app.py

import gradio as gr
import transformers
import torch


def fmt_prompt(prompt: str) -> str:
    return f"""[Instructions]:\n{prompt}\n\n[Response]:"""

#device = "cuda:0"
device = "cpu"


model_name = "abacaj/starcoderbase-1b-sft"
tokenizer = transformers.AutoTokenizer.from_pretrained(model_name)

model = (
    transformers.AutoModelForCausalLM.from_pretrained(
        model_name,
    )
    .to(device)
    .eval()
)


def respond(message, chat_history):
    
    #prompt = "Write a python function to sort the following array in ascending order, don't use any built in sorting methods: [9,2,8,1,5]"
    prompt_input = fmt_prompt(message)
    inputs = tokenizer(prompt_input, return_tensors="pt").to(model.device)
    input_ids_cutoff = inputs.input_ids.size(dim=1)

    with torch.no_grad():
        generated_ids = model.generate(
            **inputs,
            use_cache=True,
            max_new_tokens=512,
            temperature=0.2,
            top_p=0.95,
            do_sample=True,
            eos_token_id=tokenizer.eos_token_id,
            pad_token_id=tokenizer.pad_token_id,
        )

    completion = tokenizer.decode(
        generated_ids[0][input_ids_cutoff:],
        skip_special_tokens=True,
    )
    chat_history.append((message, completion))
    time.sleep(2)
    return "", chat_history

with gr.Blocks() as app:

    chatbot = gr.Chatbot()
    msg = gr.Textbox("Input")
    clear = gr.ClearButton([msg, chatbot])

    msg.submit(respond, [msg, chatbot], [msg, chatbot])


app.launch()