Instructions to use SinaLab/Qwen-2.5-VL-7B-Instruct-Image-Captioning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use SinaLab/Qwen-2.5-VL-7B-Instruct-Image-Captioning with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-VL-7B-Instruct") model = PeftModel.from_pretrained(base_model, "SinaLab/Qwen-2.5-VL-7B-Instruct-Image-Captioning") - Notebooks
- Google Colab
- Kaggle
Alaa Aljabari commited on
Commit ·
0b7d988
1
Parent(s): bacb3bc
added training dataset link
Browse files
README.md
CHANGED
|
@@ -2,6 +2,8 @@
|
|
| 2 |
library_name: peft
|
| 3 |
license: mit
|
| 4 |
base_model: Qwen/Qwen2.5-VL-7B-Instruct
|
|
|
|
|
|
|
| 5 |
tags:
|
| 6 |
- arabic
|
| 7 |
- image-captioning
|
|
@@ -24,6 +26,7 @@ This model is a LoRA fine-tuned version of [Qwen/Qwen2.5-VL-7B-Instruct](https:/
|
|
| 24 |
|
| 25 |
This model was developed as part of the [Arabic Image Captioning Shared Task 2025](https://sina.birzeit.edu/image_eval2025/index.html). It generates natural Arabic captions for images with focus on historical and cultural content related to Palestinian heritage.
|
| 26 |
|
|
|
|
| 27 |
|
| 28 |
## Usage
|
| 29 |
|
|
|
|
| 2 |
library_name: peft
|
| 3 |
license: mit
|
| 4 |
base_model: Qwen/Qwen2.5-VL-7B-Instruct
|
| 5 |
+
datasets:
|
| 6 |
+
- SinaLab/ImageEval2025Task2TrainDataset
|
| 7 |
tags:
|
| 8 |
- arabic
|
| 9 |
- image-captioning
|
|
|
|
| 26 |
|
| 27 |
This model was developed as part of the [Arabic Image Captioning Shared Task 2025](https://sina.birzeit.edu/image_eval2025/index.html). It generates natural Arabic captions for images with focus on historical and cultural content related to Palestinian heritage.
|
| 28 |
|
| 29 |
+
please refer to the [training dataset](https://huggingface.co/datasets/SinaLab/ImageEval2025Task2TrainDataset) for more details.
|
| 30 |
|
| 31 |
## Usage
|
| 32 |
|