|
--- |
|
language: |
|
- en |
|
tags: |
|
- openvino |
|
--- |
|
|
|
# t5-small-ov |
|
|
|
This is the [t5-small](https://huggingface.co/t5-small) model converted to [OpenVINO](https://openvino.ai), for accellerated inference. |
|
|
|
The model weights are compressed to FP16. |
|
|
|
An example of how to do inference on this model, based on the [T5 documentation](https://huggingface.co/docs/transformers/model_doc/t5#transformers.T5Model): |
|
|
|
```python |
|
from optimum.intel.openvino import OVModelForSeq2SeqLM |
|
from transformers import AutoTokenizer, pipeline |
|
|
|
model_id = "t5-small-ov" |
|
model = OVModelForSeq2SeqLM.from_pretrained(model_id) |
|
tokenizer = AutoTokenizer.from_pretrained(model_id) |
|
input_ids = tokenizer("translate English to German: The house is wonderful.", return_tensors="pt").input_ids |
|
outputs = model.generate(input_ids) |
|
print(tokenizer.decode(outputs[0], skip_special_tokens=True)) |
|
``` |
|
|