Instructions to use workwithHasnain/FF-Image-to-Recipe with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use workwithHasnain/FF-Image-to-Recipe 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="workwithHasnain/FF-Image-to-Recipe")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("workwithHasnain/FF-Image-to-Recipe") model = AutoModelForMultimodalLM.from_pretrained("workwithHasnain/FF-Image-to-Recipe", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Delete config.json
Browse files- config.json +0 -27
config.json
DELETED
|
@@ -1,27 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_name_or_path": "Salesforce/blip-image-captioning-base",
|
| 3 |
-
"architectures": [
|
| 4 |
-
"BlipForConditionalGeneration"
|
| 5 |
-
],
|
| 6 |
-
"image_text_hidden_size": 256,
|
| 7 |
-
"initializer_factor": 1.0,
|
| 8 |
-
"initializer_range": 0.02,
|
| 9 |
-
"label_smoothing": 0.0,
|
| 10 |
-
"logit_scale_init_value": 2.6592,
|
| 11 |
-
"model_type": "blip",
|
| 12 |
-
"projection_dim": 512,
|
| 13 |
-
"text_config": {
|
| 14 |
-
"initializer_factor": 1.0,
|
| 15 |
-
"model_type": "blip_text_model",
|
| 16 |
-
"num_attention_heads": 12
|
| 17 |
-
},
|
| 18 |
-
"torch_dtype": "float32",
|
| 19 |
-
"transformers_version": "4.39.3",
|
| 20 |
-
"vision_config": {
|
| 21 |
-
"dropout": 0.0,
|
| 22 |
-
"initializer_factor": 1.0,
|
| 23 |
-
"initializer_range": 0.02,
|
| 24 |
-
"model_type": "blip_vision_model",
|
| 25 |
-
"num_channels": 3
|
| 26 |
-
}
|
| 27 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|