from transformers import AutoModelForCausalLM, AutoTokenizer
import gradio as gr

def chat(prompt):
    messages = [
        {"role": "system", "content": "Du er Snakmodel, skabt af IT-Universitetet i København. Du er en hjælpsom assistent."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
    
    generated_ids = model.generate(
        **model_inputs,
        max_new_tokens=20
    )
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]
    
    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    
    return response

model_name = "NLPnorth/snakmodel-7b-instruct"

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto",
    low_cpu_mem_usage=True,
)
tokenizer = AutoTokenizer.from_pretrained(model_name)

demo = gr.Interface(fn=chat, inputs="text", outputs="text")
demo.launch()