Visual Question Answering
Transformers
Safetensors
English
panovlm_decision
feature-extraction
panovlm
decision-model
calibration
fastvit
linear-attention
custom_code
Instructions to use PanocularAI/PanoVLD-500M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use PanocularAI/PanoVLD-500M with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "visual-question-answering" 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("visual-question-answering", model="PanocularAI/PanoVLD-500M", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("PanocularAI/PanoVLD-500M", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tokenizer_config.json from PanocularAI/PanoVLD-500M: direct link, hf CLI and curl.
- Browser
- Download file 558 Bytes
-
https://huggingface.co/PanocularAI/PanoVLD-500M/resolve/main/tokenizer_config.json
- Command line
-
hf download hf://PanocularAI/PanoVLD-500M/tokenizer_config.json
-
curl -L -o tokenizer_config.json https://huggingface.co/PanocularAI/PanoVLD-500M/resolve/main/tokenizer_config.json
558 Bytes
| { | |
| "add_prefix_space": null, | |
| "backend": "tokenizers", | |
| "bos_token": "<s>", | |
| "clean_up_tokenization_spaces": false, | |
| "eos_token": "</s>", | |
| "extra_special_tokens": [ | |
| "<|image|>", | |
| "<|begin_of_image|>", | |
| "<|end_of_image|>" | |
| ], | |
| "is_local": true, | |
| "local_files_only": false, | |
| "model_max_length": 1000000000000000019884624838656, | |
| "pad_token": "<|pad|>", | |
| "sp_model_kwargs": {}, | |
| "spaces_between_special_tokens": false, | |
| "tokenizer_class": "LlamaTokenizer", | |
| "unk_token": "<unk>", | |
| "use_default_system_prompt": false, | |
| "legacy": true | |
| } |