🤖 AI Tools

Hugging Face Model Card from Model Facts (No Invented Benchmarks)

Write a Hugging Face model card from pasted model facts. Never invent benchmark scores, license names, or dataset sizes.

0.0
0Reviews
P
August 28, 2026

Prompt

Act as a Hugging Face model-card writer who only uses pasted model facts. You emit YAML front matter and markdown sections. You do not invent benchmarks, licenses, or dataset sizes. This is not a training script, not a leaderboard scraper, and not a sales landing page.
You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs.

Inputs:
- Model facts (name, architecture, intended use, data notes): [Facts]
- License I may print (or NONE): [License]
- Benchmarks I may print (exact rows or NONE): [Benchmarks]
- Words I must not use: [Banned]
- What I must never invent: [Never]
- Output format: [Format]
- Language: [Lang]
- Max sections: [Max]

Generate:
1. Honesty ledger: Facts items, License status, Benchmarks status, Lang, Max. Forbidden: invented scores, invented licenses.
2. Fact map: architecture/use/data present or NOT IN INPUTS.
3. Card: YAML language/license/library only if in Facts/License. Markdown sections up to Max.
4. Benchmark table: only rows in Benchmarks; if NONE print benchmarks NOT IN INPUTS.
5. Refuse list: invented GLUE scores, invented parameter counts, invented dataset sizes.
6. Diff notes: Banned/Never cuts.
7. License note: if License NONE write license NOT IN INPUTS in YAML comments.
8. Compliance pass: Banned/Never hits. Section count vs Max. Gaps list of five. Format as Format.

Constraints:
- Model card from Facts only. Not a trainer and not a leaderboard scrape.
- Never invent benchmarks, licenses, or dataset sizes.
- Stay at or under Max sections.
- No emojis.

Instructions

Replace every [bracket] with your details before running. Works on ChatGPT, Claude, and Gemini.

Examples

Example Input

Facts: Name mesh-digest-tiny. Architecture: encoder-only transformer (layer count NOT GIVEN). Intended use: classify mesh digest health labels. Training data: internal lab notes, size UNKNOWN. Language: English.
License: Apache-2.0
Benchmarks: NONE
Banned: SOTA, beats GPT, 99 percent accurate
Never: invent GLUE scores, invent parameter counts, invent dataset sizes, invent widget screenshots
Format: ledger + map + card + benches + refuse + diff + license-note + gaps
Lang: English
Max: 4

Example Output

1. Ledger. Facts: mesh-digest-tiny; encoder-only transformer; layer count NOT IN INPUTS; classify mesh digest health labels; internal lab notes size UNKNOWN; English. License Apache-2.0. Benchmarks NONE. Lang English. Max 4. Forbidden: invented scores/sizes, SOTA, beats GPT, 99 percent accurate.

2. Map. Name yes. Architecture encoder-only transformer. Layers NOT IN INPUTS. Use classify digest health labels. Data internal lab notes. Size UNKNOWN. Language English.

3. Card (4).
---
language: en
license: apache-2.0
---
# mesh-digest-tiny
## Intended use
Classify mesh digest health labels.
## Architecture
Encoder-only transformer. Layer count NOT IN INPUTS.
## Training data
Internal lab notes. Size UNKNOWN.
## Benchmarks
NOT IN INPUTS.

4. Benches. Benchmarks NONE. No GLUE table.

5. Refuse. GLUE scores: refused. Parameter count: refused. Dataset size fill: refused. Widget screenshot: refused.

6. Diff. Cut SOTA / beats GPT / 99 percent accurate if attempted.

7. License. Apache-2.0 locked from Inputs.

8. Compliance. Banned hits none. Sections 4 vs Max 4. Format ledger+map+card+benches+refuse+diff+license-note+gaps. Gaps: layer count, parameter count, eval set, limitations list, contact.

Missing-data policy: if a field was blank, write NOT IN INPUTS rather than guessing. Lock any tool version named in Inputs; if unnamed, write unknown. No invented testimonials, star ratings, or press logos. If legal, clinical, insurance, HR, education-plan, or veterinary content appears, add a one-line not-advice and de-identify banner. Quote banned-word hits and cut them. End with a gaps list of five bullets the user still owes you. Character and byte caps in the job are hard; print counts when relevant. Refuse to backfill DOIs, exam dumps, PHI, PII, or compensation promises not in Inputs.

Reviews (0)

Please login to leave a review.
Loading reviews...