| library_name: transformers | |
| license: apache-2.0 | |
| datasets: | |
| - HuggingFaceM4/the_cauldron | |
| - HuggingFaceM4/Docmatix | |
| - lmms-lab/LLaVA-OneVision-Data | |
| - lmms-lab/M4-Instruct-Data | |
| - HuggingFaceFV/finevideo | |
| - MAmmoTH-VL/MAmmoTH-VL-Instruct-12M | |
| - lmms-lab/LLaVA-Video-178K | |
| - orrzohar/Video-STaR | |
| - Mutonix/Vript | |
| - TIGER-Lab/VISTA-400K | |
| - Enxin/MovieChat-1K_train | |
| - ShareGPT4Video/ShareGPT4Video | |
| pipeline_tag: image-text-to-text | |
| language: | |
| - en | |
| base_model: HuggingFaceTB/SmolVLM2-500M-Video-Instruct | |
| tags: | |
| - openvino | |
| - nncf | |
| - 8-bit | |
| This model is a quantized version of [`HuggingFaceTB/SmolVLM2-500M-Video-Instruct`](https://huggingface.co/HuggingFaceTB/SmolVLM2-500M-Video-Instruct) and is converted to the OpenVINO format. This model was obtained via the [nncf-quantization](https://huggingface.co/spaces/echarlaix/nncf-quantization) space with [optimum-intel](https://github.com/huggingface/optimum-intel). | |
| First make sure you have `optimum-intel` installed: | |
| ```bash | |
| pip install optimum[openvino] | |
| ``` | |
| To load your model you can do as follows: | |
| ```python | |
| from optimum.intel import OVModelForVisualCausalLM | |
| model_id = "echarlaix/SmolVLM2-500M-Video-Instruct-openvino-8bit-woq-data-free" | |
| model = OVModelForVisualCausalLM.from_pretrained(model_id) | |
| ``` | |