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
| { | |
| "_name_or_path": "perception_decision", | |
| "architectures": [ | |
| "Decision" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "checkpoint_format_version": 2, | |
| "eos_token_id": 151645, | |
| "hidden_act": "silu", | |
| "hidden_size": 1536, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 8960, | |
| "max_position_embeddings": 32768, | |
| "model_type": "dispider_decision", | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 28, | |
| "num_key_value_heads": 2, | |
| "perception_vision_tower": "vision_tower", | |
| "perception_hidden_size": 1024, | |
| "perception_projector_type": "pool", | |
| "perception_select_feature": "patch", | |
| "perception_select_layer": -2, | |
| "pool_num": 4, | |
| "resolution": 64, | |
| "rms_norm_eps": 1e-06, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": null, | |
| "tie_word_embeddings": true, | |
| "tokenizer_model_max_length": 32768, | |
| "tokenizer_padding_side": "right", | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.41.2", | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 151936 | |
| } | |