app.py

from __future__ import annotations
import gradio as gr
import time
from ctransformers import AutoModelForCausalLM
from typing import Iterable
import gradio as gr
from gradio.themes.base import Base
from gradio.themes.utils import colors, fonts, sizes
import subprocess

from huggingface_hub import hf_hub_download

# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
model = AutoModelForCausalLM.from_pretrained("s3nh/PY007-TinyLlama-1.1B-Chat-v0.2-GGUF", model_file="PY007-TinyLlama-1.1B-Chat-v0.2.Q4_K_M.gguf", gpu_layers=0)
ins = '''
'''


theme = gr.themes.Monochrome(
    primary_hue="indigo",
    secondary_hue="blue",
    neutral_hue="slate",
    radius_size=gr.themes.sizes.radius_sm,
    font=[gr.themes.GoogleFont("Open Sans"), "ui-sans-serif", "system-ui", "sans-serif"],
)
def response(question):
    res = model(ins.format(question))
    yield res


examples = [
    "Hello!"
]

def process_example(args):
    for x in response(args):
        pass
    return x
    
css = ".generating {visibility: hidden}"

# Based on the gradio theming guide and borrowed from https://huggingface.co/spaces/shivi/dolly-v2-demo
class SeafoamCustom(Base):
    def __init__(
        self,
        *,
        primary_hue: colors.Color | str = colors.emerald,
        secondary_hue: colors.Color | str = colors.blue,
        neutral_hue: colors.Color | str = colors.blue,
        spacing_size: sizes.Size | str = sizes.spacing_md,
        radius_size: sizes.Size | str = sizes.radius_md,
        font: fonts.Font
        | str
        | Iterable[fonts.Font | str] = (
            fonts.GoogleFont("Quicksand"),
            "ui-sans-serif",
            "sans-serif",
        ),
        font_mono: fonts.Font
        | str
        | Iterable[fonts.Font | str] = (
            fonts.GoogleFont("IBM Plex Mono"),
            "ui-monospace",
            "monospace",
        ),
    ):
        super().__init__(
            primary_hue=primary_hue,
            secondary_hue=secondary_hue,
            neutral_hue=neutral_hue,
            spacing_size=spacing_size,
            radius_size=radius_size,
            font=font,
            font_mono=font_mono,
        )
        super().set(
            button_primary_background_fill="linear-gradient(90deg, *primary_300, *secondary_400)",
            button_primary_background_fill_hover="linear-gradient(90deg, *primary_200, *secondary_300)",
            button_primary_text_color="white",
            button_primary_background_fill_dark="linear-gradient(90deg, *primary_600, *secondary_800)",
            block_shadow="*shadow_drop_lg",
            button_shadow="*shadow_drop_lg",
            input_background_fill="zinc",
            input_border_color="*secondary_300",
            input_shadow="*shadow_drop",
            input_shadow_focus="*shadow_drop_lg",
        )


seafoam = SeafoamCustom()


with gr.Blocks(theme=seafoam, analytics_enabled=False, css=css) as demo:
    with gr.Column():
        gr.Markdown(
            """ ## Shi-Ci Extensional Analyzer
            
            Type in the box below and click the button to generate answers to your most pressing questions!
            
      """
        )

        with gr.Row():
    
            with gr.Column(scale=3):
                instruction = gr.Textbox(placeholder="Enter your question here", label="Question", elem_id="q-input")

                with gr.Box():
                    gr.Markdown("**Answer**")
                    output = gr.Markdown(elem_id="q-output")
                submit = gr.Button("Generate", variant="primary")
                gr.Examples(
                    examples=examples,
                    inputs=[instruction],
                    cache_examples=True,
                    fn=process_example,
                    outputs=[output],
                )
        


    submit.click(response, inputs=[instruction], outputs=[output])
    instruction.submit(response, inputs=[instruction], outputs=[output])

demo.queue(concurrency_count=1).launch(debug=False,share=True)