Video-Text-to-Text
Transformers
Safetensors
English
videochat_flash_qwen
feature-extraction
multimodal
custom_code
Eval Results (legacy)
Instructions to use MInference/videochat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MInference/videochat with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("MInference/videochat", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
File size: 293 Bytes
14936a3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 | CONTROLLER_HEART_BEAT_EXPIRATION = 30
WORKER_HEART_BEAT_INTERVAL = 15
LOGDIR = "."
# Model Constants
IGNORE_INDEX = -100
IMAGE_TOKEN_INDEX = -200
DEFAULT_IMAGE_TOKEN = "<image>"
DEFAULT_IMAGE_PATCH_TOKEN = "<im_patch>"
DEFAULT_IM_START_TOKEN = "<im_start>"
DEFAULT_IM_END_TOKEN = "<im_end>"
|