from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
model = AutoModelForCausalLM.from_pretrained(
    "Girinath11/recursive-language-model-198m",
    trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained(
    "Girinath11/recursive-language-model-198m",
    trust_remote_code=True
)
device = "cuda" if torch.cuda.is_available() else "cpu"
model = model.to(device)
model.eval()
print(f"✅ Model loaded on {device}")
print(f"📊 Parameters: {sum(p.numel() for p in model.parameters()):,}\n")
def chat(question, max_new_tokens=150, temperature=0.7, top_p=0.9):
    prompt = f"<|user|>\n{question}\n<|assistant|>\n"
    inputs = tokenizer(
        prompt,
        return_tensors="pt",
        add_special_tokens=False
    ).to(device)
    with torch.no_grad():
        outputs = model.generate(
            inputs['input_ids'],
            max_new_tokens=max_new_tokens,
            temperature=temperature,
            top_p=top_p,
            do_sample=True,
        )
    full_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
    if "<|assistant|>" in full_text:
        response = full_text.split("<|assistant|>")[-1].strip()
    else:
        response = full_text.replace(question, "").strip()

    return response
questions = [
    "What is machine learning?",
    "What is Python programming?",
    "Explain neural networks simply",
    "What is artificial intelligence?",
]
for q in questions:
    print(f"\n❓ {q}")
    print(f"💬 {chat(q)}")