Scripts/Inference_safetensors.py

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# Insert your research topic here
RESEARCH_TOPIC = """

"""

def load_model(model_path):
    model = AutoModelForCausalLM.from_pretrained(
        model_path,
        torch_dtype=torch.float16,
        device_map="auto"
    )
    
    tokenizer = AutoTokenizer.from_pretrained(model_path)
    
    return model, tokenizer

def generate_response(model, tokenizer, topic):
    topic = topic.strip()
    
    prompt = f"USER: Research Topic: \"{topic}\"\nLet's think step by step:\nASSISTANT:"
    
    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
    
    outputs = model.generate(
        **inputs,
        max_new_tokens=2500,
        temperature=0.7,
        top_p=0.9,
        repetition_penalty=1.1,
        do_sample=True
    )
    
    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
    
    return response.split("ASSISTANT:")[-1].strip()

def run():
    model_path = "./" # Path to the directory containing your model weight files
    
    model, tokenizer = load_model(model_path)
    
    result = generate_response(model, tokenizer, RESEARCH_TOPIC)
    
    print(result)

if __name__ == "__main__":
    run()