Video-Text-to-Text
Transformers
Safetensors
English
Chinese
qwen3_vl
image-text-to-text
video
streaming-video
proactive-response
visual-question-answering
Instructions to use MCG-NJU/OneStreamer-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MCG-NJU/OneStreamer-4B with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("MCG-NJU/OneStreamer-4B") model = AutoModelForMultimodalLM.from_pretrained("MCG-NJU/OneStreamer-4B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
28 days ago
-
Upload OneStreamer-4B weights and tokenizer
Verified signatureAdd four BF16 weight shards, their tensor index, and model, processor, and tokenizer configuration with streaming state tokens.71408bb