mlsanityData to 7 Oct 2026

The Breeze 2 Herd of Models: Traditional Chinese LLMs Based on Llama with Vision-Aware and Function-Calling Capabilities

arXiv 2501.13921 ↗First posted 23 Jan 2025cs.CLcited by 4

On the map: Multimodal LLMs / vision-language models → MLLM training and visual instruction tuning

Abstract (arXiv)

Llama-Breeze2 (hereinafter referred to as Breeze2) 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 model family, we continue the pre-training of Breeze2 on an extensive corpus to enhance the linguistic and cultural heritage of Traditional Chinese. In addition to language modeling capabilities, we significantly augment the models with function calling and vision understanding capabilities. At the time of this publication, as far as we are aware, absent reasoning-inducing prompts, Breeze2 are the strongest performing models in Traditional Chinese function calling and image understanding in its size class. The effectiveness of Breeze2 is benchmarked across various tasks, including Taiwan general knowledge, instruction-following, long context, function calling, and vision understanding. We are publicly releasing all Breeze2 models under the Llama 3.2 Community License. We also showcase the capabilities of the model running on mobile platform with a mobile application which we also open source.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Placed in MLLM training and visual instruction tuning, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 25 of its 30 references that are in the map. First posted on arXiv 23 Jan 2025.

Builds on

25 of 30 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024A High-Quality Text-Rich Image Instruction Tuning Dataset via Hybrid Instruction Generation20 Dec
  2. 2024How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites25 Apr
  3. 2023ShareGPT4V: Improving Large Multi-Modal Models with Better Captions21 Nov

Other references · 22

  1. 2024The Llama 3 Herd of Modelscited by 14,192
  2. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  3. 2023Visual Instruction Tuningcited by 7,792
  4. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  5. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
  6. 2016Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answeringcited by 2,498
  7. 2023MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGIcited by 2,044
  8. 2021Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpuscited by 481
  9. 2022The Stack: 3 TB of permissively licensed source codecited by 354
  10. 2021WIT: Wikipedia-based Image Text Dataset for Multimodal Multilingual Machine Learningcited by 285
  11. 2016COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Imagescited by 235
  12. 2019NeMo: a toolkit for building AI applications using Neural Modulescited by 230
10 more
  1. 2024APIGen: Automated Pipeline for Generating Verifiable and Diverse Function-Calling Datasetscited by 188
  2. 2023MMC: Advancing Multimodal Chart Understanding with Large-scale Instruction Tuningcited by 149
  3. 2019ICDAR2019 Robust Reading Challenge on Arbitrary-Shaped Text (RRC-ArT)cited by 147
  4. 2024The All-Seeing Project V2: Towards General Relation Comprehension of the Open Worldcited by 90
  5. 2023Taiwan LLM: Bridging the Linguistic Divide with a Culturally Aligned Language Modelcited by 29
  6. 2024Enhancing Function-Calling Capabilities in LLMs: Strategies for Prompt Formats, Data Integration, and Multilingual Translationcited by 14
  7. 2023Advancing the Evaluation of Traditional Chinese Language Models: Towards a Comprehensive Benchmark Suitecited by 13
  8. 2024An Improved Traditional Chinese Evaluation Suite for Foundation Modelcited by 10
  9. 2024Breeze-7B Technical Reportcited by 4
  10. 2024FineWeb-zhtw: Scalable Curation of Traditional Chinese Text Data from the Webcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 3.

4 papers.

Similar, not cited

Close in wording, no citation either way

  1. 2023YAYI 2: Multilingual Open-Source Large Language Models
  2. 2024MERaLiON-TextLLM: Cross-Lingual Understanding of Large Language Models in Chinese, Indonesian, Malay, and Singlish
  3. 2024Measuring Taiwanese Mandarin Language Understanding
  4. 2024BayLing 2: A Multilingual Large Language Model with Efficient Language Alignment
  5. 2025VocalBench-zh: Decomposing and Benchmarking the Speech Conversational Abilities in Mandarin Context
  6. 2023CMMLU: Measuring massive multitask language understanding in Chinese
  7. 2024Responsible Multilingual Large Language Models: A Survey of Development, Applications, and Societal Impact
  8. 2024SUTRA: Scalable Multilingual Language Model Architecture