AI NEWS.ccLFM2.5-Encoder-230M
**LFM2.5-Encoder** is a family of multilingual bidirectional encoders built on the LFM2 architecture, available in two sizes: Both are masked language models with full bidirectional attention, designed to be fine-tuned into task-specific models (classification, token classification, retrieval, reranking, and semantic similarity) across 15 languages, and to run efficiently on-device. > [!NOTE] > π» **Demos**: We built the demos below from fine-tuned LFM2.5-Encoders. Each one runs in a CPU-only Hugging Face space: > - **Zero-shot prompt routing** β define your own routing lanes as free text. The model scores the whole prompt against every lane in one pass. > - **Zero-shot policy linting** β check text against your company's rules, written as free text. It scores every token against every rule in one pass. > - **Spell checking** β correct misspellings token by token. > - **PII detection** β spot and remove 40 kinds of personal information across 16 languages. > - **Masked-diffusion text generation** β bonus: run the encoder as a chatbot that generates text by iteratively unmasking instead of left to right.
**LFM2.5-Encoder** is a family of multilingual bidirectional encoders built on the LFM2 architecture, available in two sizes: Both are masked language models with full bidirectional attention, designed to be fine-tuned into task-specific models (classification, token classification, retrieval, reranking, and semantic similarity) across 15 languages, and to run efficiently on-device. > [!NOTE] > π» **Demos**: We built the demos below from fine-tuned LFM2.5-Encoders. Each one runs in a CPU-only Hugging Face space: > - **Zero-shot prompt routing** β define your own routing lanes as free text. The model scores the whole prompt against every lane in one pass. > - **Zero-shot policy linting** β check text against your company's rules, written as free text. It scores every token against every rule in one pass. > - **Spell checking** β correct misspellings token by token. > - **PII detection** β spot and remove 40 kinds of personal information across 16 languages. > - **Masked-diffusion text generation** β bonus: run the encoder as a chatbot that generates text by iteratively unmasking instead of left to right.