness, and NeMo Evaluator. Use when benchmarking models or measuring performance.

Production LLM inference including vLLM, TensorRT-LLM, llama.cpp, and SGLang. Use when deploying models for production inference.

Production LLM inference including vLLM, TensorRT-LLM, llama.cpp, and SGLang. Use when deploying models for production inference.

Production LLM inference including vLLM, TensorRT-LLM, llama.cpp, and SGLang. Use when deploying models for production inference.

Production LLM inference including vLLM, TensorRT-LLM, llama.cpp, and SGLang. Use when deploying models for production inference.

ML experiment tracking and lifecycle including Weights & Biases, MLflow, and TensorBoard. Use when tracking experiments or managing models.

ML experiment tracking and lifecycle including Weights & Biases, MLflow, and TensorBoard. Use when tracking experiments or managing models.

ML experiment tracking and lifecycle including Weights & Biases, MLflow, and TensorBoard. Use when tracking experiments or managing models.

LLM agent frameworks including LangChain, LlamaIndex, CrewAI, and AutoGPT. Use when building chatbots, autonomous agents, or tool-using systems.

LLM agent frameworks including LangChain, LlamaIndex, CrewAI, and AutoGPT. Use when building chatbots, autonomous agents, or tool-using systems.

LLM agent frameworks including LangChain, LlamaIndex, CrewAI, and AutoGPT. Use when building chatbots, autonomous agents, or tool-using systems.

LLM agent frameworks including LangChain, LlamaIndex, CrewAI, and AutoGPT. Use when building chatbots, autonomous agents, or tool-using systems.

Retrieval-Augmented Generation including Chroma, FAISS, Pinecone, Qdrant, and Sentence Transformers. Use when building semantic search or document retrieval systems.

Retrieval-Augmented Generation including Chroma, FAISS, Pinecone, Qdrant, and Sentence Transformers. Use when building semantic search or document retrieval systems.

Retrieval-Augmented Generation including Chroma, FAISS, Pinecone, Qdrant, and Sentence Transformers. Use when building semantic search or document retrieval systems.

Retrieval-Augmented Generation including Chroma, FAISS, Pinecone, Qdrant, and Sentence Transformers. Use when building semantic search or document retrieval systems.

Retrieval-Augmented Generation including Chroma, FAISS, Pinecone, Qdrant, and Sentence Transformers. Use when building semantic search or document retrieval systems.

Structured LLM outputs including DSPy, Instructor, Guidance, and Outlines. Use when extracting structured data or constraining LLM outputs.

Structured LLM outputs including DSPy, Instructor, Guidance, and Outlines. Use when extracting structured data or constraining LLM outputs.

Structured LLM outputs including DSPy, Instructor, Guidance, and Outlines. Use when extracting structured data or constraining LLM outputs.

Structured LLM outputs including DSPy, Instructor, Guidance, and Outlines. Use when extracting structured data or constraining LLM outputs.

LLM application monitoring including LangSmith and Phoenix. Use when debugging LLM apps or monitoring production systems.

LLM application monitoring including LangSmith and Phoenix. Use when debugging LLM apps or monitoring production systems.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

Research ideation frameworks including structured brainstorming and creative thinking. Use when exploring new research directions, generating novel ideas, or seeking fresh angles on existing work.

Research ideation frameworks including structured brainstorming and creative thinking. Use when exploring new research directions, generating novel ideas, or seeking fresh angles on existing work.