Visual Question Answering
Transformers
PyTorch
Safetensors
English
paligemma
image-text-to-text
coffe
caption
text-generation-inference
Instructions to use Fer14/paligemma_coffee_machine_caption with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Fer14/paligemma_coffee_machine_caption with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("visual-question-answering", model="Fer14/paligemma_coffee_machine_caption")# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("Fer14/paligemma_coffee_machine_caption") model = AutoModelForMultimodalLM.from_pretrained("Fer14/paligemma_coffee_machine_caption", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "_name_or_path": "google/paligemma-3b-pt-224", | |
| "architectures": [ | |
| "PaliGemmaForConditionalGeneration" | |
| ], | |
| "bos_token_id": 2, | |
| "eos_token_id": 1, | |
| "hidden_size": 2048, | |
| "ignore_index": -100, | |
| "image_token_index": 257152, | |
| "model_type": "paligemma", | |
| "pad_token_id": 0, | |
| "projection_dim": 2048, | |
| "text_config": { | |
| "hidden_size": 2048, | |
| "intermediate_size": 16384, | |
| "model_type": "gemma", | |
| "num_attention_heads": 8, | |
| "num_hidden_layers": 18, | |
| "num_image_tokens": 256, | |
| "num_key_value_heads": 1, | |
| "torch_dtype": "float32", | |
| "vocab_size": 257216 | |
| }, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.42.0.dev0", | |
| "vision_config": { | |
| "hidden_size": 1152, | |
| "intermediate_size": 4304, | |
| "model_type": "siglip_vision_model", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 27, | |
| "num_image_tokens": 256, | |
| "patch_size": 14, | |
| "projection_dim": 2048, | |
| "projector_hidden_act": "gelu_fast", | |
| "vision_use_head": false | |
| }, | |
| "vocab_size": 257216 | |
| } | |