Feature Extraction
Transformers
Safetensors
qwen2_5_vl
image-text-to-text
embedding
multimodal
vision-language
mmeb
mveb
Instructions to use HugC/VisME-Qwen25VL-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use HugC/VisME-Qwen25VL-3B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="HugC/VisME-Qwen25VL-3B")# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("HugC/VisME-Qwen25VL-3B") model = AutoModelForMultimodalLM.from_pretrained("HugC/VisME-Qwen25VL-3B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
File size: 200 Bytes
2e124cb | 1 2 3 4 5 6 7 8 9 | {
"name": "Qwen2_5_VLEmbedding",
"pooling": "eos",
"normalize": true,
"output_layer": -1,
"output_component": "full",
"system_prompt": "You are a helpful assistant.",
"max_length": 768
} |