README.md

metadata

{}

Tradutor

A translation system from English to European Portuguese.

Usage

Using the pipeline

from transformers import pipeline

translator = pipeline("text-generation", model="liaad/Tradutor")

text = "Hello, how are you?"
chat = [
        {
            "role": "system",
            "content": "You are a translator from English to European Portuguese",
    },
    {
        "role": "user",
        "content": f"Translate this text from English to European Portuguese: {text}",
    },
]

translated_text = translator(
    chat, 
    max_length=1024,
    pad_token_id=translator.model.config.eos_token_id  # Not necessary. Just to avoid warning.
)

print(translated_text[-1]["generated_text"][-1]["content"])

Using model and tokenizer

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer


model_name = "liaad/Tradutor"
max_length = 1024

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    device_map="auto",
    torch_dtype=torch.bfloat16,
)


text = "Hello, how are you?"
chat = [
    {
        "role": "system",
        "content": "You are a translator from English to European Portuguese",
    },
    {
        "role": "user",
        "content": f"Translate this text from English to European Portuguese: {text}",
    },
]

input_ids = tokenizer.apply_chat_template(
    chat,
    add_generation_prompt=True,
    tokenize=True,
    return_tensors="pt",
    max_length=max_length,
)

output_ids = model.generate(
    input_ids,
    max_length=max_length,
    num_return_sequences=1,
    pad_token_id=tokenizer.eos_token_id,
)

generated_ids = output_ids[0, input_ids.shape[1] :]
translated_text = tokenizer.decode(generated_ids, skip_special_tokens=True)

print(translated_text.strip())