lmms-eval-guide

Official

Navigate LMMs-Eval codebase

AuthorEvolvingLMMs-Lab
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill provides a comprehensive guide to understanding and interacting with the lmms-eval codebase, a powerful framework for evaluating Large Multimodal Models (LMMs). It simplifies complex workflows for developers and researchers.

Core Features & Use Cases

  • Codebase Navigation: Understand the architecture and key components of lmms-eval.
  • Workflow Guidance: Get step-by-step instructions for common tasks like adding models, tasks, or running evaluations.
  • Debugging Assistance: Learn how to systematically debug pipeline failures.
  • Use Case: A researcher wants to integrate a new LMM into lmms-eval. They can use this Skill to find the correct files for model backend implementation, understand the registration process, and learn how to run a smoke test to verify their integration.

Quick Start

Use the lmms-eval-guide skill to understand how to add a new model backend to the lmms-eval codebase.

Dependency Matrix

Required Modules

None required

Components

references

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: lmms-eval-guide
Download link: https://github.com/EvolvingLMMs-Lab/lmms-eval/archive/main.zip#lmms-eval-guide

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.