Video-Text-to-Text
Transformers
Safetensors
arc_hunyuan_video
text-generation
multimodal
video-understanding
video-audio understanding
video-qa
video-captioning
video-grounding
video-reasoning
short video understanding
Instructions to use TencentARC/ARC-Hunyuan-Video-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TencentARC/ARC-Hunyuan-Video-7B with Transformers:
# Load model directly from transformers import AutoModelForSeq2SeqLM model = AutoModelForSeq2SeqLM.from_pretrained("TencentARC/ARC-Hunyuan-Video-7B", dtype="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "added_tokens_decoder": {}, | |
| "clean_up_tokenization_spaces": false, | |
| "eos_token": "<|endoftext|>", | |
| "extra_special_tokens": {}, | |
| "model_max_length": 32768, | |
| "processor_class": "ARCHunyuanVideoProcessor", | |
| "tokenizer_class": "ARCHunyuanVideoTokenizer" | |
| } | |