Results for “models”

Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.

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.

Use when writing technical documentation that needs to be readable by both humans and AI models, converting existing docs to HADS format, validating a HADS document, or optimizing documentation for token-efficient AI consumption.

Design, implement, and debug Python asyncio and concurrent code with structured concurrency, bounded parallelism, cancellation safety, timeouts, cleanup, and clear error propagation. Use for async workflows, task orchestration, or choosing among concurrency models.

Model-trader version compatibility protocol: Embed version metadata in checkpoints, validate at load time. Trigger when: (1) training and live trading versions diverge, (2) models fail to load, (3) action interpretation issues.

Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.

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.

Optimize content to be cited by AI language models (ChatGPT, Perplexity, Claude, Gemini, Mistral) as authoritative sources, distinct from traditional SEO.

Queries Hugging Face benchmark leaderboards to find the best AI models for a task, filters by device constraints, and returns a ranked comparison table with scores.

Train or fine-tune sentence-transformers models for retrieval, similarity, clustering, classification, and reranking, with support for bi-encoders, cross-encoders, and sparse encoders.

Extract text, tables, and structured data from documents using Azure Document Intelligence. Process invoices, receipts, IDs, forms, or build custom document models.

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

Trains, evaluates, exports, and runs inference for Siamese-network-based optical inspection models to detect manufacturing defects and quality issues in image pairs.

Provides production-grade Django architecture patterns including project structure, model design, REST API design with DRF, ORM best practices, caching, signals, and middleware.

Design, operate, and troubleshoot OCI services including OKE, IoT, Functions, and Enterprise AI with OCI Generative AI models, agents, RAG, and cost estimation.

Convert chemical structures (SMILES or RDKit molecules) into numerical representations for machine learning using 100+ featurizers, including ECFP, MACCS, descriptors, and pretrained models like ChemBERTa.

Generate images using FLUX models via the inference.sh CLI, supporting text-to-image, image-to-image, and LoRA fine-tuning.

Generate images with 50+ AI models including GPT-Image-2, FLUX, Gemini, Grok, Seedream, and Reve via the inference.sh CLI.

Learn and apply prompt engineering techniques for LLMs, image generators, and video models using the inference.sh CLI.

Quantize large language models to 4-bit using activation-aware weight quantization, achieving ~3x speedup with minimal accuracy loss for deployment on limited GPU memory.

Provides expert guidance for fine-tuning LLMs with LLaMA-Factory, covering WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, and multimodal support.

Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies for maximum GPU efficiency.

Plan and govern product content: audit existing material, define content models, establish voice and tone, and set ownership workflows.

Analyze card sorting results to inform information architecture and navigation structure. Use after conducting open or closed card sort studies.

Quantize large language models to 8/4/3/2/1-bit precision without calibration data, using multiple optimized backends and integrations with HuggingFace Transformers, vLLM, and PEFT/LoRA.

Fine-tune large language models by training less than 1% of parameters using LoRA, QLoRA, and 25+ adapter methods, enabling efficient adaptation on limited GPU memory.

Build applications with Gemini API hosted models, including multimodal content, function calling, and structured outputs, using the latest SDKs and model specifications.

Generates images, videos, and audio transcripts using fal.ai's API, supporting models like FLUX, Stable Diffusion, and Whisper.

Orchestrator — author the flow-anchored logical domain model (entities, state machines, events/commands, read models, policies, logical contracts) from an approved user-flow map, running one domain-modeling framework per session, before UX variation work

Answer Engine Optimization (AEO) skill — optimize content to be cited by AI language models (ChatGPT, Perplexity, Claude, Gemini, Mistral) as authoritative sources. Distinct from SEO — AEO optimizes for citation in LLM-generated responses, not search rankings.

Use mmx to generate text, images, video, speech, and music via the MiniMax AI platform. Use when the user wants to create media content, chat with MiniMax models, perform web search, or manage MiniMax

State-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, performing image-to-image translation, inpainting, or building custom diffusion pipelines.

Adds PyTorch FSDP2 (fully_shard) to training scripts with correct init, sharding, mixed precision/offload config, and distributed checkpointing. Use when models exceed single-GPU memory or when you need DTensor-based sharding with DeviceMesh.

State-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, performing image-to-image translation, inpainting, or building custom diffusion pipelines.

Adds PyTorch FSDP2 (fully_shard) to training scripts with correct init, sharding, mixed precision/offload config, and distributed checkpointing. Use when models exceed single-GPU memory or when you need DTensor-based sharding with DeviceMesh.

Run Python code in the cloud with serverless containers, GPUs, and autoscaling. Use when deploying ML models, running batch processing jobs, scheduling compute-intensive tasks, or serving APIs that require GPU acceleration or dynamic scaling.