huggingface-llm-trainer SKILL.md skillA
huggingface-llm-trainer from metaspartan/cybara is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add metaspartan/cybara/huggingface-llm-trainer@git:20260730.e75ee1aPins git:20260730.e75ee1a in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- metaspartan/cybara
- Path
plugins/huggingface-workflows/skills/huggingface-llm-trainer/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260730.e75ee1a, committed Jul 30, 2026
- Size
- 2,220 bytes
- Repository stars
- 32
- License
- MIT
Design and run reproducible LLM fine-tuning with TRL, PEFT, Hugging Face Jobs, validated datasets, experiment tracking, and durable Hub outputs.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Hugging Face LLM Trainer Use TRL and PEFT for supervised fine-tuning, preference optimization, reinforcement learning, and reward modeling. Use Hugging Face Jobs when remote compute is requested. ## Method selection - SFT: instruction, conversation, or prompt-completion demonstrations - DPO: prompt with chosen and rejected responses - GRPO: prompts with deterministic, testable reward functions or environments - Reward modeling: examples labeled or ranked for preference quality Do not choose a method from the dataset name alone. Inspect the schema and sample records first with `huggingface-datasets`. ## Training plan 1. Record the base model ID and immutable revision, license, architecture, context length, tokenizer, and chat template. 2. Validate train and evaluation splits, field mapping, length distribution, duplication, contamination risk, and redaction. 3. Select full fine-tuning or PEFT from model size, hardware, memory, and deployment needs. 4. Pin dependencies in a self-contained UV script. 5. Seed data splitting and training, log the complete configuration, and define evaluation criteria before launch. …
Read the whole file at its exact version.
How to install
mdr add metaspartan/cybara/huggingface-llm-trainer@sha256:20b53f6a9e1e2bf0The line at the top of this page pins the label git:20260730.e75ee1a, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_q5u3zvt44bvfrajz)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Jul 30, 2026.
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 (2220 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
metaspartan/cybara · 32 stars · license MIT · pushed 2026-10-20 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_q5u3zvt44bvfrajz GET https://markdownregistry.com/api/v1/resolve?ref=metaspartan/cybara/huggingface-llm-trainer GET https://markdownregistry.com/api/v1/blob/20b53f6a9e1e2bf074bde26b7a1ec215204a53440bf9478da9d5d96aed4b52b1
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.