license: llama3.2
language:
- en
- zh
Breeze2-3B-Instruct-v0_1
【Paper】◇【Demo】◇【Collection】
The Breeze 2 Herd of Models: Traditional Chinese LLMs Based on LLaMA with Vision-Aware and Function-Calling Capabilities
Breeze 2 is a suite of advanced multi-modal language models, available in 3B and 8B parameter configurations, specifically designed to enhance Traditional Chinese language representation. Building upon the LLaMA 3.2, Breeze 2 continues pretraining on an extensive corpus to enhance the linguistic and cultural heritage of Traditional Chinese. It incorporates vision-aware capabilities through a visual encoder and a bridge module, and supports function-calling via prompt templates and post-training on function-calling data.
We list all contributors in alphabetical order of their first names, as follows: Chan-Jan Hsu (許湛然), Chia-Sheng Liu (劉佳昇), Meng-Hsi Chen (陳孟羲), Muxi Chen (陳沐希), Po-Chun Hsu (許博竣), Yi-Chang Chen (陳宜昌), and the supervisor Da-Shan Shiu (許大山).
Installation
pip3 install transformers==4.47.0
pip3 install -U mtkresearch
from transformers import AutoModel, AutoTokenizer
import torch
model_id = 'MediaTek-Research/Breeze2-8B-Instruct-v0_1'
model = AutoModel.from_pretrained(
model_id,
torch_dtype=torch.bfloat16,
low_cpu_mem_usage=True,
trust_remote_code=True,
device_map='auto').eval()
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True, use_fast=False)
Feature: Instruction Following
Feature: Visual Instruction Following
Feature: Function Calling
Citation
@article{breeze2,
title={The Breeze 2 Herd of Models: Traditional Chinese LLMs Based on LLaMA with Vision-Aware and Function-Calling Capabilities},
author={Breeze Team, MediaTek Research},
journal={arXiv},
year={2025}
}