MameLoshnLM: Yiddish Language Model and Evaluation Benchmark

  • 类型:arxiv
  • 标识:2608.05850
  • 链接:https://arxiv.org/abs/2608.05850
  • 主分类:evaluation
  • 形态:benchmark
  • 被引:0
  • 被引来源:Semantic Scholar
  • S2被引:0
  • 影响力被引:0
  • TLDR:MameLoshnLM, the first open-source 8B-parameter language model built specifically for Yiddish, is presented, providing both a foundation for Yiddish NLP and a practical template for language model development in historically rich but digitally underrepresented languages.
  • 待LLM分类:否
  • 标题中文:MameLoshnLM:意第绪语语言模型与评估基准
  • TLDR中文:MameLoshnLM 是首个专为意第绪语构建的 8B 参数开源语言模型,既为意第绪语 NLP 提供基础,也为历史悠久但数字化程度不足的语言建模开发提供可复用的实践模板。
  • 来源文件
  • /inbox/tom/_candidates/2026-08-07-agent-rag-longcontext-candidates.json
  • /inbox/tom/_candidates/2026-08-08-agent-rag-longcontext-candidates.json
  • /inbox/tom/_candidates/2026-08-09-agent-rag-longcontext-candidates.json
  • /inbox/tom/_candidates/2026-08-10-agent-rag-longcontext-candidates.json
  • /inbox/tom/_candidates/2026-08-10-agent-memory-tool-use-candidates.json
  • [S2 enrich]