Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,41 @@
|
|
1 |
-
---
|
2 |
-
license: cc-by-nc-4.0
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: cc-by-nc-4.0
|
3 |
+
base_model:
|
4 |
+
- Qwen/Qwen3-32B
|
5 |
+
tags:
|
6 |
+
- transformers
|
7 |
+
pipeline_tag: text-generation
|
8 |
+
---
|
9 |
+
# INFIndo-Qwen3-32B-Preview
|
10 |
+
## Model Overview
|
11 |
+
**INFIndo-Qwen3-32B-Preview** enhances the Indonesian language capabilities based on Qwen3-32B, which is produced through our designed data production pipeline using proprietary Indonesian language corpus. As of May 25th, 2025, this model has achieved the top performance among open-source models on the indonesian task in SEA-HELM (SouthEast Asian Holistic Evaluation of Language Models), which confirms the effectiveness of the improvement in the model's Indonesian language capabilities, and further validates the efficacy of our continual fine-tuning pipeline.
|
12 |
+
|
13 |
+
## Evaluation Results
|
14 |
+
|
15 |
+
| Model | SEA-HELM(ID)
|
16 |
+
|--------------------------------|---------|
|
17 |
+
| **INFIndo-Qwen3-32B-Preview** | 72.8 |
|
18 |
+
| Qwen3-32B | 71.9 |
|
19 |
+
| DeepSeek-R1 | 72.1 |
|
20 |
+
| Llama 3.3 | 70.4 |
|
21 |
+
|
22 |
+
## Contributors
|
23 |
+
### Supervisors
|
24 |
+
Wei Chu • Yuan Qi
|
25 |
+
|
26 |
+
### Instruction Following Team
|
27 |
+
Tianchu Yao • Xiaoyu Tan • Dakuan Lu
|
28 |
+
|
29 |
+
## Citation
|
30 |
+
If you find our model useful, please consider citing:
|
31 |
+
|
32 |
+
```
|
33 |
+
@misc{INFIndo_Preview,
|
34 |
+
author = {Yao, Tianchu and Tan, Xiaoyu and Lu, Dakuan and Chu, Wei and Qi, Yuan},
|
35 |
+
title = {INFIndo-Qwen3-32B-Preview},
|
36 |
+
year = {2025},
|
37 |
+
month = {May},
|
38 |
+
howpublished = {Hugging Face},
|
39 |
+
url = {https://huggingface.co/infly/INFIndo-Qwen3-32B-Preview},
|
40 |
+
}
|
41 |
+
```
|