from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T"  # Or local path if downloaded
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

# Example: Use a line from your cleaned file as a prompt
with open("skin_disease_articles_clean.txt", "r", encoding="utf-8") as f:
    prompt = f.readline().strip()

inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=100)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))