Skip to main content

Persian LLM Reference

Local path: ~/Desktop/PERSIAN-LLM-REFERENCE/ — this folder is the git repo root for GitHub.

مرجع جهانی مدل‌های زبانی فارسی

The open global atlas for Persian (Farsi) language models — built as a structured registry — clearer than link lists and more honest than hype.

Not a personal notebook. Not a local mirror. Online-first · community-maintained · machine-readable.

Why this repo exists

Existing references What they lack What PLR adds
Awesome Persian LLM Links rot; no schema Structured records + verification gates
Leaderboards (MIZAN, PartAI) Scores only; no corpus law Model + dataset + benchmark in one manifest
Hugging Face search No Persian-native taxonomy Script · corpus · curriculum · literary axes
Papers Scattered Indexed with asOf dates and primary URLs

Discovery credit: Awesome-Persian-LLM by Mohammad Heydari — verified entry awesome-persian-llm · ECOSYSTEM.md.

Live surfaces (after deploy)

Surface URL
Atlas UI https://sinakazemnezhad.github.io/persian-llm-reference
PyPI (Python client) https://pypi.org/project/persian-llm-reference/
Manifest JSON /data/reference-manifest.json
Agent discovery /.well-known/persian-llm-reference.json
Raw (cite in papers) raw.githubusercontent.com/.../data/reference-manifest.json

Repository layout

Path Role
data/reference-manifest.json SSOT — all models, datasets, benchmarks
workspace/public/ Static site (GitHub Pages root after build)
governance/MANIFEST_LAW.md Taxonomy + verification gates
governance/METHODOLOGY.md Trust, axes, cite policy
governance/POSITIONING.md How we beat other references
governance/ROADMAP.md Full phased plan — meaningful · usable · productive · smart
docs/PYPI_TRUSTED_PUBLISHING_SETUP.md PyPI OIDC publish (sourcea-boot pattern)
pyproject.toml Python package · pip install persian-llm-reference

GitHub setup (required)

  1. Repo: github.com/sinakazemnezhad/persian-llm-reference
  2. Enable GitHub Pages → source: GitHub Actions
  3. Push main branch
  4. Site: https://sinakazemnezhad.github.io/persian-llm-reference

Python client (PyPI)

Same pattern as sourcea-boot · pypi.org/project/sourcea-boot.

pip install persian-llm-reference
plr stats
plr get persianmind-v1
plr cite
plr validate

Editable install from repo root:

cd workspace && node scripts/sync-python-manifest.mjs
pip install -e .
  • Python client: MIT (LICENSE-MIT)
  • Registry metadata: CC-BY-4.0 (LICENSE)
  • Publish: GitHub Release → publish-pypi workflow (trusted publishing). See docs/PYPI_TRUSTED_PUBLISHING_SETUP.md.

Build & verify

cd workspace
npm run build    # validate + copy manifest to public/
npm run e2e      # local server smoke

Verification gates

indexedverifiedmeasuredcorpus-documentedliterary

No invented scores. null until a primary source exists.

Cite

@misc{persian_llm_reference,
  title={Persian LLM Reference — Global Atlas},
  year={2026},
  url={https://sinakazemnezhad.github.io/persian-llm-reference},
  note={Manifest version in generatedAt field}
}

Contributing

One PR = one entry + primary source URL. See governance/CONTRIBUTING.md.

License

Manifest metadata and docs: CC-BY-4.0. Each model entry retains its own license.

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

persian_llm_reference-0.3.1.tar.gz (16.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

persian_llm_reference-0.3.1-py3-none-any.whl (16.3 kB view details)

Uploaded Python 3

File details

Details for the file persian_llm_reference-0.3.1.tar.gz.

File metadata

  • Download URL: persian_llm_reference-0.3.1.tar.gz
  • Upload date:
  • Size: 16.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for persian_llm_reference-0.3.1.tar.gz
Algorithm Hash digest
SHA256 a7a34ee1957e89877397122cc074e9530ba805cb9e865c2ee90346117945aa8d
MD5 ca2b5748008b6300041e1d3d90b3add6
BLAKE2b-256 77c506e68809d7f827be14616807cb2048e408b2f621cbd8580f382ebfade7a2

See more details on using hashes here.

Provenance

The following attestation bundles were made for persian_llm_reference-0.3.1.tar.gz:

Publisher: publish-pypi.yml on sinakazemnezhad/persian-llm-reference

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file persian_llm_reference-0.3.1-py3-none-any.whl.

File metadata

File hashes

Hashes for persian_llm_reference-0.3.1-py3-none-any.whl
Algorithm Hash digest
SHA256 c92e2aeeb11c217a1e7a1bf8bc670684df5ed44eefc56d8ac8daeb91a579acbd
MD5 d9961776fe1eb5ed9c54c11d854a8a9e
BLAKE2b-256 b13a3b226fd879f88a3331fccba8a7f381906f6f74db1ac532ea2efcfdfdba45

See more details on using hashes here.

Provenance

The following attestation bundles were made for persian_llm_reference-0.3.1-py3-none-any.whl:

Publisher: publish-pypi.yml on sinakazemnezhad/persian-llm-reference

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page