Instructions to use microsoft/git-base-textcaps with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/git-base-textcaps 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-textcaps")# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("microsoft/git-base-textcaps") model = AutoModelForMultimodalLM.from_pretrained("microsoft/git-base-textcaps", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tokenizer_config.json from microsoft/git-base-textcaps: direct link, hf CLI and curl.
- Browser
- Download file 453 Bytes
-
https://huggingface.co/microsoft/git-base-textcaps/resolve/refs%2Fpr%2F1/tokenizer_config.json
- Command line
-
hf download hf://microsoft/git-base-textcaps@refs/pr/1/tokenizer_config.json
-
curl -L -o tokenizer_config.json https://huggingface.co/microsoft/git-base-textcaps/resolve/refs%2Fpr%2F1/tokenizer_config.json
453 Bytes
| { | |
| "cls_token": "[CLS]", | |
| "do_lower_case": true, | |
| "mask_token": "[MASK]", | |
| "model_input_names": [ | |
| "input_ids", | |
| "attention_mask" | |
| ], | |
| "model_max_length": 512, | |
| "name_or_path": "bert-base-uncased", | |
| "pad_token": "[PAD]", | |
| "processor_class": "GitProcessor", | |
| "sep_token": "[SEP]", | |
| "special_tokens_map_file": null, | |
| "strip_accents": null, | |
| "tokenize_chinese_chars": true, | |
| "tokenizer_class": "BertTokenizer", | |
| "unk_token": "[UNK]" | |
| } | |