Any-to-Any
Transformers
Safetensors
English
Chinese
qwen3_vl
image-text-to-text
embodied-ai
vision-language-model
robotics
spatial-reasoning
multimodal
Instructions to use DeepCybo/PhysBrain1.5-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DeepCybo/PhysBrain1.5-8B with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("DeepCybo/PhysBrain1.5-8B") model = AutoModelForMultimodalLM.from_pretrained("DeepCybo/PhysBrain1.5-8B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update pipeline tag and add library name
#3
by nielsr HF Staff - opened
This PR updates the model card metadata to better reflect the model’s capabilities and compatibility:
- Changes
pipeline_tagfromimage-text-to-texttoany-to-any, since PhysBrain 1.5 supports unified multimodal understanding, action generation, and future-state prediction. - Adds
library_name: transformers, as the model uses a standard Transformers architecture (Qwen3VLForConditionalGeneration) and is compatible with the Transformers library.
No content changes are made.
VLyb changed pull request status to merged