Video-Text-to-Text
Transformers
Safetensors
dispider_reaction
video
streaming-video
multimodal
qwen2
cvpr-2025
Instructions to use Mar2Ding/Dispider with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Mar2Ding/Dispider with Transformers:
# Load model directly from transformers import Reaction model = Reaction.from_pretrained("Mar2Ding/Dispider", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download perception_decision/generation_config.json from Mar2Ding/Dispider: direct link, hf CLI and curl.
- Browser
- Download file 242 Bytes
-
https://huggingface.co/Mar2Ding/Dispider/resolve/main/perception_decision/generation_config.json
- Command line
-
hf download hf://Mar2Ding/Dispider/perception_decision/generation_config.json
-
curl -L -o generation_config.json https://huggingface.co/Mar2Ding/Dispider/resolve/main/perception_decision/generation_config.json
242 Bytes
| { | |
| "bos_token_id": 151643, | |
| "do_sample": true, | |
| "eos_token_id": [ | |
| 151645, | |
| 151643 | |
| ], | |
| "pad_token_id": 151643, | |
| "repetition_penalty": 1.1, | |
| "temperature": 0.7, | |
| "top_k": 20, | |
| "top_p": 0.8, | |
| "transformers_version": "4.41.2" | |
| } | |