from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model = AutoModelForCausalLM.from_pretrained("Sigmafox/qwen2.5-0.5B-finance-summarizer")
tokenizer = AutoTokenizer.from_pretrained("Sigmafox/qwen2.5-0.5B-finance-summarizer")

messages = [
    {"role": "system", "content": "You are a financial analyst. Summarize financial news clearly."},
    {"role": "user", "content": "Summarize this financial news headline: Apple reports record quarterly earnings"},
]

text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt")

with torch.no_grad():
    outputs = model.generate(**inputs, max_new_tokens=150, temperature=0.7, do_sample=True)

print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))