Image-to-Text
Transformers
Safetensors
Arabic
lfm2_vl
image-text-to-text
arabic
vlm
image-captioning
siglip2
lfm2-vl
emhotob
Instructions to use oddadmix/Nawah-VL-50M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use oddadmix/Nawah-VL-50M with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "image-to-text" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("image-to-text", model="oddadmix/Nawah-VL-50M")# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("oddadmix/Nawah-VL-50M") model = AutoModelForMultimodalLM.from_pretrained("oddadmix/Nawah-VL-50M", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "image_processor": { | |
| "do_image_splitting": false, | |
| "do_normalize": true, | |
| "do_pad": true, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "downsample_factor": 2, | |
| "encoder_patch_size": 16, | |
| "image_mean": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "image_processor_type": "Lfm2VlImageProcessor", | |
| "image_std": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "max_image_tokens": 64, | |
| "max_num_patches": 256, | |
| "max_pixels_tolerance": 2.0, | |
| "max_tiles": 10, | |
| "min_image_tokens": 32, | |
| "min_tiles": 2, | |
| "resample": 2, | |
| "rescale_factor": 0.00392156862745098, | |
| "return_row_col_info": false, | |
| "size": { | |
| "height": 512, | |
| "width": 512 | |
| }, | |
| "tile_size": 512, | |
| "use_thumbnail": false | |
| }, | |
| "processor_class": "Lfm2VlProcessor" | |
| } | |