LLaVA-NeXT-Video OpenVINO Model
This is an OpenVINO optimized version of the LLaVA-NeXT-Video-7B-hf model.
Model Description
- Base Model: llava-hf/LLaVA-NeXT-Video-7B-hf
- Optimization: Converted to OpenVINO format for efficient inference
- Size: ~7B parameters
Usage
from optimum.intel.openvino import OVModelForVisualCausalLM
model = OVModelForVisualCausalLM.from_pretrained("YOUR_USERNAME/llava-next-video-openvino")
License
This model inherits the license from the original LLaVA-NeXT model.
- Downloads last month
- 51
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for ezelanza/llava-next-video-openvino
Base model
llava-hf/LLaVA-NeXT-Video-7B-hf