Patronus AI has launched Glider, a new small language model that outperforms GPT-4o-mini in key AI evaluation tasks. Glider, which features 3 billion parameters, is designed as an open-source evaluator model capable of providing both quantitative and qualitative assessments across 183 criteria and 685 domains. The model is available for free, with open weights and code, allowing users to explore its capabilities. The introduction of Glider marks a significant advancement in the field of artificial intelligence, particularly in the area of model evaluation.
Patronus AI Open Sources Glider: A 3B State-of-the-Art Small Language Model (SLM) Judge https://t.co/ZsjDPe9gGw #GliderAI #LLMEvaluation #OpenSourceAI #ArtificialIntelligence #PatronusAI #ai #news #llm #ml #research #ainews #innovation #artificialintelligence #machinelearning… https://t.co/KwqY9J1TUA
Patronus AI Open Sources Glider: A 3B State-of-the-Art Small Language Model (SLM) Judge Patronus AI has introduced Glider, a 3-billion parameter Small Language Model (SLM) designed to meet these needs. Glider is an open-source evaluator model that provides both quantitative and… https://t.co/OlGAMypOXp
Patronus AI releases Glider: a small, high-performance AI evaluator model for other models https://t.co/wCdEwuQQsH