Cohere Command & Embed on Amazon Bedrock

Generative LLMs for enterprises

Benefits

Integrate generative AI capabilities into essential apps and workflows that improve business outcomes.
Data is kept private where customers have complete control over customization and model inputs and outputs.
Models are trained from known, purchased, or public data sources, and subjected to adversarial testing and bias mitigation.

Meet Cohere's Command FM

Command is a text generation model for business use cases.

Use cases

Enables apps like knowledge assistants and customer support chatbots with seamless and dynamic user experiences that maintain conversational context.

Builds articles, product descriptions, and more based on user prompts.

Summarizes key ideas and themes from diverse long-form text, such as news, investor reports, legal, or medical information.

Enables powerful search applications when coupled with a vector database, with excellent relevance based on search phrase meaning.

Finds and retrieves most relevant information from connected enterprise data sources for RAG use cases.

Model version

Command

Command is Cohere’s generative large language model (LLM) (52B parameters).

Max tokens: 4K

Languages: English

Supported use cases: Chat, text generation, text summarization.

Command Light

Command Light is a smaller version of Command, Cohere's generative LLM (6B parameters).

Max tokens: 4K

Languages: English

Supported use cases: Chat, text generation, text summarization.

Embed - English

Embed is Cohere's text representation, or embeddings, model.
This version supports English only.

Dimensions: 1024

Languages: English

Supported use cases: Semantic search, retrieval augmented generation (RAG), classification, clustering.

Embed - Multilingual

Embed is Cohere's text representation, or embeddings, model.
This version supports multiple languages.

Dimensions: 1024

Languages: Multilingual (100+ supported languages)

Supported use cases: Semantic search, retrieval-augmented generation (RAG), classification, clustering.