Gemma-2-2B
PulseAugur coverage of Gemma-2-2B — every cluster mentioning Gemma-2-2B across labs, papers, and developer communities, ranked by signal.
1 天有情绪数据
-
LLM analysis method reveals training data secrets and ethical risks
Researchers have developed a method using singular value decomposition (SVD) of a large language model's weight matrix to reveal interpretable semantic subspaces. This technique, requiring minimal code and no model infe…
-
CorrSteer 方法利用相关稀疏自编码器特征增强 LLM 引导
研究人员开发了 CorrSteer，一种在生成过程中使用从稀疏自编码器 (SAE) 提取的特征来引导大型语言模型 (LLM) 的新颖方法。该技术在推理时将样本正确性与 SAE 激活相关联，无需大型数据集或广泛的激活存储。CorrSteer 在各种基准测试中展示了显著的性能提升，包括问答、偏见缓解和推理任务，在 MMLU 和 HarmBench 中取得了显著的进步。
-
DB-KSVD algorithm offers scalable approach to disentangling high-dimensional embedding spaces
Researchers have introduced DB-KSVD, a novel dictionary learning algorithm designed to disentangle high-dimensional embedding spaces in large transformer models. This method adapts the classic KSVD algorithm to scale ef…
-
LLM jailbreaks linked to mid-to-late layer feature vulnerabilities
Researchers have developed a method to identify specific internal features within large language models that contribute to their vulnerability to jailbreaking attacks. By analyzing the Gemma-2-2B model using the BeaverT…
-
Google releases Gemma 2 2B, ShieldGemma, and Gemma Scope
Google has announced updates to its Gemma family of models, including the release of Gemma 2 2B. This new iteration is designed for efficiency and accessibility, aiming to empower developers with powerful yet lightweigh…
-
Google unveils Simula and CTCL for advanced synthetic data generation
Google Research has introduced Simula, a framework that treats synthetic data generation as a mechanism design problem. This approach allows for fine-grained control over dataset characteristics like coverage, complexit…
-
Google DeepMind发布T5Gemma编码器-解码器LLM，改编自Gemma
Google DeepMind推出了T5Gemma，这是一个新的编码器-解码器大型语言模型系列，源自其现有的Gemma 2模型。这种改编技术允许灵活组合编码器和解码器的大小，从而在模型质量和推理效率之间取得更好的平衡。实验表明，T5Gemma模型在各种基准测试中的表现与同类仅解码器的Gemma模型相当或更优，在数学推理和阅读理解等任务中提供了显著的速度和准确性优势。