Instructions to use anocha-mcomp/lora_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use anocha-mcomp/lora_model with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("anocha-mcomp/lora_model", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Desktop
Update model card from Confluence: Model Card: Gemma-SEA-LION-v4-4B-VL
Browse files
model_card_gemma-sea-lion-v4-4b-vl.md
CHANGED
|
@@ -4,9 +4,7 @@
|
|
| 4 |
|
| 5 |
SEA-LION is a collection of Large Language Models (LLMs) which have been pretrained and instruct-tuned for the Southeast Asia (SEA) region.
|
| 6 |
|
| 7 |
-
**Gemma-SEA-LION-v4-4B-VL** is a 4-billion parameter Vision-Language Model (VLM) built upon the gemma-3-4b-it architecture. To ensure **domain adaptation** for the region, the model underwent rigorous post-training on a curated dataset of approximately **8.54 million** instruction-text pairs.
|
| 8 |
-
|
| 9 |
-
This extensive post-training instills **multilingual** and **multicultural** fluency, covering English and key SEA languages with a heavy emphasis on Burmese, Malay, Tagalog and Tamil.
|
| 10 |
|
| 11 |
Gemma-SEA-LION-v4-4B-VL inherits the following features from gemma-3-4b-it:
|
| 12 |
|
|
@@ -20,7 +18,7 @@ Gemma-SEA-LION-v4-4B-VL inherits the following features from gemma-3-4b-it:
|
|
| 20 |
|
| 21 |
SEA-LION stands for *Southeast Asian Languages In One Network*.
|
| 22 |
|
| 23 |
-
We performed post-training in
|
| 24 |
|
| 25 |
For tokenization, the model employs the default tokenizer used in gemma-3-4b-it.
|
| 26 |
|
|
@@ -52,8 +50,7 @@ The model has not been aligned for safety. Developers and users should perform t
|
|
| 52 |
Use the code below to get started with the model with 🤗 Transformers libraries.
|
| 53 |
|
| 54 |
```
|
| 55 |
-
|
| 56 |
-
|
| 57 |
```
|
| 58 |
|
| 59 |
```
|
|
@@ -75,7 +72,7 @@ messages = [
|
|
| 75 |
"role": "user",
|
| 76 |
"content": [
|
| 77 |
{"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
|
| 78 |
-
{"type": "text", "text": "
|
| 79 |
]
|
| 80 |
}
|
| 81 |
]
|
|
@@ -103,6 +100,15 @@ The instruction fine-tuning text dataset comprises of a collection of OSS & synt
|
|
| 103 |
- <https://huggingface.co/datasets/allenai/Dolci-Instruct-SFT-Tool-Use>
|
| 104 |
- <https://huggingface.co/datasets/Agent-Ark/Toucan-1.5M>
|
| 105 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 106 |
**Datasets for Reinforcement Learning:**
|
| 107 |
|
| 108 |
- Instruction following: <https://huggingface.co/datasets/nvidia/Nemotron-Cascade-RL-Instruction-Following>
|
|
@@ -118,8 +124,6 @@ The instruction fine-tuning text dataset comprises of a collection of OSS & synt
|
|
| 118 |
|
| 119 |
### Testing Data, Factors & Metrics
|
| 120 |
|
| 121 |
-
#### Testing Data
|
| 122 |
-
|
| 123 |
We evaluated Gemma-SEA-LION-v4-4B-VL on general language capabilities and LLM-specific capabilities using SEA-HELM.
|
| 124 |
|
| 125 |
**Testing Data**
|
|
@@ -171,7 +175,17 @@ The following metrics were used for text capabilities:
|
|
| 171 |
|
| 172 |
### Results
|
| 173 |
|
| 174 |
-
For details on Gemma-SEA-LION-v4-4B-VL performance, please refer to the SEA-HELM leaderboard, <https://leaderboard.sea-lion.ai/>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 175 |
|
| 176 |
### Retaining VL Capabilities
|
| 177 |
|
|
@@ -204,9 +218,9 @@ For more info, please contact us at [sealion@aisingapore.org](mailto:sealion@ais
|
|
| 204 |
|
| 205 |
## Team
|
| 206 |
|
| 207 |
-
Ahmed Dabeer, Ahn Jeongmi, Antonyrex Sajeban, Chan Hok Teng Adwin, Cheng Zi Yi Nicholas, Choa Hsueh Mei Esther, Heng Jonathan, Huang Yuli, Jann Railey Estrada Montalan, Kang Siow Wei Bryan, Lee Chwan Ren, Leong Wai Yi, Leong Wei Qi, Liew Rachel, Limkonchotiwat Peerat, Muhammad Ridzuan Bin Mokhtar, Nagarajan Karthik, Ng Boon Cheong Raymond, Ngee Chia Tai, Ngui Jian Gang, Nguyen Thanh Ngan, Ong Tat-Wee David, Ong Zhi Hao, Pereira Mark, Poon Joseph, Rengarajan Hamsawardhini, Susanto Yosephine, Sutaveephamochanon Anocha, Tan Choon Meng, Tan Chor Phin Evelyn, Tan Siao Wei Jessica, Tan Yixian, Tee Jun Yun, Teng Kok Wai Walter, Teo Eng Sipp Leslie, Tjhi William, Yeo Yeow Tong, Yong Xianbin, Zhang Zhou
|
| 208 |
|
| 209 |
-
Gemma team??? Elliott Chris (Google), Mohseni Mohammadreza (Google), Sharan Mayank (Google), Wei Fanny (Google), Tang Jiuqiang (Google), Xu Xiang (Google), Yu Ting (Google), Loh Michelle (Google), Mangal Saurabh (Google), Mukherjee Pratyusha (Google), Sim Stephanie (Google)
|
| 210 |
|
| 211 |
## Acknowledgement
|
| 212 |
|
|
|
|
| 4 |
|
| 5 |
SEA-LION is a collection of Large Language Models (LLMs) which have been pretrained and instruct-tuned for the Southeast Asia (SEA) region.
|
| 6 |
|
| 7 |
+
**Gemma-SEA-LION-v4-4B-VL** is a 4-billion parameter Vision-Language Model (VLM) built upon the gemma-3-4b-it architecture. To ensure **domain adaptation** for the region, the model underwent rigorous post-training on a curated dataset of approximately **8.54 million** instruction-text pairs. This curated dataset included various SEA Languages such as Burmese, Malay, Tagalog and Tamil. This extensive post-training instills **multilingual** and **multicultural** fluency for both SEA languages and English.
|
|
|
|
|
|
|
| 8 |
|
| 9 |
Gemma-SEA-LION-v4-4B-VL inherits the following features from gemma-3-4b-it:
|
| 10 |
|
|
|
|
| 18 |
|
| 19 |
SEA-LION stands for *Southeast Asian Languages In One Network*.
|
| 20 |
|
| 21 |
+
We performed post-training in SEA languages and English on gemma-3-4b-it, a decoder model using the gemma-3 architecture, and post-training to create Gemma-SEA-LION-v4-4B-VL.
|
| 22 |
|
| 23 |
For tokenization, the model employs the default tokenizer used in gemma-3-4b-it.
|
| 24 |
|
|
|
|
| 50 |
Use the code below to get started with the model with 🤗 Transformers libraries.
|
| 51 |
|
| 52 |
```
|
| 53 |
+
pip install transformers>=4.50.0
|
|
|
|
| 54 |
```
|
| 55 |
|
| 56 |
```
|
|
|
|
| 72 |
"role": "user",
|
| 73 |
"content": [
|
| 74 |
{"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
|
| 75 |
+
{"type": "text", "text": "Respond and provide a brief description in Indonesian. What animal is on the candy?"}
|
| 76 |
]
|
| 77 |
}
|
| 78 |
]
|
|
|
|
| 100 |
- <https://huggingface.co/datasets/allenai/Dolci-Instruct-SFT-Tool-Use>
|
| 101 |
- <https://huggingface.co/datasets/Agent-Ark/Toucan-1.5M>
|
| 102 |
|
| 103 |
+
**Datasets for OCR:**
|
| 104 |
+
|
| 105 |
+
- <https://huggingface.co/datasets/Goekdeniz-Guelmez/unsloth-LaTeX_OCR-for-mlx-vlm> (68,700)
|
| 106 |
+
- <https://huggingface.co/datasets/sushanthr/fineweb_ocr/viewer/default/train?row=0> (150,000)
|
| 107 |
+
- <https://huggingface.co/datasets/sushanthr/wiki_ocr> (50,000)
|
| 108 |
+
- <https://huggingface.co/datasets/Chanrith123333/khmer_english_ocr_image_line> (11.3 million)
|
| 109 |
+
- <https://huggingface.co/datasets/chuuhtetnaing/burmese_ocr_data_hf> (9070)
|
| 110 |
+
- <https://huggingface.co/datasets/SoyVitou/KhmerST-Dataset-OCR-Cropped> (3560)
|
| 111 |
+
|
| 112 |
**Datasets for Reinforcement Learning:**
|
| 113 |
|
| 114 |
- Instruction following: <https://huggingface.co/datasets/nvidia/Nemotron-Cascade-RL-Instruction-Following>
|
|
|
|
| 124 |
|
| 125 |
### Testing Data, Factors & Metrics
|
| 126 |
|
|
|
|
|
|
|
| 127 |
We evaluated Gemma-SEA-LION-v4-4B-VL on general language capabilities and LLM-specific capabilities using SEA-HELM.
|
| 128 |
|
| 129 |
**Testing Data**
|
|
|
|
| 175 |
|
| 176 |
### Results
|
| 177 |
|
| 178 |
+
For details on Gemma-SEA-LION-v4-4B-VL performance, please refer to the SEA-HELM leaderboard, <https://leaderboard.sea-lion.ai/>.
|
| 179 |
+
|
| 180 |
+
### Tool calling
|
| 181 |
+
|
| 182 |
+
We evaluated the tool calling capabilities of our model
|
| 183 |
+
|
| 184 |
+
#### Results
|
| 185 |
+
|
| 186 |
+
### OCR
|
| 187 |
+
|
| 188 |
+
#### Results
|
| 189 |
|
| 190 |
### Retaining VL Capabilities
|
| 191 |
|
|
|
|
| 218 |
|
| 219 |
## Team
|
| 220 |
|
| 221 |
+
Ahmed Dabeer, Ahn Jeongmi, Antonyrex Sajeban, Chan Hok Teng Adwin, Cheng Zi Yi Nicholas, Choa Hsueh Mei Esther, Heng Jonathan, Huang Yuli, Jann Railey Estrada Montalan, Kang Siow Wei Bryan, Lee Chwan Ren, Leong Wai Yi, Leong Wei Qi, Liew Rachel, Limkonchotiwat Peerat, Muhammad Ridzuan Bin Mokhtar, Nagarajan Karthik, Ng Boon Cheong Raymond, Ngee Chia Tai, Ngui Jian Gang, Nguyen Thanh Ngan, Ong Tat-Wee David, Ong Zhi Hao, Pereira Mark, Poon Joseph, Rengarajan Hamsawardhini, Susanto Yosephine, Sutaveephamochanon Anocha, Tan Choon Meng, Tan Chor Phin Evelyn, Tan Siao Wei Jessica, Tan Yixian, Tee Jun Yun, Teng Kok Wai Walter, Teo Eng Sipp Leslie, Tjhi William, Yeo Yeow Tong, Yong Xianbin, Zhang Zhou, Elliott Chris (Google), Mohseni Mohammadreza (Google), Sharan Mayank (Google), Wei Fanny (Google), Tang Jiuqiang (Google), Xu Xiang (Google), Yu Ting (Google), Loh Michelle (Google), Mangal Saurabh (Google), Mukherjee Pratyusha (Google), Sim Stephanie (Google)
|
| 222 |
|
| 223 |
+
~~Gemma team??? Elliott Chris (Google), Mohseni Mohammadreza (Google), Sharan Mayank (Google), Wei Fanny (Google), Tang Jiuqiang (Google), Xu Xiang (Google), Yu Ting (Google), Loh Michelle (Google), Mangal Saurabh (Google), Mukherjee Pratyusha (Google), Sim Stephanie (Google)~~
|
| 224 |
|
| 225 |
## Acknowledgement
|
| 226 |
|