Spaces:
Sleeping
Sleeping
File size: 2,514 Bytes
9c9ed59 743d1bd 1e3869c 1854dfd 99d9e8c 9c9ed59 579a255 1854dfd 1e3869c 579a255 755b97f 579a255 8bf7783 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 |
import gradio as gr
from huggingface_hub import InferenceClient
# Initialize the InferenceClient
client = InferenceClient("mistralai/Mixtral-8x7B-Instruct-v0.1")
def format_prompt(message, history):
prompt = "<s>"
for user_prompt, bot_response in history:
prompt += f"[INST] {user_prompt} [/INST]"
prompt += f" {bot_response}</s> "
prompt += f"[INST] {message} [/INST]"
return prompt
def generate(prompt, history, system_prompt, temperature=0.9, max_new_tokens=9048, top_p=0.95, repetition_penalty=1.0):
temperature = max(float(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(f"{system_prompt}, {prompt}", history)
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
# Define inputs (user interface elements)
system_prompt_input = gr.Textbox(label="System Prompt", max_lines=1, interactive=True)
slider_temperature = gr.Slider(label="Temperature", value=0.9, minimum=0.0, maximum=1.0, step=0.05, interactive=True, info="Higher values produce more diverse outputs")
slider_max_tokens = gr.Slider(label="Max new tokens", value=9048, minimum=256, maximum=9048, step=64, interactive=True, info="The maximum numbers of new tokens")
slider_top_p = gr.Slider(label="Top-p (nucleus sampling)", value=0.90, minimum=0.0, maximum=1, step=0.05, interactive=True, info="Higher values sample more low-probability tokens")
slider_repetition_penalty = gr.Slider(label="Repetition penalty", value=1.2, minimum=1.0, maximum=2.0, step=0.05, interactive=True, info="Penalize repeated tokens")
inputs = [system_prompt_input] + [slider_temperature, slider_max_tokens, slider_top_p, slider_repetition_penalty]
# Define output (generated text)
output_text = gr.Textbox(label="Output")
# Create the Gradio interface
gr.Interface(
fn=generate,
chatbot=gr.Chatbot(show_label=True, show_share_button=True, show_copy_button=True, likeable=True, layout="panel"),
inputs=inputs,
outputs=output_text,
title="ConvoLite",
description="Remember! The AI might give incorrect information about people, locations, history, etc...",
concurrency_limit=20,
theme=gr.themes.Soft()
).launch(show_api=False,)
|