Visual Question Answering
Transformers
Safetensors
English
Chinese
qwen2_vl
image-text-to-text
multimodal
text-generation-inference
Instructions to use Cylingo/Xinyuan-VL-2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Cylingo/Xinyuan-VL-2B 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="Cylingo/Xinyuan-VL-2B")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("Cylingo/Xinyuan-VL-2B") model = AutoModelForMultimodalLM.from_pretrained("Cylingo/Xinyuan-VL-2B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download added_tokens.json from Cylingo/Xinyuan-VL-2B: direct link, hf CLI and curl.
- Browser
- Download file 392 Bytes
-
https://huggingface.co/Cylingo/Xinyuan-VL-2B/resolve/main/added_tokens.json
- Command line
-
hf download hf://Cylingo/Xinyuan-VL-2B/added_tokens.json
-
curl -L -o added_tokens.json https://huggingface.co/Cylingo/Xinyuan-VL-2B/resolve/main/added_tokens.json
392 Bytes
| { | |
| "<|box_end|>": 151649, | |
| "<|box_start|>": 151648, | |
| "<|endoftext|>": 151643, | |
| "<|im_end|>": 151645, | |
| "<|im_start|>": 151644, | |
| "<|image_pad|>": 151655, | |
| "<|object_ref_end|>": 151647, | |
| "<|object_ref_start|>": 151646, | |
| "<|quad_end|>": 151651, | |
| "<|quad_start|>": 151650, | |
| "<|video_pad|>": 151656, | |
| "<|vision_end|>": 151653, | |
| "<|vision_pad|>": 151654, | |
| "<|vision_start|>": 151652 | |
| } | |