Display leaderboard for earthquake intent classification models
Export Hugging Face models to ONNX
Evaluate LLM over-refusal rates with OR-Bench
Multilingual Text Embedding Model Pruner
Evaluate open LLMs in the languages of LATAM and Spain.
Browse and submit model evaluations in LLM benchmarks
Benchmark AI models by comparison
Create and upload a Hugging Face model card
Display benchmark results
Upload a machine learning model to Hugging Face Hub
Retrain models for new data at edge devices
Display leaderboard of language model evaluations
Calculate GPU requirements for running LLMs
Intent Leaderboard V12 is a specialized tool designed for benchmarking and comparing earthquake intent classification models. It provides a comprehensive platform to evaluate and rank the performance of different models, helping researchers and developers identify top-performing solutions.
• Leaderboard Display: Visualizes the performance of earthquake intent classification models in a ranked format.
• Performance Tracking: Monitors the accuracy and effectiveness of models over time.
• Comparison Tools: Enables side-by-side comparison of model performance metrics.
• Real-Time Updates: Reflects the latest improvements and updates in model benchmarking.
• Detailed Metrics: Provides in-depth insights into model strengths and weaknesses.
What is Intent Leaderboard V12 used for?
Intent Leaderboard V12 is used to benchmark and compare earthquake intent classification models, helping users identify the best-performing models for their applications.
How are models evaluated on the leaderboard?
Models are evaluated based on their accuracy, precision, recall, and other relevant metrics for earthquake intent classification tasks.
Can I use Intent Leaderboard V12 for real-time data?
Yes, Intent Leaderboard V12 supports real-time updates, allowing users to evaluate models with the most current data available.