Toolverse
All skills

implementing-llms-litgpt

by davila7

Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational understanding of architectures, or production fine-tuning with LoRA/QLoRA. Single-file

Installation

Pick a client and clone the repository into its skills directory.

Installation

Quick info

Author
davila7
Category
Security

About this skill

Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational understanding of architectures, or production fine-tuning with LoRA/QLoRA. Single-file implementations, no abstraction layers.

How to use

  1. Zainstaluj LitGPT za pomocą pip install 'litgpt[extra]' – to przygotuje wszystkie wymagane zależności (torch, transformers).

  2. Pobierz wybrany model pretrenowany, na przykład Phi-2 poleceniem litgpt download microsoft/phi-2 lub Llama 3 8B poleceniem litgpt download meta-llama/Meta-Llama-3-8B. Modele zapisują się w katalogu checkpoints/.

  3. Załaduj model w kodzie Pythona: from litgpt import LLM, następnie llm = LLM.load("microsoft/phi-2") – zastąp ścieżką do pobranego modelu.

  4. Generuj tekst za pomocą metody generate() – podaj prompt, ustaw max_new_tokens (liczba tokenów do wygenerowania) i temperature (kontrola losowości odpowiedzi).

  5. Aby dostosować model do swoich danych, przygotuj dataset w formacie Alpaca (instrukcja, input, output jako JSON) lub innym obsługiwanym formacie, a następnie uruchom fine-tuning za pomocą dostępnych skryptów treningowych z LitGPT.

  6. Sprawdź dostępne modele poleceniem litgpt download list – zobaczysz pełną listę 20+ architektur, które możesz pobrać i użyć.

Related skills

qmd

by tobi

Search personal markdown knowledge bases, notes, meeting transcripts, and documentation using QMD - a local hybrid search engine. Combines BM25 keyword search, vector semantic search, and LLM re-ranking. Use when users ask to search notes, find documents, look up information in

Security
1951

reviewing-code

by CaptainCrouton89

Systematically evaluate code changes for security, correctness, performance, and spec alignment. Use when reviewing PRs, assessing code quality, or verifying implementation against requirements.

Security
1493

senior-security

by davila7

Comprehensive security engineering skill for application security, penetration testing, security architecture, and compliance auditing. Includes security assessment tools, threat modeling, crypto implementation, and security automation. Use when designing security architecture,

Security
2482

content-creator

by alirezarezvani

Create SEO-optimized marketing content with consistent brand voice. Includes brand voice analyzer, SEO optimizer, content frameworks, and social media templates. Use when writing blog posts, creating social media content, analyzing brand voice, optimizing SEO, planning content

Security
25124

reverse-engineering-tools

by gmh5225

Guide for reverse engineering tools and techniques used in game security research. Use this skill when working with debuggers, disassemblers, memory analysis tools, binary analysis, or decompilers for game security research.

Security
3168

youtube-watcher

by openclaw

Fetch and read transcripts from YouTube videos. Use when you need to summarize a video, answer questions about its content, or extract information from it.

Security
2231