vLLM Compatible TranslateGemma Configuration This is a modified version of google/translategemma 12b it optimized for deployment with vLLM. Changes from Original Model Chat Template The original TranslateGemma model requires a structured payload with dedicated source lang code and target lang code fields: However, vLLM does not support these custom content parameters. To maintain compatibility, the chat template has been modified to encode language codes directly in the message content using a delimiter based format: Format: {source lang} {target lang} {text to translate} If you need to provide a custom prompt input Format: {text} Model Configuration (RoPE) The original model uses the new Transformers RoPE configuration format with separate attention type settings: This has been simplified for vLLM compatibility: Generation Configuration The EOS token has been corrected from to to ensure proper sequence termination. Original readme Resources and Technical Documentation : + Technical Report + Responsible Generative AI Toolkit + TranslateGemma on Kaggle + TranslateGemma on Vertex Model Garden Terms of Use : Terms Authors : Google Translate Model Information Summary description and br…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy