Update README.md
Browse files
README.md
CHANGED
|
@@ -14,6 +14,7 @@ pipeline_tag: image-text-to-text
|
|
| 14 |
<img src="https://cdn-uploads.huggingface.co/production/uploads/6336b5c831efcb5647f00170/-G297bBqMzYvTbD6_Bkd9.png" width="500"/>
|
| 15 |
</div>
|
| 16 |
|
|
|
|
| 17 |
# Vintern-1B-v3.5 ❄️
|
| 18 |
We introduce **Vintern-1B-v3.5**, the latest version in the Vintern series, offering significant improvements over v2 across all evaluation benchmarks. This model has been fine-tuned from **InternVL2.5-1B**, which already good in Vietnamese 🇻🇳 tasks because it used [Viet-ShareGPT-4o-Text-VQA](https://huggingface.co/datasets/5CD-AI/Viet-ShareGPT-4o-Text-VQA) data during its fine-tuning process by the InternVL 2.5 [1] team.
|
| 19 |
|
|
|
|
| 14 |
<img src="https://cdn-uploads.huggingface.co/production/uploads/6336b5c831efcb5647f00170/-G297bBqMzYvTbD6_Bkd9.png" width="500"/>
|
| 15 |
</div>
|
| 16 |
|
| 17 |
+
|
| 18 |
# Vintern-1B-v3.5 ❄️
|
| 19 |
We introduce **Vintern-1B-v3.5**, the latest version in the Vintern series, offering significant improvements over v2 across all evaluation benchmarks. This model has been fine-tuned from **InternVL2.5-1B**, which already good in Vietnamese 🇻🇳 tasks because it used [Viet-ShareGPT-4o-Text-VQA](https://huggingface.co/datasets/5CD-AI/Viet-ShareGPT-4o-Text-VQA) data during its fine-tuning process by the InternVL 2.5 [1] team.
|
| 20 |
|