Instructions to use KETI-NLP/clip-roberta-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use KETI-NLP/clip-roberta-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="KETI-NLP/clip-roberta-base")# Load model directly from transformers import AutoProcessor, AutoModel processor = AutoProcessor.from_pretrained("KETI-NLP/clip-roberta-base") model = AutoModel.from_pretrained("KETI-NLP/clip-roberta-base", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tokenizer_config.json from KETI-NLP/clip-roberta-base: direct link, hf CLI and curl.
- Browser
- Download file 445 Bytes
-
https://huggingface.co/KETI-NLP/clip-roberta-base/resolve/main/tokenizer_config.json
- Command line
-
hf download hf://KETI-NLP/clip-roberta-base/tokenizer_config.json
-
curl -L -o tokenizer_config.json https://huggingface.co/KETI-NLP/clip-roberta-base/resolve/main/tokenizer_config.json
445 Bytes
| { | |
| "add_prefix_space": false, | |
| "bos_token": "<s>", | |
| "cls_token": "<s>", | |
| "eos_token": "</s>", | |
| "errors": "replace", | |
| "mask_token": "<mask>", | |
| "model_max_length": 512, | |
| "name_or_path": "./aligned-clip-roberta", | |
| "pad_token": "<pad>", | |
| "processor_class": "VisionTextDualEncoderProcessor", | |
| "sep_token": "</s>", | |
| "special_tokens_map_file": null, | |
| "tokenizer_class": "RobertaTokenizer", | |
| "trim_offsets": true, | |
| "unk_token": "<unk>" | |
| } | |