finetuning SKILL.md skillA
finetuning from ericrisco/rsc-harness is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add ericrisco/rsc-harness/finetuning@git:20260729.9b4d66aPins git:20260729.9b4d66a in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- ericrisco/rsc-harness
- Path
skills/finetuning/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260729.9b4d66a, committed Jul 29, 2026
- First version recorded
- Jul 18, 2026
- Size
- 15,188 bytes
- Repository stars
- 236
- License
- MIT
Use when adapting an open-weight model to a target form or behavior — tone, output format, reasoning pattern — via LoRA/QLoRA or full fine-tuning with TRL SFTTrainer, then preference optimization (DPO/ORPO/KTO/GRPO), and for fine-tune vs prompt vs RAG. NOT adding facts to a model (that is rag); NOT the single-GPU Unsloth backend or GGUF export (that is unsloth).
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
# finetuning — teach an open model a form or behavior, not a fact You own the discipline of **adapting an open-weight model**: deciding whether to fine-tune at all, then running SFT and (optionally) preference optimization with `trl` + `peft`, backend-agnostic. You are judged by whether the tuned model reliably produces the target **form/behavior** on a held-out set — not by train loss, and not by vibes. The one sentence that routes half of all "should I fine-tune?" questions correctly: **fine-tuning teaches *form and behavior*; RAG supplies *facts*.** If the ask is "know our latest prices / docs / tickets," that is retrieval (`../rag/SKILL.md`), not training. If the ask is "sound like us, always emit this JSON, follow this reasoning pattern," that is here. ## Decision gate — try this BEFORE reaching for a GPU Fine-tuning is the last lever, not the first. Exhaust the cheaper, reversible options first; each row below is a real off-ramp. | If the goal is… | Do this first | Fine-tune only when… | |---|---|---| | The model should *know* current/company facts | **RAG** (`../rag/SKILL.md`) — retrieve + ground | never for facts; facts go stale, weights don't update | …
Read the whole file at its exact version.
How to install
mdr add ericrisco/rsc-harness/finetuning@sha256:715a71d7b2aaeeebThe line at the top of this page pins the label git:20260729.9b4d66a, 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_lv3kl64oesmfvimx)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Jul 18, 2026 and Jul 29, 2026, about one every 11 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260729.9b4d66a latest | 2026-07-29 | 9b4d66a | 15,188 B | A | view · diff |
| git:20260718.2408919 | 2026-07-18 | 2408919 | 16,615 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 (15188 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
ericrisco/rsc-harness · 236 stars · license MIT · pushed 2026-10-21 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_lv3kl64oesmfvimx GET https://markdownregistry.com/api/v1/resolve?ref=ericrisco/rsc-harness/finetuning GET https://markdownregistry.com/api/v1/blob/715a71d7b2aaeeeb71b25b72e2aef2fd59bb292dc1007cac53c8706a51f22de0
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.
More from ericrisco/rsc-harness
Every file in ericrisco/rsc-harness