air-gapped/skills · .claude/skills/transformers-config-tokenizers-expert/SKILL.md

transformers-config-tokenizers-expert skillA

transformers-config-tokenizers-expert is agent-read markdown (skill) from air-gapped/skills: Preflight reference for HuggingFace snapshots — what vLLM, sglang, and transformers.generate see at runtime. Covers config-file precedence (tokenizer.json, tokenizer_config.json, generation_config.json, chat_template.jinja), transformers v5 tokenizer-class taxonomy (TokenizersBackend, PythonBackend, MistralCommonBackend, TikTokenTokenizer), special-token discovery (all_special_ids, added_tokens_decoder, extra_special_tokens, backend_tokenizer.get_added_tokens_decoder), chat-template Jinja contra.

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

How to install

Latest version
mdr add air-gapped/skills/transformers-config-tokenizers-expert@git:20260915.e6eb5e8
Exact content
mdr add air-gapped/skills/transformers-config-tokenizers-expert@sha256:e2889dce9248f05b

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_a735x5hok4gsfjev.svg)](https://markdownregistry.com/a/art_a735x5hok4gsfjev)

0 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260915.e6eb5e8 latest2026-09-15 e6eb5e8 23,199 BA view · diff
git:20260915.517712e2026-09-15 517712e 22,273 BA view · diff
git:20260915.223ba3a2026-09-15 223ba3a 21,191 BA view · diff
git:20260426.f30be1c2026-04-26 f30be1c 19,142 BA view · diff
git:20260421.9da35842026-04-21 9da3584 17,833 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (23199 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

air-gapped/skills · 5 stars · license MIT · pushed 2026-09-15 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_a735x5hok4gsfjev
GET https://markdownregistry.com/api/v1/resolve?ref=air-gapped/skills/transformers-config-tokenizers-expert
GET https://markdownregistry.com/api/v1/blob/e2889dce9248f05bc0e26fbfe523752837267c3ed6df39b6307262538694f319