skills.rest
Rachasumanth
RachasumanthCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

model-architect

Designs transformer architectures and emits Hugging Face-compatible config.json files.

Updated Feb 17, 2026
Search Tags:#architecture#llm#transformer#config.json#hugging face#model design
One-click install
npx skills add https://github.com/Rachasumanth/text2llm001 --skill model-architect
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: model-architect
Source: https://github.com/Rachasumanth/text2llm001/tree/main/workspace/skills/model-architect
Command: npx skills add https://github.com/Rachasumanth/text2llm001 --skill model-architect

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill assists in designing transformer model architectures from scratch, ensuring the generated configurations align with specific computational, memory, and quality objectives.

Core Features & Use Cases

  • Architecture Design: Generates Hugging Face Transformers-compatible config.json files for decoder-only transformer models.
  • Scale Templates: Provides predefined architecture templates for various model scales (100M to 7B+ parameters).
  • Component Selection: Recommends modern defaults like GQA, SwiGLU, RoPE, and RMSNorm, with explanations for deviations.
  • Parameter & Memory Estimation: Calculates total parameters, optimizer state memory, activation memory, and checkpoint sizes.
  • Tokenizer Integration: Validates and integrates tokenizer configurations (vocab size, special tokens) for seamless training.
  • Use Case: A researcher needs to design a new LLM architecture for a specific research goal and budget. This skill helps them define the model's layers, hidden size, attention heads, and other parameters, providing a ready-to-use configuration file and detailed reports on its resource implications.

Quick Start

Use the model-architect skill to design a 1B class transformer model architecture.

Frequently Asked Questions about model-architect

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I integrate tokenizer configurations into a transformer model design?▼

To integrate tokenizer configurations into a transformer model design, this Skill validates and incorporates vocabulary size and special tokens directly into the generated Hugging Face configuration for seamless training.

How do I integrate tokenizer configurations into a transformer model design?▼

To integrate tokenizer configurations into a transformer model design, this Skill validates and incorporates vocabulary size and special tokens directly into the generated Hugging Face configuration for seamless training.

How do I integrate tokenizer configurations into a transformer model design?▼

To integrate tokenizer configurations into a transformer model design, this Skill validates and incorporates vocabulary size and special tokens directly into the generated Hugging Face configuration for seamless training.

How do I integrate tokenizer configurations into a transformer model design?▼

To integrate tokenizer configurations into a transformer model design, this Skill validates and incorporates vocabulary size and special tokens directly into the generated Hugging Face configuration for seamless training.

How do I integrate tokenizer configurations into a transformer model design?▼

To integrate tokenizer configurations into a transformer model design, this Skill validates and incorporates vocabulary size and special tokens directly into the generated Hugging Face configuration for seamless training.

Related Skills

Explore More Software Engineering Skills→
AgriciDanielAgriciDaniel
7.9k

ads-plan

Generate strategic paid advertising plans from business objectives, audiences, and budgets.

Community
Advanced
huggingfacehuggingface
10.9k

huggingface-vision-trainer

Automate vision model training and fine-tuning on Hugging Face Jobs.

Official
Advanced
sheawinklersheawinkler
78

huggingface-tokenizers

Train BPE, WordPiece, and Unigram tokenizers with Rust performance.

Community
Advanced
CHENyiru3CHENyiru3

transformers

Fine-tune and deploy Hugging Face transformer models for NLP tasks.

Community
Advanced