---
base_model: yujiepan/llama-2-tiny-3layers-random
library_name: transformers
pipeline_tag: text-generation
tags:
- openvino
- nncf
- 8-bit
inference: true
widget:
- text: Hello!
  example_title: Hello world
  group: Python
---

This model is a quantized version of [`yujiepan/llama-2-tiny-3layers-random`](https://huggingface.co/yujiepan/llama-2-tiny-3layers-random) 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 OVModelForCausalLM

model_id = "yujiepan/llama-2-tiny-3layers-random-openvino-8bit"
model = OVModelForCausalLM.from_pretrained(model_id)
```