new-model

Name: new-model
Availability: InStock
Author: Invergent

Scaffold Surogate DSL blocks and HuggingFace weight mappings for new model architectures.

807|6|Updated Jan 2, 2026

Search Tags:#nlp #pytorch #dsl #huggingface #model-architecture #hf-mapping #block-definition

Ready to run

npx skills add https://github.com/invergent-ai/surogate --skill new-model

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: new-model
Source: https://github.com/invergent-ai/surogate/tree/main/.claude/skills/new-model
Command: npx skills add https://github.com/invergent-ai/surogate --skill new-model

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This capability enables teams to add support for new HuggingFace models by scaffolding the required DSL components: a transformer block, a model wrapper, and the corresponding HF weight mappings.

Core Features & Use Cases

Scaffold a new DSL block, model, and HF mappings for a target architecture.
Map HuggingFace config fields to Surogate DSL parameters and integrate with existing modules.
Use case: integrate Gemma2 or DeepSeek backbones into a production-ready training workflow with minimal boilerplate.

Quick Start

Provide the model name or HF repo and the DSL will scaffold the block, model, and HF mappings for a new architecture.

Frequently Asked Questions about new-model

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

FAQPage Schema

How do I add a new HuggingFace model architecture to a training workflow?▼

To add a new HuggingFace model architecture, you scaffold the required transformer block, model wrapper, and HF weight mappings. This ensures proper block structure and configuration alignment with HF config fields for production-ready training.

What is the best way to map HuggingFace config fields to DSL parameters?▼

Mapping HuggingFace config fields to DSL parameters involves generating corresponding block definitions and weight mappings for the target architecture. This automates configuration alignment and integrates the new model with existing modules.

Can I integrate custom HuggingFace backbones like Gemma2 or DeepSeek with minimal boilerplate?▼

Yes, you can integrate custom HuggingFace backbones like Gemma2 or DeepSeek with minimal boilerplate. Providing the model name or HF repo scaffolds the block, model, and HF mappings for the new architecture.

Does adding new model support require manual block definition and weight mapping?▼

Adding new model support does not require manual block definition and weight mapping. The process automates the creation of the DSL block, model wrapper, and HF weight mappings directly from the provided HuggingFace repo.

What components are scaffolded when integrating a new model architecture into a DSL?▼

When integrating a new model architecture into a DSL, the scaffolded components include a transformer block, a model wrapper, and the corresponding HuggingFace weight mappings to ensure proper structural and configuration alignment.