nllb-en-kn-v1

import torch
from peft import PeftModel, PeftConfig
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

# 1. Load Base Model and Tokenizer
base_model_id = "facebook/nllb-200-distilled-600M"
adapter_model_id = "rajaykumar12959/nllb-en-kn-v1" # Replace with your specific repo name

tokenizer = AutoTokenizer.from_pretrained(base_model_id, src_lang="eng_Latn", tgt_lang="kan_Knda")
base_model = AutoModelForSeq2SeqLM.from_pretrained(
    base_model_id,
    torch_dtype=torch.float16,
    device_map="auto"
)

# 2. Load the Fine-tuned Adapter
model = PeftModel.from_pretrained(base_model, adapter_model_id)
model.eval()

# 3. Define Translation Function
def translate(text):
    inputs = tokenizer(text, return_tensors="pt").to(model.device)
    
    with torch.no_grad():
        translated_tokens = model.generate(
            **inputs,
            forced_bos_token_id=tokenizer.convert_tokens_to_ids("kan_Knda"), # Vital for NLLB to target Kannada
            max_length=128,
            num_beams=5,
            early_stopping=True
        )
    return tokenizer.batch_decode(translated_tokens, skip_special_tokens=True)[0]

# 4. Test
input_text = "Machine learning is the future of technology."
print(translate(input_text))