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-4B-Instruct
Input Modalities
Output Modalities
Supported Functionality
TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs
bash
pip install -U torch torchvision "transformers>=4.57.0" accelerate "qwen-vl-utils[decord]>=0.0.14"pip install -U flash-attn --no-build-isolationpython
from pathlib import Path from qwen_vl_utils import process_vision_infofrom transformers import AutoModelForImageTextToText, AutoProcessor model_id = "MCG-NJU/TimeLens2-4B"video_path = "/path/to/video.mp4"query = "A man opens the refrigerator." model = AutoModelForImageTextToText.from_pretrained( model_id, torch_dtype="auto", device_map="auto", attn_implementation="flash_attention_2",)processor = AutoProcessor.from_pretrained(model_id) prompt = ( f'Given the query: "{query}", return ALL time spans (in seconds) where the query is relevant.\n' "Output format MUST be a JSON array of [start, end] pairs.\n")messages = [ { "role": "user", "content": [ { "type": "video", "video": Path(video_path).resolve().as_uri(), "fps": 2.0, "min_pixels": 32 * 32, "max_pixels": 480 * 480, "total_pixels": 128000 * 32 * 32, }, {"type": "text", "text": prompt}, ], }] text = processor.apply_chat_template( messages, tokenize=False, add_generation_prompt=True,)images, videos, video_kwargs = process_vision_info( messages, image_patch_size=16, return_video_kwargs=True, return_video_metadata=True,) if videos is not None: videos, video_metadatas = zip(*videos) videos, video_metadatas = list(videos), list(video_metadatas)else: video_metadatas = None inputs = processor( text=text, images=images, videos=videos, video_metadata=video_metadatas, do_resize=False, return_tensors="pt", **video_kwargs,).to(model.device) output_ids = model.generate( **inputs, max_new_tokens=4096, temperature=0.01, top_p=0.001, top_k=1, repetition_penalty=1.0,)output_ids = [ output[len(input_ids) :] for input_ids, output in zip(inputs.input_ids, output_ids)]response = processor.batch_decode( output_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False,)print(response[0])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}}pip install -U torch torchvision "transformers>=4.57.0" accelerate "qwen-vl-utils[decord]>=0.0.14"pip install -U flash-attn --no-build-isolationfrom pathlib import Path from qwen_vl_utils import process_vision_infofrom transformers import AutoModelForImageTextToText, AutoProcessor model_id = "MCG-NJU/TimeLens2-4B"video_path = "/path/to/video.mp4"query = "A man opens the refrigerator." model = AutoModelForImageTextToText.from_pretrained( model_id, torch_dtype="auto", device_map="auto", attn_implementation="flash_attention_2",)processor = AutoProcessor.from_pretrained(model_id) prompt = ( f'Given the query: "{query}", return ALL time spans (in seconds) where the query is relevant.\n' "Output format MUST be a JSON array of [start, end] pairs.\n")messages = [ { "role": "user", "content": [ { "type": "video", "video": Path(video_path).resolve().as_uri(), "fps": 2.0, "min_pixels": 32 * 32, "max_pixels": 480 * 480, "total_pixels": 128000 * 32 * 32, }, {"type": "text", "text": prompt}, ], }] text = processor.apply_chat_template( messages, tokenize=False, add_generation_prompt=True,)images, videos, video_kwargs = process_vision_info( messages, image_patch_size=16, return_video_kwargs=True, return_video_metadata=True,) if videos is not None: videos, video_metadatas = zip(*videos) videos, video_metadatas = list(videos), list(video_metadatas)else: video_metadatas = None inputs = processor( text=text, images=images, videos=videos, video_metadata=video_metadatas, do_resize=False, return_tensors="pt", **video_kwargs,).to(model.device) output_ids = model.generate( **inputs, max_new_tokens=4096, temperature=0.01, top_p=0.001, top_k=1, repetition_penalty=1.0,)output_ids = [ output[len(input_ids) :] for input_ids, output in zip(inputs.input_ids, output_ids)]response = processor.batch_decode( output_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False,)print(response[0])@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}}