SFR Embedding 2 R

Open WeightModel weights are publicly available — can be downloaded and self-hosted

Released June 202433K context≈ 24,576 words

SFR Embedding 2 R is a focused specialist — it takes text in and produces dense vector representations optimized for semantic similarity and retrieval tasks. Built by Salesforce, it carries a research-oriented lineage, meaning it tends to perform reliably on retrieval-augmented generation pipelines and document search. The non-commercial license keeps it out of production commercial contexts, making it more of a lab and prototyping companion.

Capabilities

Capability scores are AI-generated based on model documentation, benchmarks, and technical specifications. Learn more

Instruction Following

Basic

Multilingual

SFR Embedding 2 R

Open WeightModel weights are publicly available — can be downloaded and self-hosted

Released June 202433K context≈ 24,576 words

SFR Embedding 2 R is a focused specialist — it takes text in and produces dense vector representations optimized for semantic similarity and retrieval tasks. Built by Salesforce, it carries a research-oriented lineage, meaning it tends to perform reliably on retrieval-augmented generation pipelines and document search. The non-commercial license keeps it out of production commercial contexts, making it more of a lab and prototyping companion.

Capabilities

Capability scores are AI-generated based on model documentation, benchmarks, and technical specifications. Learn more

Instruction Following

Basic

Multilingual

Glossary

Dense VectorA compact numerical representation where most values are non-zero, used to efficiently store and compare the meaning of text.EmbeddingA dense numerical vector that represents a word, sentence, or concept in a high-dimensional space.Non-Commercial LicenseA legal restriction that permits using the model for learning and research but prohibits using it in production systems or for commercial purposes.RetrievalThe process of finding and returning relevant documents or information from a database based on a query.Retrieval-AugmentedA technique that enhances AI systems by first searching for relevant information from a database before generating responses, improving accuracy and relevance.Retrieval-Augmented GenerationA technique that allows a model to search and reference external documents or knowledge bases to answer questions more accurately and with citations.Semantic SimilarityA measure of how closely related two pieces of text are in meaning, regardless of whether they use identical words.

Capabilities

Capabilities

Use Case Fit

Glossary