Machine learning

End-to-end Quark ONNX AutoSearchPro recipe — drives `quark.onnx.AutoSearchPro` (Optuna-based hyperparameter search) on a `.onnx` model to find the best…

End-to-end ONNX PTQ workflow for AMD Quark — for `.onnx` input models (with optional sibling `.onnx_data` external-weights file).

Apply existing ShapeShifter graph passes to an .onnx model via the quark-cli shapeshifter CLI or a ShapeShifter YAML.

Install or verify the correct PyTorch build for a user's accelerator backend before Quark installation.

End-to-end LLM accuracy evaluation on AMD ROCm (ROCm-only) — docker container setup OR host (no-docker) runtime, vLLM/SGLang/ATOM serving, lm-eval / lighteval…

Inspect a HuggingFace transformers / safetensors model and prepare metadata for Quark Torch PTQ planning.

Runs an end-to-end AMD Quark post-training quantization workflow for PyTorch / Hugging Face LLMs: inspect a Hub or local model, choose a quantization plan…

Run, resume, monitor, diagnose, and report Quark Quant-Perf workflows for PyTorch and HuggingFace transformers models.

Validate Quark Torch quantization output (HuggingFace safetensors + config.json) using four lightweight checks: auxiliary file copy alignment, excluded tensor…

Shrink a HuggingFace safetensors model to 1 hidden layer for fast debugging without loading the full model into memory.

Detects prompt injection attacks targeting LLM-based applications using a multi-layered defense combining regex pattern matching for known attack signatures…

Use Hugging Face Hub via MCP server tools.

Build, maintain, and query a personal LLM-managed wiki — a markdown knowledge base where the LLM owns all writing, cross-referencing, and bookkeeping while…

Deep-crawl any website from start URLs, return per-page LLM-ready text/markdown/HTML plus metadata (title, description, author, language, canonical URL, OG)…

Generate novel crystal structures and molecules using ADiT (All-atom Diffusion Transformer), a unified latent diffusion model.

Shrink a HuggingFace safetensors model to 1 hidden layer for fast debugging without loading the full model into memory.

Expert FinOps guidance for cloud, AI, and SaaS technology spend.

Check live performance KPIs from connected analytics: RAG status, trends, actions.

Wire Promptfoo and DeepTeam into CI/CD for automated regression red-teaming of LLM apps against OWASP LLM Top 10 and OWASP Agentic presets, failing the build…

Design a critical thinking task targeting specific skills like evaluating evidence, identifying bias, or analysing arguments.

Design discipline-specific critical thinking tasks grounded in knowledge-contingent reasoning rather than generic skills.

Slow down interpretation from observation to action.

Design a structured outdoor learning sequence embedding curriculum objectives in an available outdoor space.

Guide for selecting the most appropriate foundation MLIP model based on simulation requirements.