Video-Text-to-Text
Transformers
Safetensors
English
qwen2_5_vl
image-text-to-text
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:
# 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 generation_config.json from Video-R1/Video-R1-7B: direct link, hf CLI and curl.
- Browser
- Download file 317 Bytes
-
https://huggingface.co/Video-R1/Video-R1-7B/resolve/refs%2Fpr%2F1/generation_config.json
- Command line
-
hf download hf://Video-R1/Video-R1-7B@refs/pr/1/generation_config.json
-
curl -L -o generation_config.json https://huggingface.co/Video-R1/Video-R1-7B/resolve/refs%2Fpr%2F1/generation_config.json
317 Bytes
| { | |
| "attn_implementation": "flash_attention_2", | |
| "bos_token_id": 151643, | |
| "do_sample": true, | |
| "eos_token_id": [ | |
| 151645, | |
| 151643 | |
| ], | |
| "pad_token_id": 151643, | |
| "repetition_penalty": 1.05, | |
| "temperature": 0.1, | |
| "top_k": 1, | |
| "top_p": 0.001, | |
| "transformers_version": "4.49.0.dev0", | |
| "use_cache": false | |
| } | |