New Encoders for German Trained from Scratch: Comparing ModernGBERT with Converted LLM2Vec Models

Documenti analoghi

• LLäMmlein: Transparent, Compact and Competitive German-Only Language Models from Scratch
  di: Pfister, Jan, et al.
  Pubblicazione: (2024)
• Historical German Text Normalization Using Type- and Token-Based Language Modeling
  di: Ehrmanntraut, Anton
  Pubblicazione: (2024)
• LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders
  di: BehnamGhader, Parishad, et al.
  Pubblicazione: (2024)
• Conan-Embedding-v2: Training an LLM from Scratch for Text Embeddings
  di: Li, Shiyu, et al.
  Pubblicazione: (2025)
• A Comparative Analysis of Bilingual and Trilingual Wav2Vec Models for Automatic Speech Recognition in Multilingual Oral History Archives
  di: Lehečka, Jan, et al.
  Pubblicazione: (2024)