Instructions to use dxkrnn/blipball with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dxkrnn/blipball with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("dxkrnn/blipball") model = AutoModelForMultimodalLM.from_pretrained("dxkrnn/blipball", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tokenizer_config.json from dxkrnn/blipball: direct link, hf CLI and curl.
- Browser
- Download file 487 Bytes
-
https://huggingface.co/dxkrnn/blipball/resolve/main/tokenizer_config.json
- Command line
-
hf download hf://dxkrnn/blipball/tokenizer_config.json
-
curl -L -o tokenizer_config.json https://huggingface.co/dxkrnn/blipball/resolve/main/tokenizer_config.json
487 Bytes
| { | |
| "cls_token": "[CLS]", | |
| "do_basic_tokenize": true, | |
| "do_lower_case": true, | |
| "mask_token": "[MASK]", | |
| "model_max_length": 512, | |
| "name_or_path": "Salesforce/blip-image-captioning-base", | |
| "never_split": null, | |
| "pad_token": "[PAD]", | |
| "processor_class": "BlipProcessor", | |
| "sep_token": "[SEP]", | |
| "special_tokens_map_file": null, | |
| "strip_accents": null, | |
| "tokenize_chinese_chars": true, | |
| "tokenizer_class": "BertTokenizer", | |
| "trust_remote_code": false, | |
| "unk_token": "[UNK]" | |
| } |