---
library_name: transformers
license: apache-2.0
pipeline_tag: image-text-to-text
language:
- en
base_model: echarlaix/SmolVLM2-256M-Video-Instruct-openvino
tags:
- openvino
- nncf
- 8-bit
---

This model is a quantized version of [`echarlaix/SmolVLM2-256M-Video-Instruct-openvino`](https://huggingface.co/echarlaix/SmolVLM2-256M-Video-Instruct-openvino) 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/SmolVLM2-256M-Video-Instruct-openvino-8bit-woq-data-free"
model = OVModelForVisualCausalLM.from_pretrained(model_id)
```