Cohere Labs Command R7B is an open weights research release of a 7B billion parameter model with advanced capabilities optimized for a variety of use cases including reasoning, summarization, question answering, and code. The model is trained to perform sophisticated tasks including Retrieval Augmented Generation (RAG) and tool use. The model also has powerful agentic capabilities with the ability to use and combine multiple tools over multiple steps to accomplish more difficult tasks. It obtains top performance on enterprise relevant code use cases. Command R7B is a multilingual model trained on 23 languages.
For more details on how this model was developed, check out our Tech Report.
Try Command R7B
You can try out Cohere Labs Command R7B before downloading the weights in our hosted Hugging Face Space.
Usage
Please install transformers from the source repository that includes the necessary changes for this model.
py
1# pip install 'git+https://github.com/huggingface/transformers.git'2from transformers import AutoTokenizer, AutoModelForCausalLM
34model_id ="CohereLabs/c4ai-command-r7b-12-2024"5tokenizer = AutoTokenizer.from_pretrained(model_id)6model = AutoModelForCausalLM.from_pretrained(model_id)78# Format message with the c4ai-command-r7b-12-2024 chat template9messages =[{"role":"user","content":"Hello, how are you?"}]10input_ids = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt")1112gen_tokens = model.generate(13 input_ids,14 max_new_tokens=100,15 do_sample=True,16 temperature=0.3,17)1819gen_text = tokenizer.decode(gen_tokens[0], skip_special_tokens=True)20print(gen_text)
Model Details
Input: Models input text only.
Output: Models generate text only.
Model Architecture: 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 features three layers with sliding window attention (window size 4096) and ROPE for efficient local context modeling and relative positional encoding. A fourth layer uses global attention without positional embeddings, enabling unrestricted token interactions across the entire sequence.
Languages covered: The model has been trained on 23 languages: English, French, Spanish, Italian, German, Portuguese, Japanese, Korean, Arabic, Chinese, Russian, Polish, Turkish, Vietnamese, Dutch, Czech, Indonesian, Ukrainian, Romanian, Greek, Hindi, Hebrew, and Persian.
Context length: Command R7B supports a context length of 128K.
A well-rounded model
Command R7B excels on standardized and externally verifiable benchmarks such as the HuggingFace Open LLM Leaderboard. Compared to other similarly sized open-weights models, Command R7B ranks first with strong performance across all tasks.
Command R7B
Gemma 2 IT 9B
Ministral 8B
Llama 3.1 8B
Qwen 2.5 7B
Tulu 3 8B
Average
31.4
28.9
22
28.2
26.87
26.03
IFEval
77.9
74.4
58.96
78.6
75.85
82.67
BBH
36.1
42.1
25.82
29.9
34.89
16.67
MATH hard
26.4
0.2
6.5
19.3
0.0
19.64
GPQA
7.7
14.8
4.5
2.4
5.48
6.49
MUSR
11.6
9.74
10.7
8.41
8.45
10.45
MMLU-Pro
28.5
32
25.5
30.7
36.52
20.3
HuggingFace Leaderboard evaluation results. Competitor numbers are taken from the official leaderboard. Command R7B results are calculated by us using the official HuggingFace prompts and evaluation code.
Chat Capabilities:
Command R7B can be configured as both a conversational model and an instruct model. The conversational mode conditions the model on interactive behaviour, meaning it is expected to reply in a conversational fashion, provides introductory statements and follow-up questions, and uses Markdown as well as LaTeX where appropriate. It is optimized for interactive experiences, such as chatbots, where the model engages in dialogue.
The instruct mode, in contrast, conditions the model to provide concise yet comprehensive responses, and does not use Markdown / LaTeX by default. It is designed for non-interactive, task-focused use cases like extracting information, summarizing text, translation, and categorization.
Note: by default, Command R7B is delivered without a system preamble. We recommend to add the conversational or instruct preambles as described in our docs.
RAG Capabilities:
Command R7B has been trained specifically for tasks like the final step of Retrieval Augmented Generation (RAG).
RAG with Command R7B is supported through chat templates in Transformers. The model takes a conversation as input (with an optional user-supplied system preamble), along with a list of document snippets.
RAG Example [CLICK TO EXPAND]
py
1# Define conversation input2conversation =[{"role":"user","content":"What has Man always dreamed of?"}]34# Define documents for retrieval-based generation5documents =[6{"heading":"The Moon: Our Age-Old Foe","body":"Man has always dreamed of destroying the moon. In this essay, I shall..."},7{"heading":"Love is all you need","body":"Man's dream has always been to find love. This profound lesson..."}8]910# Get the RAG prompt11input_prompt = tokenizer.apply_chat_template(conversation=conversation, documents=documents, tokenize=False, add_generation_prompt=True, return_tensors="pt")12# Tokenize the prompt13input_ids = tokenizer.encode_plus(input_prompt, return_tensors="pt")
You can then generate text from this input as normal.
Document snippets should be short chunks, rather than long documents, typically around 100-400 words per chunk, formatted as key-value pairs. The keys should be short descriptive strings, the values can be text or semi-structured.
You may find that simply including relevant documents directly in a user message works just as well, or better than using the documents parameter to render the special RAG template. The RAG template is generally a strong default. We encourage users to play with both, and to evaluate which mode works best for their specific use case.
Note that this was a very brief introduction to RAG - for more information, see the Command R7B prompt format docs and the Transformers RAG documentation.
Tool Use Capabilities:
Command R7B has been specifically trained with conversational tool use capabilities. This allows the model to interact with external tools like APIs, databases, or search engines.
Tool use with Command R7B is supported through chat templates in Transformers. We recommend providing tool descriptions using JSON schema.
Tool Use Example [CLICK TO EXPAND]
py
1# Define tools2tools =[3{4"type":"function",5"function":{6"name":"query_daily_sales_report",7"description":"Connects to a database to retrieve overall sales volumes and sales information for a given day.",8"parameters":{9"type":"object",10"properties":{11"day":{12"description":"Retrieves sales data for this day, formatted as YYYY-MM-DD.",13"type":"string",14}15},16"required":["day"]17},18}19}20]2122# Define conversation input23conversation =[{"role":"user","content":"Can you provide a sales summary for 29th September 2023?"}]2425# Get the Tool Use prompt26input_prompt = tokenizer.apply_chat_template(conversation=conversation, tools=tools, tokenize=False, add_generation_prompt=True, return_tensors="pt")2728# Tokenize the prompt29input_ids = tokenizer.encode_plus(input_prompt, return_tensors="pt")
You can then generate text from this input as normal.
If the model generates a plan and tool calls, you should add them to the chat history like so:
py
1tool_call ={"name":"query_daily_sales_report","arguments":{"day":"2023-09-29"}}2tool_plan ="I will use the query_daily_sales_report tool to find the sales summary for 29th September 2023."3conversation.append({"role":"assistant","tool_calls":[{"id":"0","type":"function","function": tool_call},],"tool_plan": tool_plan})
and then call the tool(s) and append the result(s), with the tool role, like so:
py
1# every tool result needs to be a dictionary!!2api_response_for_query_daily_sales_report ={"date":"2023-09-29","summary":"Total Sales Amount: 10000, Total Units Sold: 250"}3# append tool results4conversation.append({"role":"tool","tool_call_id":"0","content": api_response_for_query_daily_sales_report})# make sure "tool_call_id" matches the "id" of the tool_call
After that, you can generate() again to let the model use the tool result in the chat.
Note that this was a very brief introduction to tool calling - for more information, see the Command R7B prompt format docs and the Transformers tool use documentation.
Code Capabilities:
Command R7B has meaningfully improved on code capabilities. In addition to academic code benchmarks, we have evaluated it on enterprise-relevant scenarios, including SQL and code translation, where it outperforms other models of similar size. Try these out by requesting code snippets, code explanations, or code rewrites. For better performance, we also recommend using a low temperature (and even greedy decoding) for code-generation related instructions.
Model Card Contact
For errors or additional questions about details in this model card, contact labs@cohere.com
Terms of Use:
We hope that the release of this model will make community-based research efforts more accessible, by releasing the weights of a highly performant 7 billion parameter model to researchers all over the world. This model is governed by a CC-BY-NC, requires also adhering to Cohere Lab's Acceptable Use Policy
Try Chat:
You can try Command R7B chat in the playground here. You can also use it in our dedicated Hugging Face Space here.
Citation:
@misc{cohere2025commandaenterprisereadylarge,
title={Command A: An Enterprise-Ready Large Language Model},
author={Team Cohere and Aakanksha and Arash Ahmadian and Marwan Ahmed and Jay Alammar and Yazeed Alnumay and Sophia Althammer and Arkady Arkhangorodsky and Viraat Aryabumi and Dennis Aumiller and Raphaël Avalos and Zahara Aviv and Sammie Bae and Saurabh Baji and Alexandre Barbet and Max Bartolo and Björn Bebensee and Neeral Beladia and Walter Beller-Morales and Alexandre Bérard and Andrew Berneshawi and Anna Bialas and Phil Blunsom and Matt Bobkin and Adi Bongale and Sam Braun and Maxime Brunet and Samuel Cahyawijaya and David Cairuz and Jon Ander Campos and Cassie Cao and Kris Cao and Roman Castagné and Julián Cendrero and Leila Chan Currie and Yash Chandak and Diane Chang and Giannis Chatziveroglou and Hongyu Chen and Claire Cheng and Alexis Chevalier and Justin T. Chiu and Eugene Cho and Eugene Choi and Eujeong Choi and Tim Chung and Volkan Cirik and Ana Cismaru and Pierre Clavier and Henry Conklin and Lucas Crawhall-Stein and Devon Crouse and Andres Felipe Cruz-Salinas and Ben Cyrus and Daniel D'souza and Hugo Dalla-Torre and John Dang and William Darling and Omar Darwiche Domingues and Saurabh Dash and Antoine Debugne and Théo Dehaze and Shaan Desai and Joan Devassy and Rishit Dholakia and Kyle Duffy and Ali Edalati and Ace Eldeib and Abdullah Elkady and Sarah Elsharkawy and Irem Ergün and Beyza Ermis and Marzieh Fadaee and Boyu Fan and Lucas Fayoux and Yannis Flet-Berliac and Nick Frosst and Matthias Gallé and Wojciech Galuba and Utsav Garg and Matthieu Geist and Mohammad Gheshlaghi Azar and Seraphina Goldfarb-Tarrant and Tomas Goldsack and Aidan Gomez and Victor Machado Gonzaga and Nithya Govindarajan and Manoj Govindassamy and Nathan Grinsztajn and Nikolas Gritsch and Patrick Gu and Shangmin Guo and Kilian Haefeli and Rod Hajjar and Tim Hawes and Jingyi He and Sebastian Hofstätter and Sungjin Hong and Sara Hooker and Tom Hosking and Stephanie Howe and Eric Hu and Renjie Huang and Hemant Jain and Ritika Jain and Nick Jakobi and Madeline Jenkins and JJ Jordan and Dhruti Joshi and Jason Jung and Trushant Kalyanpur and Siddhartha Rao Kamalakara and Julia Kedrzycki and Gokce Keskin and Edward Kim and Joon Kim and Wei-Yin Ko and Tom Kocmi and Michael Kozakov and Wojciech Kryściński and Arnav Kumar Jain and Komal Kumar Teru and Sander Land and Michael Lasby and Olivia Lasche and Justin Lee and Patrick Lewis and Jeffrey Li and Jonathan Li and Hangyu Lin and Acyr Locatelli and Kevin Luong and Raymond Ma and Lukas Mach and Marina Machado and Joanne Magbitang and Brenda Malacara Lopez and Aryan Mann and Kelly Marchisio and Olivia Markham and Alexandre Matton and Alex McKinney and Dominic McLoughlin and Jozef Mokry and Adrien Morisot and Autumn Moulder and Harry Moynehan and Maximilian Mozes and Vivek Muppalla and Lidiya Murakhovska and Hemangani Nagarajan and Alekhya Nandula and Hisham Nasir and Shauna Nehra and Josh Netto-Rosen and Daniel Ohashi and James Owers-Bardsley and Jason Ozuzu and Dennis Padilla and Gloria Park and Sam Passaglia and Jeremy Pekmez and Laura Penstone and Aleksandra Piktus and Case Ploeg and Andrew Poulton and Youran Qi and Shubha Raghvendra and Miguel Ramos and Ekagra Ranjan and Pierre Richemond and Cécile Robert-Michon and Aurélien Rodriguez and Sudip Roy and Laura Ruis and Louise Rust and Anubhav Sachan and Alejandro Salamanca and Kailash Karthik Saravanakumar and Isha Satyakam and Alice Schoenauer Sebag and Priyanka Sen and Sholeh Sepehri and Preethi Seshadri and Ye Shen and Tom Sherborne and Sylvie Chang Shi and Sanal Shivaprasad and Vladyslav Shmyhlo and Anirudh Shrinivason and Inna Shteinbuk and Amir Shukayev and Mathieu Simard and Ella Snyder and Ava Spataru and Victoria Spooner and Trisha Starostina and Florian Strub and Yixuan Su and Jimin Sun and Dwarak Talupuru and Eugene Tarassov and Elena Tommasone and Jennifer Tracey and Billy Trend and Evren Tumer and Ahmet Üstün and Bharat Venkitesh and David Venuto and Pat Verga and Maxime Voisin and Alex Wang and Donglu Wang and Shijian Wang and Edmond Wen and Naomi White and Jesse Willman and Marysia Winkels and Chen Xia and Jessica Xie and Minjie Xu and Bowen Yang and Tan Yi-Chern and Ivan Zhang and Zhenyu Zhao and Zhoujie Zhao},
year={2025},
eprint={2504.00698},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2504.00698},
}
