Why did we open-source our inference engine? Read the post

Salesforce/SFR-Embedding-Mistral

Salesforce/SFR-Embedding-Mistral

Overview

Architecture
Mistral
Parameters
7.1B
Tasks
Encode
Outputs
Dense
Dimensions
Dense: 4,096
Max Sequence Length
4,096 tokens
License
cc-by-nc-4.0
Languages
en

Benchmarks

NFCorpus

medical retrieval en

Biomedical literature search from NutritionFacts.org

Corpus: 3,593 Queries: 323
Quality
ndcg at 10 0.4085
map at 10 0.1569
mrr at 10 0.6199
Performance L4 b1 c16
Corpus 3.1K tok/s
Corpus p50 1.1s
Query 211 tok/s
Query p50 232.1ms
Reference →

NanoFiQA2018Retrieval

finance retrieval en

Smaller subset of the FiQA financial QA dataset

Quality
ndcg at 10 0.6164
map at 10 0.5492
mrr at 10 0.6472
Performance L4 b1 c16
Corpus 2.9K tok/s
Corpus p50 673.6ms
Query 466 tok/s
Query p50 227.6ms
Reference →

Self-hosted inference for search & document processing

Cut API costs by 50x, boost quality with 85+ SOTA models, and keep your data in your own cloud.

Github 2.0K

Contact us

Tell us about your use case and we'll get back to you shortly.