Spaces:
Sleeping
Sleeping
File size: 1,713 Bytes
fbebf66 dde614e da4d45a fbebf66 70f8d75 fbebf66 70f8d75 dde614e fbebf66 da4d45a f599e3d dde614e fbebf66 70f8d75 cb9d075 fbebf66 dde614e da4d45a 70f8d75 fbebf66 70f8d75 fbebf66 70f8d75 fbebf66 70f8d75 fbebf66 70f8d75 b19dc43 67e38fa f599e3d |
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 |
import gradio as gr
import torch
import asyncio
from src.model.him_model import HIMModel
from config.model_config import HIMConfig
from config.environment_config import EnvironmentConfig
def initialize_model():
model_config = HIMConfig()
env_config = EnvironmentConfig()
device = torch.device("cuda" if torch.cuda.is_available() and env_config.device == "cuda" else "cpu")
model = HIMModel(model_config).to(device)
return model
async def chat(message: str,
system_message: str = "You are a friendly Chatbot.",
max_tokens: int = 512,
temperature: float = 0.7,
top_p: float = 0.95):
input_data = {
"message": message,
"system_message": system_message,
"parameters": {
"max_tokens": max_tokens,
"temperature": temperature,
"top_p": top_p
}
}
with torch.no_grad():
result = await model.generate_response(input_data)
return result["response"]
model = initialize_model()
interface = gr.Interface(
fn=chat,
inputs=[
gr.Textbox(label="Message"),
gr.Textbox(label="System Message", value="You are a friendly Chatbot."),
gr.Slider(minimum=1, maximum=2048, value=512, label="Max Tokens"),
gr.Slider(minimum=0.1, maximum=1.0, value=0.7, label="Temperature"),
gr.Slider(minimum=0.1, maximum=1.0, value=0.95, label="Top P")
],
outputs=gr.Textbox(label="HIM Response"),
title="Hybrid Intelligence Matrix (HIM)",
description="Interact with the HIM system for advanced cognitive processing"
)
if __name__ == "__main__":
interface.launch(server_name="0.0.0.0", server_port=7860)
|