metadata

library_name: transformers
license: apache-2.0
language:
  - mn

Model Card for Model ID

Model Details

Model Description

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: [Sainbayar B. (Б. Сайнбаяр) https://www.instagram.com/only_sainaa/]
Funded by [optional]: [More Information Needed]
Shared by [optional]: [More Information Needed]
Model type: [Mongolian Cyrillic to Traditional Mongolian Script conversion (Монгол кириллээс монгол бичиг рүү хөрвүүлэгч загвар)]
Language(s) (NLP): [Mongolian /Монгол/]
License: [More Information Needed]
Finetuned from model [google-t5-small]: [More Information Needed]

#Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("onlysainaa/cyrillic_to_script-t5-model")
model = AutoModelForSeq2SeqLM.from_pretrained("onlysainaa/cyrillic_to_script-t5-model")

#Check if CUDA (GPU) is available
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

#Move the model to the same device (GPU or CPU)
model.to(device)

#Prepare text input
input_text = "сайн уу"  #Mongolian greeting

#Tokenize the input text
inputs = tokenizer(input_text, return_tensors="pt")

#Move the input tensors to the same device as the model
inputs = {k: v.to(device) for k, v in inputs.items() if k in ['input_ids', 'attention_mask']}

#Generate translation
outputs = model.generate(**inputs)

#Decode the output to human-readable text
translated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)

#Print the translated text
print(f"Translated Text: {translated_text}")