Data Science & ML Agent Skills

NeMo Curator Data Processing

Accelerates LLM data curation using GPU-powered deduplication, quality filtering, and PII redaction at scale.

OpenRLHF Model Training

Deploys and manages high-performance RLHF training pipelines for large-scale language models using Ray and vLLM acceleration.

SAELens Mechanistic Interpretability

Decomposes neural network activations into interpretable, sparse features using SAELens for deep mechanistic interpretability research.

NVIDIA TensorRT-LLM Optimization

Optimizes Large Language Model inference for maximum throughput and ultra-low latency on NVIDIA GPUs.

Pyvene Causal Interventions

Facilitates causal interventions on PyTorch models using a declarative framework for mechanistic interpretability experiments.

LM Evaluation Harness

Evaluates Large Language Models across 60+ academic benchmarks using standardized prompts and metrics for reproducible research.

BLIP-2 Vision-Language

Implements state-of-the-art vision-language pre-training to enable high-quality image captioning and visual question answering within AI workflows.

Sentence Transformers Embeddings

Generates high-quality sentence, text, and image embeddings for RAG, semantic search, and clustering using state-of-the-art transformer models.

Weights & Biases MLOps

Integrates Weights & Biases into your workflow to track machine learning experiments, visualize training metrics, and manage model artifacts in real-time.

SentencePiece Tokenization

Implements language-independent subword tokenization using BPE and Unigram algorithms for robust NLP model training and inference.

RWKV Model Architecture

Implements and manages RWKV architectures for efficient, linear-time AI inference and long-context processing.

DSPy AI Programming & Optimization

Build and optimize complex AI systems using declarative programming instead of manual prompt engineering.

Mamba Architecture Guide

Implements and optimizes Selective State Space Models (SSM) for high-performance sequence modeling and long-context AI applications.

vLLM Inference Serving

Serves large language models with high throughput and low latency using PagedAttention and continuous batching.

Axolotl LLM Fine-Tuning

Streamlines the fine-tuning of large language models using Axolotl through expert YAML configuration and advanced training pattern guidance.

torchforge RL Training

Implements PyTorch-native agentic reinforcement learning workflows using Meta's torchforge library for scalable algorithm experimentation.

GPTQ Model Quantization

Compresses large language models to 4-bit precision to enable high-speed inference and deployment on consumer-grade hardware.

SimPO LLM Alignment

Implements Simple Preference Optimization to align Large Language Models without requiring a reference model.

Whisper Speech Recognition

Transcribes and translates audio across 99 languages using OpenAI's robust general-purpose speech recognition models.

Ray Data Scalable Processing

Facilitates high-performance distributed data processing and streaming for large-scale machine learning workloads.

DeepSpeed Distributed Training

Optimizes large-scale model training using DeepSpeed configurations, ZeRO optimization stages, and high-performance I/O management.

Knowledge Distillation for LLMs

Compresses large language models into efficient student models while retaining performance through advanced teacher-student transfer techniques.

BigCode Evaluation Harness

Evaluates AI code generation models using industry-standard benchmarks and pass@k metrics.

LLaVA Multimodal Vision Assistant

Integrates LLaVA to enable sophisticated visual instruction following and multi-turn conversational image understanding.

Speculative Decoding & Inference Optimization

Accelerates LLM inference speed by up to 3.6x using speculative decoding, Medusa heads, and lookahead techniques without sacrificing model quality.

PyTorch Lightning Training

Standardizes and accelerates PyTorch model training with built-in support for distributed computing, logging, and engineering best practices.

LangChain Framework Integration

Builds sophisticated LLM applications using agents, chains, and Retrieval-Augmented Generation (RAG) with a unified interface.

AWQ LLM Quantization & Optimization

Optimizes Large Language Models using 4-bit activation-aware weight quantization to achieve 3x faster inference with minimal accuracy loss.

HuggingFace Tokenizers

Provides high-performance, Rust-based tokenization tools for building and training NLP models with support for BPE, WordPiece, and Unigram algorithms.

CLIP Multimodal Vision

Integrates OpenAI's CLIP model to enable zero-shot image classification, semantic image search, and cross-modal retrieval without task-specific training.