Tofu Leaderboard

Visit Tool

Tofu Leaderboard is an AI application that allows users to browse and search unlearning performance data for large language models. It enables submission of new evaluation results for models like Llama and Phi.

Claim this tool

2Views

At a glance

Pricing

Likely Free

Free tier

Yes

API

Skill level

Technical

Product Hunt

About

What is Tofu Leaderboard?

Tofu Leaderboard is a specialized AI application hosted on Hugging Face Spaces, designed for researchers and developers working with large language models (LLMs). It provides a platform to browse and search comprehensive unlearning performance data, offering insights into how effectively LLMs can forget specific information. Users can also contribute by submitting new evaluation results for various models, including popular ones like Llama and Phi. This tool serves as a central repository for tracking and comparing the unlearning capabilities of different LLMs, fostering advancements in model safety and ethical AI development.

Best used for

Ideal for data scientists and developers who need to analyze the unlearning performance of large language models, compare different model evaluations, and contribute new research results. Especially valuable for those focused on ethical AI, model safety, and understanding how LLMs forget information.

Common actions

analyze LLM performance

compare AI models

evaluate unlearning capabilities

contribute research data

AI chatbotsTask automationContent generationAutomationfun toolsEducationai

Capabilities

Key features

Browse unlearning performance data
Search unlearning performance data
Submit new evaluation results
Supports Llama models
Supports Phi models

Target Audience

data scientistdeveloper

Integrations

Not yet documented

Pricing & Plans

Likely Free

Free

FAQs

What kind of data can I find on the Tofu Leaderboard?

The Tofu Leaderboard provides unlearning performance data for large language models. This includes metrics and results related to how effectively models like Llama and Phi can remove or forget specific information they were trained on.

Can I submit my own evaluation results to the Tofu Leaderboard?

Yes, the Tofu Leaderboard allows users to submit new evaluation results for various large language models. This feature helps expand the dataset and provides a broader comparison of unlearning capabilities across different models.

Which large language models are supported for evaluation on the Tofu Leaderboard?

The Tofu Leaderboard supports evaluation results for a range of large language models, including popular ones like Llama and Phi. The platform aims to be inclusive of various LLMs to provide comprehensive comparative data.

Trending

Subcategories trending in AI Agents & Automation

AI Frameworks & Infra General-Purpose Agents Workflow Agents Personal Assistants RAG & Document AI Voice Agents

Trending

Explore

Browse AI tools by category

Content & Design Productivity & Business Coding & Development AI Agents & Automation Research & Education Wellness & Lifestyle Career Development Marketing & Growth Data & Analytics Customer Support & CX Finance E-commerce