MISHANM/Maithili_text_generation_Llama3_8B_instruction

 
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Set the device
device = "cuda" if torch.cuda.is_available() else "cpu"

# Load the fine-tuned model and tokenizer
model_path = "MISHANM/MISHANM/Maithili_text_generation_Llama3_8B_instruction"
model = AutoModelForCausalLM.from_pretrained(model_path)

# Wrap the model with DataParallel if multiple GPUs are available
if torch.cuda.device_count() > 1:
    print(f"Using {torch.cuda.device_count()} GPUs")
    model = torch.nn.DataParallel(model)

# Move the model to the appropriate device
model.to(device)

tokenizer = AutoTokenizer.from_pretrained(model_path)

# Function to generate text
def generate_text(prompt, max_length=1000, temperature=0.9):
    # Format the prompt according to the chat template
    messages = [
        {
            "role": "system",
            "content": "You are a Maithili language expert and linguist, with same knowledge give answers in Maithili language. ",
        },
        {"role": "user", "content": prompt}
    ]

    # Apply the chat template
    formatted_prompt = f"<|system|>{messages[0]['content']}<|user|>{messages[1]['content']}<|assistant|>"

    # Tokenize and generate output
    inputs = tokenizer(formatted_prompt, return_tensors="pt").to(device)
    output = model.module.generate(  # Use model.module for DataParallel
        **inputs, max_new_tokens=max_length, temperature=temperature, do_sample=True
    )
    return tokenizer.decode(output[0], skip_special_tokens=True)

# Example usage
prompt = """What is LLM ."""
translated_text = generate_text(prompt)
print(translated_text)

@misc{MISHANM/MISHANM/Maithili_text_generation_Llama3_8B_instruction,
  author = {Mishan Maurya},
  title = {Introducing Fine Tuned LLM for Maithili Language},
  year = {2024},
  publisher = {Hugging Face},
  journal = {Hugging Face repository},
  
}