Image-to-Text
Transformers
Safetensors
PyTorch
Vietnamese
blip
image-text-to-text
image-captioning
vietnamese
vision-language
uit-openviic
Instructions to use nviquang/Vie-BLIP with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nviquang/Vie-BLIP 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="nviquang/Vie-BLIP", device_map="auto")# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("nviquang/Vie-BLIP") model = AutoModelForMultimodalLM.from_pretrained("nviquang/Vie-BLIP", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "added_tokens_decoder": { | |
| "0": { | |
| "content": "<s>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "1": { | |
| "content": "<pad>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "2": { | |
| "content": "</s>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "3": { | |
| "content": "<unk>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "64000": { | |
| "content": "<mask>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| } | |
| }, | |
| "additional_special_tokens": null, | |
| "backend": "custom", | |
| "bos_token": "<s>", | |
| "cls_token": "<s>", | |
| "eos_token": "</s>", | |
| "is_local": false, | |
| "mask_token": "<mask>", | |
| "model_max_length": 1000000000000000019884624838656, | |
| "pad_token": "<pad>", | |
| "processor_class": "BlipProcessor", | |
| "sep_token": "</s>", | |
| "tokenizer_class": "PhobertTokenizer", | |
| "unk_token": "<unk>" | |
| } | |