---
license: mit
datasets:
- databricks/databricks-dolly-15k
language:
- en
tags:
- openvino
pipeline_tag: text-generation
---

# databricks/dolly-v2-3b

This is the [databricks/dolly-v2-3b](https://huggingface.co/databricks/dolly-v2-3b) model converted to [OpenVINO](https://openvino.ai), for accellerated inference.

An example of how to do inference on this model:
```python
from optimum.intel.openvino import OVModelForCausalLM
from transformers import AutoTokenizer, pipeline

# model_id should be set to either a local directory or a model available on the HuggingFace hub.
model_id = "katuni4ka/dolly-v2-3b-ov"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = OVModelForCausalLM.from_pretrained(model_id)
pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
result = pipe("hello world")
print(result)
```

More detailed example how to use model in instruction following scenario, can be found in this [notebook](https://github.com/openvinotoolkit/openvino_notebooks/tree/main/notebooks/240-dolly-2-instruction-following)