Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2408.12480 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909293970718720 |
|---|---|
| author | Doan, Khang T. Huynh, Bao G. Hoang, Dung T. Pham, Thuc D. Pham, Nhat H. Nguyen, Quan T. M. Vo, Bang Q. Hoang, Suong N. |
| author_facet | Doan, Khang T. Huynh, Bao G. Hoang, Dung T. Pham, Thuc D. Pham, Nhat H. Nguyen, Quan T. M. Vo, Bang Q. Hoang, Suong N. |
| contents | In this report, we introduce Vintern-1B, a reliable 1-billion-parameters multimodal large language model (MLLM) for Vietnamese language tasks. By integrating the Qwen2-0.5B-Instruct language model with the InternViT-300M-448px visual model, Vintern-1B is optimized for a range of applications, including optical character recognition (OCR), document extraction, and general question-answering in Vietnamese context. The model is fine-tuned on an extensive dataset of over 3 million image-question-answer pairs, achieving robust performance and reliable results across multiple Vietnamese language benchmarks like OpenViVQA and ViTextVQA. Vintern-1B is small enough to fit into various on-device applications easily. Additionally, we have open-sourced several Vietnamese vision question answering (VQA) datasets for text and diagrams, created with Gemini 1.5 Flash. Our models are available at: https://huggingface.co/5CD-AI/Vintern-1B-v2. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_12480 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Vintern-1B: An Efficient Multimodal Large Language Model for Vietnamese Doan, Khang T. Huynh, Bao G. Hoang, Dung T. Pham, Thuc D. Pham, Nhat H. Nguyen, Quan T. M. Vo, Bang Q. Hoang, Suong N. Machine Learning Computation and Language In this report, we introduce Vintern-1B, a reliable 1-billion-parameters multimodal large language model (MLLM) for Vietnamese language tasks. By integrating the Qwen2-0.5B-Instruct language model with the InternViT-300M-448px visual model, Vintern-1B is optimized for a range of applications, including optical character recognition (OCR), document extraction, and general question-answering in Vietnamese context. The model is fine-tuned on an extensive dataset of over 3 million image-question-answer pairs, achieving robust performance and reliable results across multiple Vietnamese language benchmarks like OpenViVQA and ViTextVQA. Vintern-1B is small enough to fit into various on-device applications easily. Additionally, we have open-sourced several Vietnamese vision question answering (VQA) datasets for text and diagrams, created with Gemini 1.5 Flash. Our models are available at: https://huggingface.co/5CD-AI/Vintern-1B-v2. |
| title | Vintern-1B: An Efficient Multimodal Large Language Model for Vietnamese |
| topic | Machine Learning Computation and Language |
| url | https://arxiv.org/abs/2408.12480 |