Video-Text-to-Text
Transformers
Safetensors
English
qwen2_5_vl
image-text-to-text
Eval Results
text-generation-inference
Instructions to use Video-R1/Video-R1-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Video-R1/Video-R1-7B with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("Video-R1/Video-R1-7B") model = AutoModelForMultimodalLM.from_pretrained("Video-R1/Video-R1-7B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download .eval_results/longshotbench.yaml from Video-R1/Video-R1-7B: direct link, hf CLI and curl.
- Browser
- Download file 1.41 kB
-
https://huggingface.co/Video-R1/Video-R1-7B/resolve/refs%2Fpr%2F3/.eval_results/longshotbench.yaml
- Command line
-
hf download hf://Video-R1/Video-R1-7B@refs/pr/3/.eval_results/longshotbench.yaml
-
curl -L -o longshotbench.yaml https://huggingface.co/Video-R1/Video-R1-7B/resolve/refs%2Fpr%2F3/.eval_results/longshotbench.yaml
1.41 kB
| - dataset: | |
| id: MBZUAI/longshot-bench | |
| task_id: overall | |
| value: 26.88 | |
| source: | |
| url: https://longshot.cvmbzuai.com/leaderboard | |
| name: LongShOTBench official results | |
| user: MBZUAI | |
| notes: 'Rubric-weighted score (0-100), LLM judge Qwen3-14B; model input: Video.' | |
| - dataset: | |
| id: MBZUAI/longshot-bench | |
| task_id: core_perception | |
| value: 22.36 | |
| source: | |
| url: https://longshot.cvmbzuai.com/leaderboard | |
| name: LongShOTBench official results | |
| user: MBZUAI | |
| notes: 'Rubric-weighted score (0-100), LLM judge Qwen3-14B; model input: Video.' | |
| - dataset: | |
| id: MBZUAI/longshot-bench | |
| task_id: reasoning | |
| value: 28.58 | |
| source: | |
| url: https://longshot.cvmbzuai.com/leaderboard | |
| name: LongShOTBench official results | |
| user: MBZUAI | |
| notes: 'Rubric-weighted score (0-100), LLM judge Qwen3-14B; model input: Video.' | |
| - dataset: | |
| id: MBZUAI/longshot-bench | |
| task_id: information | |
| value: 25.0 | |
| source: | |
| url: https://longshot.cvmbzuai.com/leaderboard | |
| name: LongShOTBench official results | |
| user: MBZUAI | |
| notes: 'Rubric-weighted score (0-100), LLM judge Qwen3-14B; model input: Video.' | |
| - dataset: | |
| id: MBZUAI/longshot-bench | |
| task_id: multimodal | |
| value: 31.57 | |
| source: | |
| url: https://longshot.cvmbzuai.com/leaderboard | |
| name: LongShOTBench official results | |
| user: MBZUAI | |
| notes: 'Rubric-weighted score (0-100), LLM judge Qwen3-14B; model input: Video.' | |