Nemotron-4-Mini-Hindi-4B-Base

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load the tokenizer and model
model_path = 'nvidia/Nemotron-4-Mini-Hindi-4B-Base'
tokenizer  = AutoTokenizer.from_pretrained(model_path)

device = 'cuda'
dtype  = torch.bfloat16
model  = AutoModelForCausalLM.from_pretrained(model_path, torch_dtype=dtype, device_map=device)

# Prepare the input text
prompt = 'भारत की राजधानी क्या है?'
inputs = tokenizer.encode(prompt, return_tensors='pt').to(model.device)

# Generate the output
outputs = model.generate(inputs, max_length=15)

# Decode and print the output
output_text = tokenizer.decode(outputs[0])
print(output_text)