fine-tune-and-serve SKILL.md skillA
fine-tune-and-serve from westwaters/pollard-weights is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add westwaters/pollard-weights/fine-tune-and-serve@v0.2Pins v0.2 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- westwaters/pollard-weights
- Path
skills/pollard/fine-tune-and-serve/SKILL.md- Versions recorded
- 1
- Latest version
- v0.2, committed Oct 12, 2026
- Size
- 12,130 bytes
- Repository stars
- 33
- License
- Apache-2.0
Fine-tune an open model (Qwen, Llama, ...) on the user's OWN data with Pollard, prove on a held-out set that it beats the base model (and optionally a frontier model), then quantize, card and serve it for an agent harness. Use when asked to "fine-tune X for <task>", "train a model on our data", "make a classifier / reviewer / decision model", or "/fine-tune-and-serve-llm I want to fine-tune Qwen for payments risk review". Covers the data checklist, `pollard tune`, reading the eval, `--ship`…
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
# Fine-tune and serve — agent skill The lane: **data checklist → `pollard tune` (prep → LoRA SFT and/or GRPO → merge) → eval against base (+ frontier) → `--ship` (GGUF ladder + card with the eval) → `pollard serve --harness`**. Everything runs on the user's machine. Rows leave it only if you point `--compare-url` / `--judge-url` at another host, and that needs `--allow-remote`. Why it is built this way (Coinbase, "Owning Intelligence" series, 2026-10): a post-trained Qwen3.5-9B beat Opus 4.5 on their onramp-fraud benchmark (+7.5 precision, +12.0 recall, +9.6 F1, +35.4 dollar-weighted recall; P50 0.683 s vs 1.515 s). What carried it was the **evaluation**: a benchmark built from matured labels, one fixed prompt and decision policy for every model, a metric weighted by what a miss costs, and weights + prompt + policy versioned as one unit. Newer frontier models did *worse* on their benchmark. Only a domain eval shows that, so never skip it. ## STEP 0 — ask the user (unless the prompt already says) 1. **The decision.** What does the model output? A label set (`fraud` / `legit`, `approve` / `review` / …
Read the whole file at its exact version.
How to install
mdr add westwaters/pollard-weights/fine-tune-and-serve@sha256:965db876c30eac21The line at the top of this page pins the label v0.2, 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_uzyzkiqle3t72vbc)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Oct 12, 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 (12130 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
westwaters/pollard-weights · 33 stars · license Apache-2.0 · pushed 2026-11-04 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_uzyzkiqle3t72vbc GET https://markdownregistry.com/api/v1/resolve?ref=westwaters/pollard-weights/fine-tune-and-serve GET https://markdownregistry.com/api/v1/blob/965db876c30eac214f9b8afd5deb016efdaf05eb3b66bd1fff180a3e0d00a0e1
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.