GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
MCG-NJU
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
MCG-NJU
Model Tree
Qwen/Qwen3-VL-8B-Instruct
Input Modalities
Output Modalities
Supported Functionality
SFT uses examples from TimeLens2-93K, TimeLens-100K, and the official Ego4D-NLQ-v2 training split. Training retains full-video context and supervises variable-cardinality temporal interval sets. The model sees diverse grounding instructions and timestamp response formats.
The 8B SFT recipe trains for one epoch with packed sequences up to 100K tokens, a global batch size of 256, and a learning rate of 5e-6. The visual encoder is frozen during training.
This is an SFT checkpoint. It is not the final GRPO-optimized release reported in the TimeLens2 paper.
This checkpoint is hosted in a Hugging Face dataset repository. Download it locally, then load the directory with Transformers:
python
from huggingface_hub import snapshot_downloadfrom transformers import AutoModelForImageTextToText, AutoProcessor model_dir = snapshot_download( repo_id="MCG-NJU/TimeLens2-8B-SFT", repo_type="dataset",)model = AutoModelForImageTextToText.from_pretrained( model_dir, torch_dtype="auto", device_map="auto",)processor = AutoProcessor.from_pretrained(model_dir)See the official repository for the SFT and GRPO training recipes, data annotations, rollout configuration, and evaluation code.
bibtex
@article{zhu2026timelens2, title={TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs}, author={Zhu, Yuhan and Ma, Changlian and Zeng, Xiangyu and Li, Xinhao and Zhang, Zhiqiu and Li, Songze and Zhang, Jun and Jiang, Tianxiang and Yang, Yuandong and Yan, Ziang and others}, journal={arXiv preprint arXiv:2607.17423}, year={2026}}@article{zhu2026timelens2, title={TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs}, author={Zhu, Yuhan and Ma, Changlian and Zeng, Xiangyu and Li, Xinhao and Zhang, Zhiqiu and Li, Songze and Zhang, Jun and Jiang, Tianxiang and Yang, Yuandong and Yan, Ziang and others}, journal={arXiv preprint arXiv:2607.17423}, year={2026}}