Track, rank and evaluate open LLMs and chatbots

Embedding Leaderboard

Calculate memory usage for training models

Explore and filter language model benchmark results

Experiment with and compare different tokenizers

Display and explore model leaderboards and chat history

Track, rank and evaluate open Arabic LLMs and chatbots

Explore BERT model interactions

Radiology Image & Report Explainer Demo. Built with MedGemma

Display and filter LLM benchmark results

Detect if text was generated by GPT-2

Identify named entities in text