embeddinggemma-2:270m-bf16-text

4 12 hours ago

EmbeddingGemma 2 is a multimodal embedding model from Google built on the Gemma 4 architecture.

vision embedding audio 270m 440m 570m 740m
... /
json
031e56a498d3 · 1.6kB
{
"__version__": {
"pytorch": "2.14.0+cu130",
"sentence_transformers": "6.1.0",
"transformers": "5.18.0.dev0"
},
"default_prompt_name": null,
"model_type": "SentenceTransformer",
"prompts": {
"BitextMining": "task: search result | query: ",
"Classification": "task: classification | query: ",
"Clustering": "task: clustering | query: ",
"CodeRetrieval": "task: code retrieval | query: ",
"Document": "title: none | text: ",
"FactChecking": "task: fact checking | query: ",
"InstructionRetrieval": "task: code retrieval | query: ",
"MultilabelClassification": "task: classification | query: ",
"PairClassification": "task: sentence similarity | query: ",
"QuestionAnswering": "task: question answering | query: ",
"Reranking": "task: search result | query: ",
"Retrieval": "task: search result | query: ",
"Retrieval-document": "title: none | text: ",
"Retrieval-query": "task: search result | query: ",
"STS": "task: sentence similarity | query: ",
"SearchQuery": "task: search result | query: ",
"SentenceSimilarity": "task: sentence similarity | query: ",
"Summarization": "task: sentence similarity | query: ",
"document": "title: none | text: ",
"query": "task: search result | query: "
},
"requirements": {
"sentence-transformers": {
"reason": "Older versions ignore the order of multimodal dict inputs and cannot put several images or texts into a single embedding.",
"specifier": ">=6.1.0"
}
},
"similarity_fn_name": "cosine"
}