ColorfulAI
/

videollamb-llava-1.5-7b

Video-Text-to-Text

Inference Endpoints

Model card Files Files and versions Community

Edit model card

Paper: https://huggingface.co/papers/2409.01071

Downloads last month: 23

Safetensors

Model size

7.48B params

Tensor type

BF16

·

Inference API

Video-Text-to-Text

Inference API (serverless) does not yet support transformers models for this pipeline type.

Datasets used to train ColorfulAI/videollamb-llava-1.5-7b