Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Sign in
Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

A page, a video or an image online.

Unlock PalateKit

Unlock everything

Plan

Paying means accepting our terms of sale.

Secure payment by Stripe. Receipts and invoices sent by email.

Welcome back

Sign in to install, download or save this resource. A free account is enough for free resources.

LLM development guidelines v1.0.0

Use this resource to design, fine-tune or evaluate a large language model

New

  • 456 downloads
  • 161 likes
  • 245 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install llm-development-best-practices

With no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.

First time: connect the CLI with

npx --yes palatekit@latest login

The agent relies on transformer principles: attention mechanisms, BPE or SentencePiece tokenization, full or parameter-efficient (PEFT) fine-tuning, distributed training, memory optimization and evaluation. You get a coherent training and evaluation plan.

Mostly picked by

Updated November 2, 2026

Card for the “LLM development guidelines” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
Apache-2.0

Similar resources

View all

What you get

  • SKILL.md: architecture and tokenization
  • SKILL.md: fine-tuning, distributed training and evaluation

Good fit for

  • You fine-tune a language model on your data
  • You design a distributed training pipeline

Not for

    Tags

    • LLM
    • fine-tuning
    • transformers
    • evaluation

    About

    You say

    “Propose a LoRA fine-tuning plan for a 7B model on my support data.”

    Card for the “LLM development guidelines” skill

    Skill published by mindrally under the Apache-2.0 license, delivered in its original version.

    Show more

    How to use it

    1. Install the skill in your agent's skills folder
    2. Ask your agent to design, fine-tune or evaluate a large language model
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE11.3 KB
    • NOTICE-PALATEKIT.md0.4 KB
    • SKILL.md2.1 KB

    Origin and licence

    Listed unmodified

    Author
    mindrally
    Source
    github.com/mindrally/skills/tree/7682ca77710e0971eab4e0ae5dddfa281aea0ba5/llm
    Licence
    Apache-2.0

    Notice

    « llm » (mindrally, Apache-2.0) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.

    User reviews

    –

    No ratings yet

    Loading reviews…

    Delete your review?

    Your rating and comment will be removed from the page.