from transformers import AutoModelForCausalLM, AutoTokenizer

checkpoint_name="ArmelR/starcoder-gradio-v0"
model = AutoModelForCausalLM.from_pretrained(checkpoint_name)
tokenizer = AutoTokenizer.from_pretrained(checkpoint_name)
def generate_text(inp):
    prompt = "Create a gradio application that help to convert temperature in celcius into temperature in Fahrenheit"
    inputs = tokenizer(f"Question: {prompt}\n\nAnswer: ", return_tensors="pt")

    outputs = model.generate(
      inputs["input_ids"],
      temperature=0.2,
      top_p=0.95,
      max_new_tokens=200
    )

    input_len=len(inputs["input_ids"])
    print(tokenizer.decode(outputs[0][input_len:]))

output_text = gr.outputs.Textbox()
gr.Interface(generate_text,"textbox",output_text,title="Text Generation machine ",description="Ask any question. Note: It can take 20-60 seconds to generate output based on your internet connection.").launch()