MDL
gemma-2b
Parameters
2B
Downloads
315.5K
on HF
Likes
1.2K
Avg score
—
Weights
Open
Released
Feb 8, 2024
About
gemma-2b is a 2B-parameter open-weights model in the gemma family from google.
gemmatext-generation
Benchmark scores · 0
No benchmark scores yet.
The research behind this model
all papers mentioning it →CommonsenseQA: A Question Answering Challenge Targeting Commonsense KnowledgeCan a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question AnsweringBeyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelsGender Bias in Coreference Resolution: Evaluation and Debiasing MethodsBBQ: A Hand-Built Bias Benchmark for Question AnsweringRealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language ModelsBOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language GenerationGender Bias in Coreference ResolutionTruthfulQA: Measuring How Models Mimic Human FalsehoodsToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech DetectionGemini: A Family of Highly Capable Multimodal ModelsMeasuring Massive Multitask Language UnderstandingHellaSwag: Can a Machine Really Finish Your Sentence?PIQA: Reasoning about Physical Commonsense in Natural LanguageSocialIQA: Commonsense Reasoning about Social InteractionsBoolQ: Exploring the Surprising Difficulty of Natural Yes/No QuestionsWinoGrande: An Adversarial Winograd Schema Challenge at ScaleOn the Measure of IntelligenceTriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading ComprehensionEvaluating Large Language Models Trained on CodeProgram Synthesis with Large Language ModelsTraining Verifiers to Solve Math Word ProblemsAGIEval: A Human-Centric Benchmark for Evaluating Foundation ModelsTransitivity Meets Cyclicity: Explicit Preference Decomposition for Dynamic Large Language Model AlignmentMay 17, 2026
Mentions matched by name in title/abstract — from the arXiv + HF daily corpus.