Scan to join WeChat grouppersonjakexiaoNo key required
"few-shot-examples"
Curated few-shot examples for construction AI tasks: classification, extraction, analysis. Domain-specific examples for improved LLM performance.
download10deployed_code—star57
Skill Directory
AI Skill Directory
Browse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.
personjakexiaoNo key required
faceforensics_classifier
Clasificador de deepfakes y face swaps entrenado en el dataset FaceForensics++
download10deployed_code—star0
personjakexiaoNo key required
scikit_image
Advanced image processing algorithms for document analysis
download10deployed_code—star0
personjakexiaoNo key required
knowledge-distillation
Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT-4 capabilities to open-source …
download10deployed_code—star23.1K
personjakexiaoNo key required
sglang
Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, or when you need 5× faster infe…
download10deployed_code—star23.1K
personjakexiaoNo key required
transformer-lens-interpretability
Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering mo…
download10deployed_code—star23.1K
personjakexiaoNo key required
audiocraft-audio-generation
PyTorch library for audio generation including text-to-music (MusicGen) and text-to-sound (AudioGen). Use when you need to generate music from text descriptions, create sound effects, or perform melod…
download10deployed_code—star23.1K
personjakexiaoNo key required
hqq-quantization
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 deployin…
download10deployed_code—star23.1K
personjakexiaoNo key required
"contractor-matching-ai"
AI-powered contractor matching and selection for construction projects. Analyze contractor capabilities, past performance, certifications, and project requirements to recommend optimal matches.
download10deployed_code—star57
personjakexiaoNo key required
fp16_int8_quantization
Quantization of ML models to FP16/INT8 to reduce memory and accelerate inference in the KYC pipeline
download10deployed_code—star0
personjakexiaoNo key required
llamaindex
Data framework for building LLM applications with RAG. Specializes in document ingestion (300+ connectors), indexing, and querying. Features vector indices, query engines, agents, and multi-modal supp…
download10deployed_code—star23.1K
personjakexiaoNo key required
peft-fine-tuning
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 a…
download10deployed_code—star23.1K
personjakexiaoNo key required
llama-cpp
Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.…
download10deployed_code—star23.1K
personjakexiaoNo key required
pyvene-interventions
Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal tracing, activation patching, interchange interven…
download10deployed_code—star23.1K
personjakexiaoNo key required
llava
Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Supports multi-turn image chat, vi…
download10deployed_code—star23.1K
personjakexiaoNo key required
optimizing-attention-flash
Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory iss…
download10deployed_code—star23.1K
personjakexiaoNo key required
esrgan_super_resolution
Super-resolución de la foto del documento para mejorar calidad del face match cuando la foto es de baja resolución
download10deployed_code—star0
personjakexiaoNo key required
insightface_arcface
State-of-the-art facial recognition with ArcFace R100 to compare selfie with document photo
download10deployed_code—star0
personjakexiaoNo key required
nemo-curator
GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, N…
download10deployed_code—star23.1K
personjakexiaoNo key required
axolotl
Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support
download10deployed_code—star23.1K
personjakexiaoNo key required
sparse-autoencoder-training
Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, …
download10deployed_code—star23.1K
personjakexiaoNo key required
nnsight-remote-interpretability
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 (…
download10deployed_code—star23.1K
personjakexiaoNo key required
distributed-llm-pretraining-torchtitan
Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs…
download10deployed_code—star23.1K
personjakexiaoNo key required
miles-rl-training
Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8/INT4, needing train-inference alignment, or requiring spec…
download10deployed_code—star23.1K