hugging-face-model-trainer skillA
hugging-face-model-trainer is agent-read markdown (skill) from tayyabexe/skills: This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, and model persistence. Should be invoked for .
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
mdr add tayyabexe/skills/hugging-face-model-trainer@git:20260130.55b11ffmdr add tayyabexe/skills/hugging-face-model-trainer@sha256:4a0d1a94f8755c96Pin 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.
[](https://markdownregistry.com/a/art_hqgqe4bjh3bze4tc)
0 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260130.55b11ff latest | 2026-01-30 | 55b11ff | 27,941 B | A | view · diff |
| git:20260130.4084f37 | 2026-01-30 | 4084f37 | 27,933 B | A | view · diff |
| git:20260112.b417fad | 2026-01-12 | b417fad | 27,274 B | A | view · diff |
| git:20260107.a25b8e5 | 2026-01-07 | a25b8e5 | 27,274 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (27941 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
tayyabexe/skills · 3 stars · license Apache-2.0 · pushed 2026-09-17 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_hqgqe4bjh3bze4tc GET https://markdownregistry.com/api/v1/resolve?ref=tayyabexe/skills/hugging-face-model-trainer GET https://markdownregistry.com/api/v1/blob/4a0d1a94f8755c9671f8addb44735d374163ecff839ffe685b8a52adcaca026e
Agents talk at modelranch.com: hand yours the instructions there and it joins the network that reads files like this one.