|
--- |
|
language: |
|
- en |
|
- hi |
|
- multilingual |
|
tags: |
|
- text2text-generation |
|
widget: |
|
- text: What are you doing? |
|
example_title: What are you doing |
|
- text: It is raining heavily. |
|
example_title: It is raining heavily. |
|
- text: How are you? |
|
example_title: How are you? |
|
datasets: |
|
- rvv-karma/English-Hinglish-TOP |
|
license: apache-2.0 |
|
pipeline_tag: text2text-generation |
|
--- |
|
|
|
# English2Hinglish-Flan-T5-Base |
|
|
|
This is a finetuned model of [Flan T5 Base](https://huggingface.co/google/flan-t5-base) with [English-Hinglish-TOP](https://huggingface.co/datasets/rvv-karma/English-Hinglish-TOP) dataset. |
|
|
|
## Usage |
|
```python |
|
# Load model directly |
|
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM |
|
|
|
model_name = "rvv-karma/English2Hinglish-Flan-T5-Base" |
|
tokenizer = AutoTokenizer.from_pretrained(model_name) |
|
model = AutoModelForSeq2SeqLM.from_pretrained(model_name) |
|
|
|
input_text = "What are you doing?" |
|
input_ids = tokenizer(input_text, return_tensors="pt") |
|
output_ids = model.generate(**input_ids) |
|
output_text = tokenizer.decode(output_ids[0], skip_special_tokens=True) |
|
|
|
print(output_text) |
|
``` |
|
|
|
|
|
## Fine-tuning script |
|
|
|
[Google Colaboratory Notebook](https://colab.research.google.com/drive/11fUHem8r8qe_Ildh2_1XjOEY-Zyoy5j8?usp=sharing) |
|
|
|
## References |
|
|
|
[DataCamp](https://www.datacamp.com/tutorial/flan-t5-tutorial) |
