Introduction

Command-R+ is a cutting-edge large language model (LLM) developed by Cohere. It is the latest addition to the R-series of LLMs, emphasizing high efficiency and strong accuracy to support real-world business applications.

Command-R+ Model

Command R+ is the latest iteration in our R-series of LLMs, specifically engineered to strike an optimal balance between efficiency and accuracy. It boasts a 128k-token context window, setting a new benchmark for LLM capabilities. Key features include:

• Features:
• • 128k-token context window
• • Advanced Retrieval Augmented Generation (RAG) with citation to reduce hallucinations
• • Multilingual coverage in 10 key languages
• • Tool Use to automate sophisticated business processes
• Multilingual Support:
• • Offers extensive support for 10 key global business languages, ensuring wide-reaching applicability.
• • Languages supported: English, French, Spanish, Italian, German, Portuguese, Japanese, Korean, Arabic, and Chinese.
• • Multilingual capability enables accurate responses from diverse data sources, facilitating global business operations.

Run Command-R+ with an API

Running the API with Clarifai's Python SDK

You can run the Command-R+ Model API using Clarifai’s Python SDK.

Export your PAT as an environment variable. Then, import and initialize the API Client.

Find your PAT in your security settings.

export CLARIFAI_PAT={your personal access token}

from clarifai.client.model import Model

prompt = "What’s the future of AI?"

inference_params = dict(temperature=0.2, max_tokens=100, top_k=40, system_prompt = "You are a helpful assistant.")

# Model Predict
model_prediction = Model("https://clarifai.com/cohere/generate/models/command-r-plus").predict_by_bytes(prompt.encode(), input_type="text", inference_params=inference_params)

print(model_prediction.outputs[0].data.text.raw)

You can also run Command-R+ API using other Clarifai Client Libraries like Java, cURL, NodeJS, PHP, etc here.

Aliases: command-r-plus, Command-R+, command R+, command R plus

Use Cases

Command R+ is versatile, addressing a broad spectrum of enterprise applications. These include, but are not limited to:

• Multilingual customer support automation.
• Sophisticated business analytics and reporting.
• Content creation and translation across multiple languages..

Evaluation

Command R+ outshines similar models in the scalable market category and remains competitive against more costly alternatives. It performs excellently in essential business capabilities while adhering to strict data privacy and security standards.

Multilingual Evaluation

Comparison of models on FLoRES (in French, Spanish, Italian, German, Portuguese, Japanese, Korean, Arabic, and Chinese) and WMT23 (in German, Japanese, and Chinese) translation tasks.

Multi-step Reasoning

Advantages

• Efficiency and Scalability: Optimized for enterprise-grade workloads, offering seamless integration into production environments.
• Multilingual Support: Ensures accurate, context-aware responses in 10 key languages, facilitating global business operations.
• Cost Reduction: Achieves up to a 57% reduction in tokenization costs for non-English texts, significantly lowering operational expenses.

Limitations

• Language Limitations: While covering 10 key languages, global businesses operating in regions with other languages may require additional solutions.
• Adaptation Time: Integrating and optimizing the model for specific business processes may require significant initial effort.