Seq vs Seq: the Ettin Suite of Paired Encoders and Decoders
#LLM #ML #AI_NEWS
via Hugging Face - Blog
#LLM #ML #AI_NEWS
via Hugging Face - Blog
huggingface.co
Ettin Suite: SoTA Paired Encoders and Decoders
Published July 16, 2025 Update on GitHub What would happen if you took the ModernBERT recipe and applied it to a decoder-only model? Turns out, a state-of-the-art decoder language model that beats…
TimeScope: How Long Can Your Video Large Multimodal Model Go?
#LLM #ML #AI_NEWS
via Hugging Face - Blog
#LLM #ML #AI_NEWS
via Hugging Face - Blog
huggingface.co
TimeScope: How Long Can Your Video Large Multimodal Model Go?
Published July 23, 2025 Update on GitHub TimeScope is an open-source benchmark designed to measure how well vision-language models understand long videos. By adding short “needle” clips into videos…