app.py

import gradio as gr
from huggingface_hub import InferenceClient
import chatglm_cpp

def list_files_tree(directory, indent=""):
    items = os.listdir(directory)
    for i, item in enumerate(items):
        prefix = "└── " if i == len(items) - 1 else "├── "
        print(indent + prefix + item)
        item_path = os.path.join(directory, item)
        if os.path.isdir(item_path):
            next_indent = indent + ("    " if i == len(items) - 1 else "│   ")
            list_files_tree(item_path, next_indent)

"""
For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
"""
# client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")

repo_id = "None1145/ChatGLM3-6B-Theresa-GGML"
filename = "ChatGLM3-6B-Theresa-GGML-Q4_0.bin"

huggingface_hub.hf_hub_download(repo_id=repo_id, filename=filename, local_dir="./Models")
list_files_tree("./Models")
import time
time.sleep(10)

pipeline = chatglm_cpp.Pipeline(model, max_length=max_length)


def respond(
    message,
    history: list[tuple[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
):
    messages = [{"role": "system", "content": system_message}]

    for val in history:
        if val[0]:
            messages.append({"role": "user", "content": val[0]})
        if val[1]:
            messages.append({"role": "assistant", "content": val[1]})

    messages.append({"role": "user", "content": message})

    response = ""

    for message in client.chat_completion(
        messages,
        max_tokens=max_tokens,
        stream=True,
        temperature=temperature,
        top_p=top_p,
    ):
        token = message.choices[0].delta.content

        response += token
        yield response


"""
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
"""
demo = gr.ChatInterface(
    respond,
    additional_inputs=[
        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
        gr.Slider(
            minimum=0.1,
            maximum=1.0,
            value=0.95,
            step=0.05,
            label="Top-p (nucleus sampling)",
        ),
    ],
)


if __name__ == "__main__":
    demo.launch()