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 For AI, including data arbitrage, multilingual preference training, safety tuning, and model merging. The result is a powerful multilingual large language model.
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 openmind library and load Aya Expanse 8B as follows:
from openmind import pipeline, AutoTokenizer, AutoModelForCausalLM
import torch
import torch_npu
import argparse
def parse_args():
parser = argparse.ArgumentParser()
parser.add_argument(
"--model_name_or_path",
type=str,
help="Jinan_AICC/aya-expanse-8b",
default=None,
)
args = parser.parse_args()
return args
args = parse_args()
model_id = args.model_name_or_path
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id).to("npu:0")
# 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").to("npu:0")
## <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)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
We evaluated Aya Expanse 8B against Gemma 2 9B, Llama 3.1 8B, Ministral 8B, and Qwen 2.5 7B using Dolly 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.