---
library_name: transformers
license: apache-2.0
---

### Model Description

<!-- Provide a longer summary of what this model is. -->

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.

- **Developed by:** https://github.com/xbmxb/RAG-query-rewriting
- **Model type:** google/t5-large

### Downstream Use [optional]

```from transformers import T5Tokenizer,T5ForConditionalGeneration,BitsAndBytesConfig 
import torch
from google.colab import userdata

os.environ["HUGGINGFACE_TOKEN"] = userdata.get('HF_TOKEN')

quantization_config = BitsAndBytesConfig(
    load_in_8bit=True)

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

model = T5ForConditionalGeneration.from_pretrained('catyung/t5l-turbo-hotpot-0331',
                                quantization_config=quantization_config)

tokenizer = T5Tokenizer.from_pretrained('catyung/t5l-turbo-hotpot-0331')


input_ids = tokenizer(rewrite_prompt, return_tensors="pt").input_ids.to(device)

outputs = model.generate(input_ids,max_new_tokens=50)

result = tokenizer.decode(outputs[0], skip_special_tokens=True)

print(result)

```