import gradio as gr
model_name = "vijjuk/codegen-350M-mono-python-18k-alpaca"
demo = gr.load(model_name, src="models")

demo.launch()





#import gradio as gr
#from transformers import AutoTokenizer, AutoModelForCausalLM


#base_model = AutoModelForCausalLM.from_pretrained(model_name)
#tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
#tokenizer.pad_token = tokenizer.eos_token
#tokenizer.padding_side = "right"

# def query(instruction, input):
#    prompt = f"""### Instruction:
#        Use the Task below and the Input given to write the Response, which is a programming code that can solve the Task.
#       ### Task:
#        {instruction}
#        ### Input:
#        {input}
#        ### Response:
#        """
#    input_ids = tokenizer(prompt, return_tensors="pt", truncation=True)
#    output_base = base_model.generate(input_ids=input_ids, max_new_tokens=500, do_sample=True, top_p=0.9,temperature=0.5)
#    response = "{tokenizer.batch_decode(output_base.detach().cpu().numpy(), skip_special_tokens=True)[0][len(prompt):]}"
#    return response

#inputs = ["text", "text"]
#outputs = "text"
#iface = gr.Interface(fn=query, inputs=inputs, outputs=outputs)
#iface.launch()