Skill Creator

zechenzhangAGI

75 published skills · 18,896 GitHub stars across the catalog. View on GitHub ↗

peft-fine-tuning

zechenzhangAGI's avatarfrom zechenzhangAGI★ 481

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.

nnsight-remote-interpretability

zechenzhangAGI's avatarfrom zechenzhangAGI★ 481

Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive models (70B+) without local GPU resources, or when working with any PyTorch architecture.

pyvene-interventions

zechenzhangAGI's avatarfrom zechenzhangAGI★ 481

Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal tracing, activation patching, interchange intervention training, or testing causal hypotheses about model behavior.

sparse-autoencoder-training

zechenzhangAGI's avatarfrom zechenzhangAGI★ 481

Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.

transformer-lens-interpretability

zechenzhangAGI's avatarfrom zechenzhangAGI★ 481

Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.

lambda-labs-gpu-cloud

zechenzhangAGI's avatarfrom zechenzhangAGI★ 481

Reserved and on-demand GPU cloud instances for ML training and inference. Use when you need dedicated GPU instances with simple SSH access, persistent filesystems, or high-performance multi-node clusters for large-scale training.

modal-serverless-gpu

zechenzhangAGI's avatarfrom zechenzhangAGI★ 481

Serverless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure management, deploying ML models as APIs, or running batch jobs with automatic scaling.

skypilot-multi-cloud-orchestration

zechenzhangAGI's avatarfrom zechenzhangAGI★ 481

Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or optimize GPU costs across providers.

awq-quantization

zechenzhangAGI's avatarfrom zechenzhangAGI★ 481

Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference than GPTQ with better accuracy preservation, or for instruction-tuned and multimodal models. MLSys 2024 Best Paper Award winner.

gguf-quantization

zechenzhangAGI's avatarfrom zechenzhangAGI★ 481

GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.

hqq-quantization

zechenzhangAGI's avatarfrom zechenzhangAGI★ 481

Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets, for fast quantization workflows, or when deploying with vLLM or HuggingFace Transformers.

evaluating-code-models

zechenzhangAGI's avatarfrom zechenzhangAGI★ 481

Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFace leaderboards.

mlflow

zechenzhangAGI's avatarfrom zechenzhangAGI★ 481

Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML lifecycle platform

tensorboard

zechenzhangAGI's avatarfrom zechenzhangAGI★ 481

Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML visualization toolkit

weights-and-biases

zechenzhangAGI's avatarfrom zechenzhangAGI★ 481

Track ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B - collaborative MLOps platform

autogpt-agents

zechenzhangAGI's avatarfrom zechenzhangAGI★ 481

Autonomous AI agent platform for building and deploying continuous agents. Use when creating visual workflow agents, deploying persistent autonomous agents, or building complex multi-step AI automation systems.

crewai-multi-agent

zechenzhangAGI's avatarfrom zechenzhangAGI★ 481

Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex tasks, when you need role-based agent collaboration with memory, or for production workflows requiring sequential/hierarchical execution. Built without LangChain dependencies for lean, fast execution.

qdrant-vector-search

zechenzhangAGI's avatarfrom zechenzhangAGI★ 481

High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.

dspy

zechenzhangAGI's avatarfrom zechenzhangAGI★ 481

Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's framework for systematic LM programming

guidance

zechenzhangAGI's avatarfrom zechenzhangAGI★ 481

Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework

instructor

zechenzhangAGI's avatarfrom zechenzhangAGI★ 481

Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library

outlines

zechenzhangAGI's avatarfrom zechenzhangAGI★ 481

Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines - dottxt.ai's structured generation library

langsmith-observability

zechenzhangAGI's avatarfrom zechenzhangAGI★ 481

LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.

phoenix-observability

zechenzhangAGI's avatarfrom zechenzhangAGI★ 481

Open-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running evaluations on datasets, or monitoring production AI systems with real-time insights.