Instructions to use Junteng/Chart_CLIP with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Junteng/Chart_CLIP with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-feature-extraction", model="Junteng/Chart_CLIP")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Junteng/Chart_CLIP", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "_name_or_path": "openai/clip-vit-large-patch14-336", | |
| "architectures": [ | |
| "CLIPModel" | |
| ], | |
| "initializer_factor": 1.0, | |
| "logit_scale_init_value": 2.6592, | |
| "model_type": "clip", | |
| "projection_dim": 768, | |
| "text_config": { | |
| "dropout": 0.0, | |
| "hidden_size": 768, | |
| "intermediate_size": 3072, | |
| "model_type": "clip_text_model", | |
| "num_attention_heads": 12, | |
| "projection_dim": 768 | |
| }, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.44.2", | |
| "vision_config": { | |
| "dropout": 0.0, | |
| "hidden_size": 1024, | |
| "image_size": 336, | |
| "intermediate_size": 4096, | |
| "model_type": "clip_vision_model", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 24, | |
| "patch_size": 14, | |
| "projection_dim": 768 | |
| } | |
| } | |