Command R+ is an open weights research release of a 104 billion parameter model with highly advanced capabilities, including Retrieval-Augmented Generation (RAG) and tool use to automate sophisticated tasks. The tool use in this model generation enables multi-step tool use, allowing the model to combine multiple tools over multiple steps to accomplish difficult tasks.
The model is optimized to perform well in the following languages: English, French, Spanish, Italian, German, Brazilian Portuguese, Japanese, Korean, Simplified Chinese, and Arabic. Pre-training data additionally included the following 13 languages: Russian, Polish, Turkish, Vietnamese, Dutch, Czech, Indonesian, Ukrainian, Romanian, Greek, Hindi, Hebrew, and Persian.
Command R+ is optimized for a variety of use cases, including reasoning, summarization, and question answering. This is an auto-regressive language model that uses an optimized transformer architecture. After pretraining, this model uses supervised fine-tuning (SFT) and preference training to align model behavior to human preferences for helpfulness and safety.
The model supports text input and output only and has a context length of 128K.
Tool Use & Multihop Capabilities
Command R+ has been specifically trained with conversational tool use capabilities. These have been trained into the model via a mixture of supervised fine-tuning and preference fine-tuning, using a specific prompt template. Deviating from this prompt template will likely reduce performance, but we encourage experimentation.
Command R+’s tool use functionality takes a conversation as input (with an optional user-system preamble), along with a list of available tools. The model will then generate a JSON-formatted list of actions to execute on a subset of those tools. Command R+ may use one of its supplied tools more than once.
The model has been trained to recognize a special "directly_answer" tool, which it uses to indicate that it doesn’t want to use any of its other tools. The ability to abstain from calling a specific tool can be useful in a range of situations, such as greeting a user or asking clarifying questions.
Grounded Generation and RAG Capabilities
Command R+ has been specifically trained with grounded generation capabilities. This means that it can generate responses based on a list of supplied document snippets, and it will include grounding spans (citations) in its response indicating the source of the information.
This can be used to enable behaviors such as grounded summarization and the final step of Retrieval-Augmented Generation (RAG). This behavior has been trained into the model via a mixture of supervised fine-tuning and preference fine-tuning, using a specific prompt template. Deviating from this prompt template may reduce performance, but we encourage experimentation.
Command R+’s grounded generation behavior takes a conversation as input (with an optional user-supplied system preamble, indicating task, context, and desired output style), along with a list of retrieved document snippets. The document snippets should be chunks, rather than long documents, typically around 100-400 words per chunk. Document snippets consist of key-value pairs. The keys should be short descriptive strings, and the values can be text or semi-structured.
By default, Command R+ will generate grounded responses by first predicting which documents are relevant, then predicting which ones it will cite, then generating an answer. Finally, it will insert grounding spans into the answer. This is referred to as accurate grounded generation.
The model is trained with a number of other answering modes, which can be selected by prompt changes. A fast citation mode is supported in the tokenizer, which will directly generate an answer with grounding spans in it, without first writing the answer out in full. This sacrifices some grounding accuracy in favor of generating fewer tokens.
Key Features
- Advanced RAG capabilities: Command R+ provides highly accurate and reliable solutions for enterprise needs, featuring in-line citations to reduce hallucinations and support tasks across various business functions like finance, HR, sales, marketing, and customer support.
- Tool use automation: It supports multi-step tool use, allowing the model to combine multiple tools over multiple steps to accomplish difficult tasks, making it ideal for automating sophisticated business workflows.
- Multilingual support: The model is optimized to perform well in 10 key languages: English, French, Spanish, Italian, German, Brazilian Portuguese, Japanese, Korean, Simplified Chinese, and Arabic. It also includes pre-training in 13 additional languages.
- Enterprise-ready: Command R+ is designed to meet the demands of large-scale production workloads while maintaining a strong commitment to data privacy and security.