app.py

'''import gradio as gr
from huggingface_hub import InferenceClient

"""
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")


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()'''
#!pip install -U "transformers==4.40.0" --upgrade
#!pip install -i https://pypi.org/simple/ bitsandbytes
#!pip install accelerate

import transformers
import torch

model_id = "unsloth/llama-3-8b-Instruct-bnb-4bit"

pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={
        "torch_dtype": torch.float16,
        "quantization_config": {"load_in_4bit": True},
        "low_cpu_mem_usage": True,
    },
)

messages = [
    {"role"   : "system",
     "content": "You are an interviewer testing the user whether he can be a good manager or not. When the user says hi there!, i want you to begin"},
    {"role"   : "user",
     "content": """hi there!"""},
]

prompt = pipeline.tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
)

terminators = [
    pipeline.tokenizer.eos_token_id,
    pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
]

outputs = pipeline(
    prompt,
    max_new_tokens=256,
    eos_token_id=terminators,
    do_sample=True,
    temperature=0.6,
    top_p=0.9,
)

print(outputs[0]["generated_text"][len(prompt):])

#!pip install gradio

import gradio as gr

messages = [{"role"   : "system",
     "content": "You are an interviewer testing the user whether he can be a good manager or not.  When the user says hi there!, i want you to begin"},
    {"role"   : "user",
     "content": """hi there!"""},]

def add_text(history, text):
    global messages  #message[list] is defined globally
    history = history + [(text,'')]
    messages = messages + [{"role":'user', 'content': text}]
    return history, ''

def generate(history):
  global messages
  prompt = pipeline.tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
)

  terminators = [
    pipeline.tokenizer.eos_token_id,
    pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
]

  outputs = pipeline(
    prompt,
    max_new_tokens=256,
    eos_token_id=terminators,
    do_sample=True,
    temperature=0.6,
    top_p=0.9,
)
  response_msg = outputs[0]["generated_text"][len(prompt):]
  for char in response_msg:
      history[-1][1] += char
      yield history
  pass

with gr.Blocks() as demo:

    chatbot = gr.Chatbot(value=[], elem_id="chatbot")
    with gr.Row():
            txt = gr.Textbox(
                show_label=False,
                placeholder="Enter text and press enter",
            )

    txt.submit(add_text, [chatbot, txt], [chatbot, txt], queue=False).then(
            generate, inputs =[chatbot,],outputs = chatbot,)

demo.queue()
demo.launch(debug=True)