app.py

import gradio as gr
import os
from huggingface_hub import InferenceClient
from huggingface_hub import hf_hub_download
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"
hf_hub_download(repo_id=repo_id, filename=filename, local_dir=f"./Models/{repo_id}")
model = f"./Models/{repo_id}/{filename}"
max_length = 8192
pipeline = chatglm_cpp.Pipeline(model, max_length=max_length)

messages = []

def respond(
    message,
    history: list[tuple[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
):
    global messages
    
    generation_kwargs = dict(
        max_length=max_length,
        max_context_length=max_tokens,
        do_sample=temperature > 0,
        top_k=0,
        top_p=top_p,
        temperature=temperature,
        repetition_penalty=1.0,
        stream=True,
    )

    if messages == []:
        messages = [chatglm_cpp.ChatMessage(role="system", content=system_message)]

    # for val in history:
    #     if val[0]:
    #         messages.append(chatglm_cpp.ChatMessage(role="user", content=val[0]))
    #     if val[1]:
    #         messages.append(chatglm_cpp.ChatMessage(role="assistant", content=val[0]))

    messages.append(chatglm_cpp.ChatMessage(role="user", content=message))

    response = ""
    chunks = []

    for chunk in pipeline.chat(messages, **generation_kwargs):
        response += chunk.content
        chunks.append(chunk)
        yield response

    messages.append(chatglm_cpp.ChatMessage(role="assistant", content=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()