What is ai4science-huggingface-recipes?

A workflow for creating and editing recipes for machine-learning models hosted on Hugging Face, a service that publishes models and datasets.

Use it for training, fine-tuning, inference, or evaluation recipes. It covers model discovery, folder placement, official scripts, version details, and AMD GPU documentation.

It helps match each recipe to what the model actually supports and keeps model identifiers, dependencies, scripts, hardware notes, and attribution accurate.

How AMDResearch/ai4science-studio configures Cursor

Reuse

Borrowing it

Nothing to install: this file belongs to AMDResearch/ai4science-studio. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/AMDResearch/ai4science-studio/main/.cursor/skills/ai4science-huggingface-recipes/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/AMDResearch/ai4science-studio

Made for: Cursor.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/amdresearch/ai4science-studio/ai4science-huggingface-recipes/github.svg)](https://agentmods.dev/skills/amdresearch/ai4science-studio/ai4science-huggingface-recipes)

Your own site

<a href="https://agentmods.dev/skills/amdresearch/ai4science-studio/ai4science-huggingface-recipes"><img src="https://agentmods.dev/badge/skills/amdresearch/ai4science-studio/ai4science-huggingface-recipes/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/amdresearch/ai4science-studio/ai4science-huggingface-recipes"><img src="https://agentmods.dev/badge/skills/amdresearch/ai4science-studio/ai4science-huggingface-recipes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 768 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00041	$0.00768
Opus 5	$0.00020	$0.00384
Sonnet 5	$0.00008	$0.00154
Haiku 4.5	$0.00004	$0.00077

Measured 11d ago against content hash 847a2d492122, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

ai4science-huggingface-recipes scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.cursor/skills/ai4science-huggingface-recipes/SKILL.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hugging Face recipes workflow

Use this skill when adding or refactoring train / fine-tune / inference / eval material for models hosted on Hugging Face inside this repo.

Steps

Identify the model on Hugging Face (model card, license, intended use, dependencies). Record the full id org/model in the model folder README.md.
Map to a folder name under the correct domain’s models/ directory. Default: replace / with __ in the Hub id (org__model). Alternative: a public model name on disk (e.g. HydraGNN, ORBIT-2) is acceptable when that domain’s models/README.md allows it and the model README.md states the full org/model id at the top—do not rename those folders to org__model unless the user asks.
Align the task with what the model card and upstream code support (inference-only vs fine-tuning vs training from scratch).
Reuse upstream scripts or minimal wrappers: prefer calling official examples with pinned versions rather than reimplementing full training stacks unless necessary.
Document Python/PyTorch (or other) versions, ROCm builds and versions for AMD Instinct when validated, and how to run from the repo root or from recipes/ subfolders.
Attribute authors, papers, and license in the model README.md and in recipe comments where helpful.

Recipe folder tips

Use subfolders under recipes/ for distinct tasks, e.g. recipes/inference/, recipes/finetune/.
Keep entrypoints small and documented; link to Hugging Face Spaces or Colab only as supplements, not replacements for reproducible commands.

Avoid

Committing token values or private Hub tokens.
Checking in large *.bin, *.safetensors, or full datasets when .gitignore already excludes them—point users to Hub or documented download steps instead.
Hardcoding HF repo filenames without verifying: model repos ship different names than recipes assume (e.g. walrus.pt not model.pt). Use list_repo_files() to discover actual names, filter by extension, pick smallest or first match.
Assuming a _mi300x.sh SLURM script name — use _amd.sh (covers MI250X, MI300X, MI350X with the same rocm7.2.x image).

Read the full file on GitHub · 51 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

11d ago First seen · 51 lines · 41 tokens per session scan A 847a2d492122

Subscribe to this mod's changes

ai4science-huggingface-recipes is a skill published in the GitHub repository AMDResearch/ai4science-studio (4 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 768 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Data and AI Scientific ai-for-science amd drug-discovery earth-science fine-tuning healthcare

exporting-to-fhir

Convert OpenMed NER output (entities from openmed.analyzetext) into FHIR R4 resources — Condition, MedicationStatement, Observation — using OpenMed's built-in FHIR R4 export helpers in openmed.clinical.exporters. Covers the verified CodeableConcept builder (coding, codeableconcept, systemuri), deterministic fullUrl…

maziyarpanahi/openmed · 163 tokens

batch-processing-clinical-text

Run large-scale batch NER, PII extraction, or de-identification over many clinical notes on-device with OpenMed, with sharding, checkpointing, resumability, and append-only JSONL output. Use when the user needs to process a corpus or folder of notes, de-identify a dataset, run NER over thousands of documents, build a…

maziyarpanahi/openmed · 161 tokens

choosing-openmed-models

Discover and pick the right OpenMed model for a clinical or biomedical task, domain, or language. Use when the user asks which OpenMed model to use, wants to list model categories, find a Disease vs Oncology vs Privacy/PII model, get a PII model for a specific language, search models by size or task, or inspect a…

maziyarpanahi/openmed · 134 tokens

extracting-clinical-entities

Run clinical and biomedical named-entity recognition on medical text with OpenMed's analyzetext. Use when the user wants to extract diseases, drugs, anatomy, genes, or other biomedical entities from notes; needs NER output as dict/json/html/csv; wants to filter by confidence, group entities, toggle sentence detection…

maziyarpanahi/openmed · 118 tokens

loading-openmed-models

Load OpenMed clinical/biomedical NER models from the Hugging Face Hub or a local path and reuse them efficiently across calls. Use when the user wants to load an OpenMed model, control the model cache, run fully offline after a one-time download, reuse a ModelLoader to avoid reloading, set a cachedir or device, or…