Post
1004
New static multilingual retrieval embedding model: amgix/static-retrieval-multilingual-69m-v1
Distilled from ibm-granite/granite-embedding-97m-multilingual-r2 via Model2Vec. Built this because I couldn't find a static model that was both multilingual and trained for retrieval, existing options are one or the other.
Faster than the leading static models, and scores higher on average across RTEB and NanoBEIR multilingual benchmarks.
Full benchmark tables and training details on the card. Feedback welcome, especially from anyone with a real multilingual retrieval workload.
Distilled from ibm-granite/granite-embedding-97m-multilingual-r2 via Model2Vec. Built this because I couldn't find a static model that was both multilingual and trained for retrieval, existing options are one or the other.
Faster than the leading static models, and scores higher on average across RTEB and NanoBEIR multilingual benchmarks.
Full benchmark tables and training details on the card. Feedback welcome, especially from anyone with a real multilingual retrieval workload.