Spaces:
Sleeping
Sleeping
File size: 1,513 Bytes
cc5b602 6f619d7 d381360 6386510 3eed0af 51a7d9e 3eed0af 6386510 d381360 51a7d9e d381360 0a751e6 e6367a7 0a751e6 f5942e7 0a751e6 e59867b 0a751e6 51a7d9e 0a751e6 |
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 |
import os
import time
import spaces
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
import gradio as gr
from threading import Thread
MODEL_LIST = ["mistralai/Mistral-Nemo-Instruct-2407"]
HF_TOKEN = os.environ.get("HF_TOKEN", None)
MODEL = os.environ.get("MODEL_ID")
# filename: gradio_app.py
import gradio as gr
from huggingface_hub import InferenceClient
# Initialize the InferenceClient
client = InferenceClient(
MODEL,
token=HF_TOKEN,
)
def chat_with_model(system_prompt, user_message):
# Prepare messages for the chat completion
messages = [
{"role": "system", "content": system_prompt},
{"role": "user", "content": user_message}
]
# Collect the response from the model
response = ""
for message in client.chat_completion(
messages=messages,
max_tokens=500,
stream=True
):
response += message.choices[0].delta.content
return response
# Create the Gradio interface
iface = gr.Interface(
fn=chat_with_model,
inputs=[
gr.Textbox(label="System Prompt", placeholder="Enter the system prompt here..."),
gr.Textbox(label="User Message", placeholder="Ask a question..."),
],
outputs=gr.Textbox(label="Response"),
title="Mistral Chatbot",
description="Chat with Mistral model using your own system prompts."
)
# Launch the app
if __name__ == "__main__":
iface.launch(show_api=True, share=False,show_error=True) |