app1.py

from huggingface_hub import InferenceClient
import gradio as gr

client = InferenceClient("""K00B404/BagOMistral_14X_Coders-ties-7B"""))

def format_prompt(message, history, model):
  prompt = f"[INST] {message} [/INST]"
  for user_prompt, bot_response in history:
    prompt += f"[INST] {user_prompt} [/”"
    prompt += f" {bot_response} [/”"
    prompt = f"[MODEL] {model} [/”" + prompt
  return prompt

def generate(prompt, history, temperature=0.2, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0, model="BagOMistral_14X_Coders-ties-7B"):
    temperature = float(temperature)
    if temperature < 1e-2:
        temperature = 1e-2
    top_p = float(top_p)

    generate_kwargs = dict(
        temperature=temperature,
        max_new_tokens=max_new_tokens,
        top_p=top_p,
        repetition_penalty=repetition_penalty,
        do_sample=True,
        seed=42,
    )

    formatted_prompt = format_prompt(prompt, history, model)

    stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
    output = ""

    for response in stream:
        output += response.token.text
        yield output
    return output

mychatbot = gr.Chatbot(avatar_images=["./user.png", "./botm.png"], bubble_full_width=False, show_label=False, show_copy_button=True, likeable=True)

model_options = ["BagOMistral_14X_Coders-ties-7B", "Model2", "Model3", "Model4", "Model5", "Model6", "Model7"]

demo = gr.ChatInterface(fn=generate, 
                        chatbot=mychatbot,
                        title="K00B404's Merged Models Test Chat",
                        retry_btn=None,
                        undo_btn=None,
                        inputs=["text", "history", "temperature", "max_new_tokens", "top_p", "repetition_penalty", "model"],
                        inputs_types={"model": "dropdown", "text": "text", "history": "text", "temperature": "number", "max_new_tokens": "number", "top_p": "number", "repetition_penalty": "number"},
                        input_labels={"model": "Select Model", "text": "Enter Prompt", "history": "Chat History", "temperature": "Temperature", "max_new_tokens": "Max New Tokens", "top_p": "Top P", "repetition_penalty": "Repetition Penalty"},
                        input_options={"model": model_options})

demo.queue().launch(show_api=False)