Results for “model-inference”

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 models, or reducing inference costs. Covers temperature scaling, soft targets, reverse KLD, logit distillation, and MiniLLM training strategies.

This skill should be used when the user asks to "implement a DiD regression", "write a causal inference pipeline", "set up an event study", "implement instrumental variables", "run a regression discontinuity design", "build a synthetic control model", "implement propensity score matching", "write parallel trends test", "implement Bacon decomposition", or needs code templates for causal inference methods in Python, R, or Stata. Based on Scott Cunningham's Causal Inference: The Mixtape.

Trains, evaluates, exports, prunes, quantizes, retrains, and runs inference for OCDNet scene text detection models using TAO, detecting arbitrary-oriented text regions in natural images.

Statistical modeling toolkit. OLS, GLM, logistic, ARIMA, time series, hypothesis tests, diagnostics, AIC/BIC, for rigorous statistical inference and econometric analysis.

Hugging Face CLI to estimate the required memory to load Safetensors or GGUF model weights for inference from the Hugging Face Hub

Statsmodels is Python's premier library for statistical modeling, providing tools for estimation, inference, and diagnostics across a wide range of statistical methods.

Hugging Face CLI to estimate the required memory to load Safetensors or GGUF model weights for inference from the Hugging Face Hub

Patterns for Bayesian inference in R using brms, including multilevel models, DAG validation, and marginal effects. Use when performing Bayesian analysis.

Hugging Face CLI to estimate the required memory to load Safetensors or GGUF model weights for inference from the Hugging Face Hub

Inspect or select a Clade execution connection while keeping agent runtime, inference provider, wire protocol, and model distinct. Use for Claude/Codex runtime selection, Anthropic/OpenAI/MiniMax/Kimi/custom gateways, model routing, or connection troubleshooting.

Hugging Face CLI to estimate the required memory to load Safetensors or GGUF model weights for inference from the Hugging Face Hub

Trains, evaluates, exports, quantizes, and runs inference for Sparse4D multi-camera temporal 3D object detection and tracking models using TAO.

Choose between scikit-learn for predictive workflows and statsmodels for inferential modeling, with guidance on preprocessing, leakage prevention, validation, and result handoff.

Build production ML systems with PyTorch 2.x, TensorFlow, and modern ML frameworks. Implements model serving, feature engineering, A/B testing, and monitoring. Use PROACTIVELY for ML model deployment, inference optimization, or production ML infrastructure.

Open Neural Network Exchange format for model interoperability across frameworks. Export models from PyTorch, TensorFlow, and other frameworks to ONNX, optimize with ONNX Runtime, and deploy for cross-platform inference on CPU, GPU, and edge devices.

Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.

Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.

Trains, evaluates, exports, and runs inference for FastFoundationStereo (FFS) stereo depth estimation models, a distilled variant of FoundationStereo with lower latency.

Plans and coordinates the deployment of a model to Amazon SageMaker AI, selecting the appropriate pathway (real-time, serverless, async, batch, or Bedrock CMI) based on model type, traffic, latency, and cost constraints.

Hugging Face Hub CLI (hf) — search, download, and upload models and datasets, manage repos, query datasets with SQL, deploy inference endpoints, manage Spaces and buckets.

Hugging Face Hub CLI (hf) — search, download, and upload models and datasets, manage repos, query datasets with SQL, deploy inference endpoints, manage Spaces and buckets.

Runs the open-source LLaVA vision-language model for image understanding, captioning, visual question answering, and multi-turn image conversations, including setup, inference, and training guidance.

Trains, evaluates, exports, quantizes, and runs inference for SegFormer semantic segmentation models using NVIDIA TAO.

Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase. Covers MoE architectures, routing mechanisms, load balancing, expert parallelism, and inference optimization.

Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase. Covers MoE architectures, routing mechanisms, load balancing, expert parallelism, and inference optimization.

Breaks down a company's business model, revenue signals, positioning, pricing, moat, and weak points into a fixed, comparable template with fact-versus-inference labeling.

Generates synthetic body MRI volumes using NVIDIA's NV-Generate-CTMR rflow-mr model. Wraps the upstream diffusion inference pipeline with config staging, output validation, and NIfTI volume summarization.

Quantize large language models to 4-bit with minimal accuracy loss using GPTQ, enabling deployment of 70B+ models on consumer GPUs with 4× memory reduction and 3-4× faster inference.

Self-hosted OpenAI-compatible LLM router — smart tier-based routing, ZK-stamped routing decisions, mode overrides, free OpenRouter at install via the Birth bot. Save 60-80% on inference costs by routing to the cheapest capable model across 12+ OpenRouter models.

Compress large language models by 40-60% with minimal accuracy loss using one-shot pruning techniques like Wanda and SparseGPT, enabling faster inference and deployment on constrained hardware.

Train, evaluate, distill, quantize, export, and run inference for RT-DETR object detection models using NVIDIA TAO.

Guarantee valid JSON, XML, or code structure during text generation using Pydantic models for type-safe outputs, supporting local models (Transformers, vLLM, llama.cpp) and maximizing inference speed with structured generation.

Generates and analyzes proteins using ESM3 and ESM C language models, covering sequence generation, structure prediction, inverse folding, embeddings, and function conditioning with local or cloud-based Forge API inference.

Train, evaluate, export, and run inference for pose classification models using ST-GCN on skeleton keypoint sequences.

Generates full songs from lyrics and tags using the open-source HeartMuLa music models, with multilingual support and local GPU or CPU inference.

State-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache. Selective SSM with hardware-aware design. Mamba-1 (d_state=16) and Mamba-2 (d_state=128, multi-head). Models 130M-2.8B on HuggingFace.