Tempo 6B Stage1

--- 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 1 Checkpoint) This repository contains the intermediate checkpoint (Stage 1) 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)

Source context: 21 downloads · 0 likes · Pipeline video-text-to-text · Repo Vision-CAIR/Tempo-6B-Stage1

Source context: 9 downloads · 0 likes · Pipeline video-text-to-text · Repo Vision-CAIR/Tempo-6B-Stage1