Video-Text-to-Text
Transformers
Safetensors
qwen3_vl
image-text-to-text
eventlens
video-understanding
temporal-grounding
reinforcement-learning
on-policy-distillation
Instructions to use Lostgreen/EventLens-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Lostgreen/EventLens-4B with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("Lostgreen/EventLens-4B") model = AutoModelForMultimodalLM.from_pretrained("Lostgreen/EventLens-4B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download NOTICE from Lostgreen/EventLens-4B: direct link, hf CLI and curl.
- Browser
- Download file 597 Bytes
-
https://huggingface.co/Lostgreen/EventLens-4B/resolve/main/NOTICE
- Command line
-
hf download hf://Lostgreen/EventLens-4B/NOTICE
-
curl -L -o NOTICE https://huggingface.co/Lostgreen/EventLens-4B/resolve/main/NOTICE
597 Bytes
| EventLens-4B | |
| This model contains fine-tuned derivative weights of Qwen3-VL-4B-Instruct, developed by the Qwen team and originally distributed under Apache License 2.0. The original license is included as LICENSE-BASE-QWEN-APACHE2. | |
| EventLens modifications were developed by AIM3 Lab, Renmin University of China, and Kling AI. EventLens model weights are distributed under Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International; see LICENSE. | |
| Base model: https://huggingface.co/Qwen/Qwen3-VL-4B-Instruct | |
| Training dataset: https://huggingface.co/datasets/Lostgreen/EventLens-Train | |