Instructions to use longvideoagent/longvideoagent-qwen2.5-3b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use longvideoagent/longvideoagent-qwen2.5-3b with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="longvideoagent/longvideoagent-qwen2.5-3b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("longvideoagent/longvideoagent-qwen2.5-3b")
model = AutoModelForCausalLM.from_pretrained("longvideoagent/longvideoagent-qwen2.5-3b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use longvideoagent/longvideoagent-qwen2.5-3b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "longvideoagent/longvideoagent-qwen2.5-3b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "longvideoagent/longvideoagent-qwen2.5-3b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/longvideoagent/longvideoagent-qwen2.5-3b

SGLang

How to use longvideoagent/longvideoagent-qwen2.5-3b with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "longvideoagent/longvideoagent-qwen2.5-3b" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "longvideoagent/longvideoagent-qwen2.5-3b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "longvideoagent/longvideoagent-qwen2.5-3b" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "longvideoagent/longvideoagent-qwen2.5-3b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use longvideoagent/longvideoagent-qwen2.5-3b with Docker Model Runner:
```
docker model run hf.co/longvideoagent/longvideoagent-qwen2.5-3b
```

LongVideoAgent Qwen2.5-3B

This repository hosts the released LLM checkpoint for LongVideoAgent, a multi-agent framework for long-video question answering. This model is a Qwen2.5-3B-based checkpoint used in the LongVideoAgent project.

Project links:

Project page: https://longvideoagent.github.io/
Code: https://github.com/longvideoagent/LongVideoAgent
Paper: https://arxiv.org/abs/2512.20618

Overview

LongVideoAgent decomposes long-video reasoning into multiple roles:

MasterAgent for planning and answer generation
GroundingAgent for subtitle-based temporal grounding
VisionAgent for local visual evidence extraction

This checkpoint is intended for use with the official LongVideoAgent codebase and evaluation pipeline.

Intended Use

Use this model for:

Research on long-video question answering
Reproducing LongVideoAgent experiments
Studying agentic reasoning over long videos

This checkpoint is not a general-purpose video model by itself. For inference and evaluation, please use the official repository:

https://github.com/longvideoagent/LongVideoAgent

Usage

Please follow the setup and inference instructions in the official repository and project documentation:

If you use this checkpoint in your work, please also cite the LongVideoAgent paper below.

Limitations

This model is designed for the LongVideoAgent framework rather than standalone chat usage.
Performance depends on the full multi-agent pipeline, including grounding and visual evidence modules.
The model may inherit limitations from the base model and training data.

Citation

@misc{liu2025longvideoagentmultiagentreasoninglong,
  title={LongVideoAgent: Multi-Agent Reasoning with Long Videos},
  author={Runtao Liu and Ziyi Liu and Jiaqi Tang and Yue Ma and Renjie Pi and Jipeng Zhang and Qifeng Chen},
  year={2025},
  eprint={2512.20618},
  archivePrefix={arXiv},
  primaryClass={cs.AI},
  url={https://arxiv.org/abs/2512.20618},
}

Acknowledgement

This checkpoint is built for the LongVideoAgent project and is based on Qwen2.5-3B.

Downloads last month: 8

Safetensors

Model size

3B params

Tensor type

BF16

Model tree for longvideoagent/longvideoagent-qwen2.5-3b

Base model

Qwen/Qwen2.5-3B

Finetuned

(419)

this model

Paper for longvideoagent/longvideoagent-qwen2.5-3b

LongVideoAgent: Multi-Agent Reasoning with Long Videos

Paper • 2512.20618 • Published Dec 23, 2025 • 56