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

← Catalog

facebook/bart-large-mnli

Open comparison →

Primitive: /extract · Extract · bart

This is the checkpoint for bart-large after being trained on the MultiNLI (MNLI) dataset.

Entities

Overview

Hardware: — drives latency, throughput & cost

Size407M params
Tasks /extract
Licensemit
Latency
Throughput
Cost /1M tok

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

Extraction

Output kindsEntities
Inputstext
Max sequence length512

Benchmarks

AG News

news classification en

Topic classification of news articles into world, sports, business, and sci/tech categories

Corpus: 7,600 Queries: 7,600
Quality
accuracy 0.6712
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 2.1K

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.