Flan T5 Base Opus En Id Id En

🚀 flan-t5-base-opus-en-id-id-en

This model serves as a translator specifically for multimodal translation between Indonesian and English, offering a practical solution for language conversion tasks between these two languages.

🚀 Quick Start

This model is a language model designed for translating between English and Indonesian. Below are some usage examples to help you get started.

✨ Features

• Multilingual Translation: Specialized in translating between English and Indonesian.
• Multiple Running Environments: Can run on both CPU and GPU, and supports different precision modes on GPU.

📦 Installation

To use this model, you need to install the transformers library. You can install it using the following command:

pip install transformers

If you want to run the model on GPU, you also need to install accelerate and bitsandbytes (for INT8 precision):

pip install accelerate
pip install bitsandbytes

💻 Usage Examples

Basic Usage

Running the model on a CPU

from transformers import T5Tokenizer, T5ForConditionalGeneration
tokenizer = T5Tokenizer.from_pretrained("muvazana/flan-t5-base-opus-en-id-id-en")
model = T5ForConditionalGeneration.from_pretrained("muvazana/flan-t5-base-opus-en-id-id-en")
input_text = "translate English to Indonesia: How old are you?"
input_ids = tokenizer(input_text, return_tensors="pt").input_ids
outputs = model.generate(input_ids)
print(tokenizer.decode(outputs[0]))

Running the model on a GPU

# pip install accelerate
from transformers import T5Tokenizer, T5ForConditionalGeneration
tokenizer = T5Tokenizer.from_pretrained("muvazana/flan-t5-base-opus-en-id-id-en")
model = T5ForConditionalGeneration.from_pretrained("muvazana/flan-t5-base-opus-en-id-id-en", device_map="auto")
input_text = "translate English to Indonesia: How old are you?"
input_ids = tokenizer(input_text, return_tensors="pt").input_ids.to("cuda")
outputs = model.generate(input_ids)
print(tokenizer.decode(outputs[0]))

Advanced Usage

Running the model on a GPU using FP16 precision

# pip install accelerate
import torch
from transformers import T5Tokenizer, T5ForConditionalGeneration
tokenizer = T5Tokenizer.from_pretrained("muvazana/flan-t5-base-opus-en-id-id-ene")
model = T5ForConditionalGeneration.from_pretrained("muvazana/flan-t5-base-opus-en-id-id-en", device_map="auto", torch_dtype=torch.float16)
input_text = "translate English to Indonesia: How old are you?"
input_ids = tokenizer(input_text, return_tensors="pt").input_ids.to("cuda")
outputs = model.generate(input_ids)
print(tokenizer.decode(outputs[0]))

Running the model on a GPU using INT8 precision

# pip install bitsandbytes accelerate
from transformers import T5Tokenizer, T5ForConditionalGeneration
tokenizer = T5Tokenizer.from_pretrained("muvazana/flan-t5-base-opus-en-id-id-en")
model = T5ForConditionalGeneration.from_pretrained("muvazana/flan-t5-base-opus-en-id-id-en", device_map="auto", load_in_8bit=True)
input_text = "translate English to Indonesia: How old are you?"
input_ids = tokenizer(input_text, return_tensors="pt").input_ids.to("cuda")
outputs = model.generate(input_ids)
print(tokenizer.decode(outputs[0]))

📚 Documentation

Model Details

Model Description

Training results

Framework versions

• Transformers 4.29.2
• Pytorch 2.0.1
• Datasets 2.13.1
• Tokenizers 0.13.3

📄 License

This model is licensed under the Apache 2.0 license.