Aya Expanse 8B is an open-weight research release of a model with highly advanced multilingual capabilities. It focuses on pairing a highly performant pre-trained Command family of models with the result of a year’s dedicated research from Cohere Labs, including data arbitrage, multilingual preference training, safety tuning, and model merging. The result is a powerful multilingual large language model.
This model card corresponds to the 8-billion version of the Aya Expanse model. We also released an 32-billion version which you can find here.
We cover 23 languages: Arabic, Chinese (simplified & traditional), Czech, Dutch, English, French, German, Greek, Hebrew, Hebrew, Hindi, Indonesian, Italian, Japanese, Korean, Persian, Polish, Portuguese, Romanian, Russian, Spanish, Turkish, Ukrainian, and Vietnamese.
Use the Cohere playground or our Hugging Face Space for interactive exploration.
Install the transformers library and load Aya Expanse 8B as follows:
from transformers import AutoTokenizer, AutoModelForCausalLM
model_id = "CohereLabs/aya-expanse-8b"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)
# Format the message with the chat template
messages = [{"role": "user", "content": "Anneme onu ne kadar sevdiğimi anlatan bir mektup yaz"}]
input_ids = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt")
## <BOS_TOKEN><|START_OF_TURN_TOKEN|><|USER_TOKEN|>Anneme onu ne kadar sevdiğimi anlatan bir mektup yaz<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>
gen_tokens = model.generate(
input_ids,
max_new_tokens=100,
do_sample=True,
temperature=0.3,
)
gen_text = tokenizer.decode(gen_tokens[0])
print(gen_text)
Fine-Tuning:
Community-Contributed Use Cases::
The following notebooks contributed by Cohere Labs Community members show how Aya Expanse can be used for different use cases:
Input: Models input text only.
Output: Models generate text only.
Model Architecture: Aya Expanse 8B is an auto-regressive language model that uses an optimized transformer architecture. Post-training includes supervised finetuning, preference training, and model merging.
Languages covered: The model is particularly optimized for multilinguality and supports the following languages: Arabic, Chinese (simplified & traditional), Czech, Dutch, English, French, German, Greek, Hebrew, Hindi, Indonesian, Italian, Japanese, Korean, Persian, Polish, Portuguese, Romanian, Russian, Spanish, Turkish, Ukrainian, and Vietnamese
Context length: 8K
For more details about how the model was trained, check out our blogpost.
We evaluated Aya Expanse 8B against Gemma 2 9B, Llama 3.1 8B, Ministral 8B, and Qwen 2.5 7B using the dolly_human_edited subset from the Aya Evaluation Suite dataset and m-ArenaHard, a dataset based on the Arena-Hard-Auto dataset and translated to the 23 languages we support in Aya Expanse 8B. Win-rates were determined using gpt-4o-2024-08-06 as a judge. For a conservative benchmark, we report results from gpt-4o-2024-08-06, though gpt-4o-mini scores showed even stronger performance.
The m-ArenaHard dataset, used to evaluate Aya Expanse’s capabilities, is publicly available here.
For errors or additional questions about details in this model card, contact labs@cohere.com
We hope that the release of this model will make community-based research efforts more accessible, by releasing the weights of a highly performant multilingual 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
You can cite Aya Expanse using:
@misc{dang2024ayaexpansecombiningresearch,
title={Aya Expanse: Combining Research Breakthroughs for a New Multilingual Frontier},
author={John Dang and Shivalika Singh and Daniel D'souza and Arash Ahmadian and Alejandro Salamanca and Madeline Smith and Aidan Peppin and Sungjin Hong and Manoj Govindassamy and Terrence Zhao and Sandra Kublik and Meor Amer and Viraat Aryabumi and Jon Ander Campos and Yi-Chern Tan and Tom Kocmi and Florian Strub and Nathan Grinsztajn and Yannis Flet-Berliac and Acyr Locatelli and Hangyu Lin and Dwarak Talupuru and Bharat Venkitesh and David Cairuz and Bowen Yang and Tim Chung and Wei-Yin Ko and Sylvie Shang Shi and Amir Shukayev and Sammie Bae and Aleksandra Piktus and Roman Castagné and Felipe Cruz-Salinas and Eddie Kim and Lucas Crawhall-Stein and Adrien Morisot and Sudip Roy and Phil Blunsom and Ivan Zhang and Aidan Gomez and Nick Frosst and Marzieh Fadaee and Beyza Ermis and Ahmet Üstün and Sara Hooker},
year={2024},
eprint={2412.04261},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2412.04261},
}
model-00003-of-00004.safetensors 5.0 GBmodel-00002-of-00004.safetensors 4.9 GBmodel-00001-of-00004.safetensors 4.9 GBmodel-00004-of-00004.safetensors 1.2 GB