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

← Catalog

GritLM/GritLM-7B

Open comparison →

Primitive: /encode · Encode · Mistral

> GritLM is a generative representational instruction tuned language model. It unifies text representation (embedding) and text generation into a single model achieving state-of-the-art performance on both types of tasks.

Dense

Overview

Hardware: — drives latency, throughput & cost

Size7.2B params
Tasks /encode
Licenseapache-2.0
Latency2.1 s
Throughput1.4K tok/s
Cost$0.157 /1M tok

Cost is approximate — computed from list GPU prices; your actual price depends on the provider you deploy SIE with.

Embedding

Output typesDense
Dimensionsdense: 4,096
Max sequence length4,096
Inputstext

Benchmarks

CQADupstackPhysicsRetrieval

scientific retrieval en

Duplicate question retrieval from StackExchange Physics

Corpus: 38,314 Queries: 1,039
Quality
ndcg at 10 0.2370
map at 10 0.1956
mrr at 10 0.2401
Reference →

CosQA

technology retrieval en

Code search with natural language queries

Corpus: 6,267 Queries: 500
Quality
ndcg at 10 0.1024
map at 10 0.0726
mrr at 10 0.0732
Reference →

FiQA2018

finance retrieval en

Financial opinion mining and question answering

Corpus: 57,599 Queries: 648
Quality
ndcg at 10 0.4555
map at 10 0.3762
mrr at 10 0.5233
Reference →

LegalBenchConsumerContractsQA

legal retrieval en

Question answering on consumer contracts

Corpus: 153 Queries: 396
Quality
ndcg at 10 0.6075
map at 10 0.5338
mrr at 10 0.5338
Reference →

NFCorpus

medical retrieval en

Biomedical literature search from NutritionFacts.org

Corpus: 3,593 Queries: 323
Quality
ndcg at 10 0.3452
map at 10 0.1293
mrr at 10 0.5618
Performance L4 b1 c16
Corpus 1.7K tok/s
Corpus p50 2.7s
Query 312 tok/s
Query p50 206.2ms
Reference →

NanoFiQA2018Retrieval

finance retrieval en

Smaller subset of the FiQA financial QA dataset

Quality
ndcg at 10 0.6289
map at 10 0.5506
mrr at 10 0.6275
Performance L4 b1 c16
Corpus 1.1K tok/s
Corpus p50 1.6s
Query 556 tok/s
Query p50 196.8ms
Reference →

SCIDOCS

scientific retrieval en

Citation prediction, document classification, and recommendation for scientific papers

Corpus: 25,656 Queries: 1,000
Quality
ndcg at 10 0.1843
map at 10 0.1064
mrr at 10 0.3150
Reference →

SciFact

scientific retrieval en

Scientific claim verification using research literature

Corpus: 5,183 Queries: 300
Quality
ndcg at 10 0.7042
map at 10 0.6556
mrr at 10 0.6662
Reference →

Open source inference for agents

Open-source inference for the models behind your agents. Run it yourself, or let us run it for you.

Github 3.3K

Contact us

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

Apply for an inference grant

Free capacity on our hosted cluster for selected projects. Tell us what you run and we reply by email.