Skip to content
ModelListedExternal
Download

Tempo 6B Stage0

This repository contains the intermediate checkpoint (Stage 0) for Tempo-6B.

Sourcehuggingface.co/Vision-CAIR/Tempo-6B-Stage0/tree/12765d2f136618167fce709617788887f9722e71
KindText modelBase modelQwen/Qwen3-4BVersionpytorch_modelCgrade

Model source

Kind
Text model
File size
12.2 GB
Base model
Qwen/Qwen3-4B
Version
vpytorch_model
Updated
Oct 24, 2026
Downloads
12
Source
Hugging Face

Source description

Tempo-6B (Stage 0 Checkpoint)

This repository contains the intermediate checkpoint (Stage 0) for Tempo-6B.

⚠️ Note: This is an intermediate training state and is NOT intended for direct inference or deployment. It is provided solely for researchers who wish to reproduce our training pipeline or conduct ablation studies.

For the final model weights, comprehensive evaluation results, and inference instructions, please refer to:

Sources

1 source
Hugging FacePrimaryVersion 12765d2f136618167fce709617788887f9722e71
huggingface.co/Vision-CAIR/Tempo-6B-Stage0/tree/12765d2f136618167fce709617788887f9722e71

Verified Oct 24

Model artifacts

1 artifact

pytorch_model.bin

bin · 12.2 GB · SHA-256 7aa9ecc8aafd…92a8 · Hugging Face

Download file

Source excerpts

3 excerpts
ReadmeAug 7huggingface.co/Vision-CAIR/Tempo-6B-Stage0

--- language: - en license: apache-2.0 pipeline_tag: video-text-to-text base_model: - Qwen/Qwen3-VL-2B-Instruct - Qwen/Qwen3-4B tags: - vision-language-model - long-video-understanding - multimodal - pytorch - custom_code --- # Tempo-6B (Stage 0 Checkpoint) This repository contains the intermediate checkpoint (Stage 0) for **Tempo-6B**. ⚠️ **Note:** This is an intermediate training state and is **NOT** intended for direct inference or deployment. It is provided solely for researchers who wish to reproduce our training pipeline or conduct ablation studies. For the final model weights, comprehensive evaluation results, and inference instructions, please refer to: - **Final Model:** [Vision-CAIR/Tempo-6B](https://huggingface.co/Vision-CAIR/Tempo-6B) - **GitHub Repository:** [FeiElysia/Tempo](https://github.com/FeiElysia/Tempo) - **Paper:** [Small Vision-Language Models are Smart Compressors for Long Video Understanding](https://huggingface.co/papers/2604.08120)

NoteOct 24huggingface.co/Vision-CAIR/Tempo-6B-Stage0

Source context: 12 downloads · 0 likes · Pipeline video-text-to-text · Repo Vision-CAIR/Tempo-6B-Stage0

NoteAug 7huggingface.co/Vision-CAIR/Tempo-6B-Stage0

Source context: 6 downloads · 0 likes · Pipeline video-text-to-text · Repo Vision-CAIR/Tempo-6B-Stage0