Image-to-Text
Transformers
PyTorch
Safetensors
English
git
image-text-to-text
vision
image-captioning
Instructions to use microsoft/git-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/git-base 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="microsoft/git-base")# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("microsoft/git-base") model = AutoModelForMultimodalLM.from_pretrained("microsoft/git-base", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download special_tokens_map.json from microsoft/git-base: direct link, hf CLI and curl.
- Browser
- Download file 125 Bytes
-
https://huggingface.co/microsoft/git-base/resolve/main/special_tokens_map.json
- Command line
-
hf download hf://microsoft/git-base/special_tokens_map.json
-
curl -L -o special_tokens_map.json https://huggingface.co/microsoft/git-base/resolve/main/special_tokens_map.json
125 Bytes
| { | |
| "cls_token": "[CLS]", | |
| "mask_token": "[MASK]", | |
| "pad_token": "[PAD]", | |
| "sep_token": "[SEP]", | |
| "unk_token": "[UNK]" | |
| } | |