File size: 2,094 Bytes
32161b2 2d8b72c 32161b2 5790f62 e3e0fa5 7e7729e 5790f62 d2086ac 5790f62 d2086ac 5790f62 2d8b72c 5790f62 2d8b72c 5790f62 7e7729e 5790f62 2d8b72c 5790f62 2d8b72c 0663176 5790f62 0663176 5790f62 2d8b72c 32161b2 5790f62 |
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 60 61 |
import gradio as gr
from huggingface_hub import InferenceClient
# Replace this with the name of your merged model on Hugging Face
MERGED_MODEL_REPO = "Grandediw/lora-model_finetuned"
# Initialize the Inference Client with your merged model
client = InferenceClient(MERGED_MODEL_REPO)
# The guide uses a mini_chatbot function that accepts `message` and `history`.
# We'll follow that pattern. We'll also introduce a system message for role context if needed.
def mini_chatbot(message, history):
"""
This function simulates a conversation with the model. It takes the latest user message
and the full conversation history, builds a prompt, and returns the model's response.
"""
# We can set a system message to define the assistant's behavior.
system_message = "You are a helpful and friendly assistant."
# Build the conversation prompt:
# history is a list of (user_message, assistant_message) tuples.
# We'll format it similarly to how we did before:
prompt = system_message.strip() + "\n\n"
for user_msg, assistant_msg in history:
if user_msg:
prompt += f"User: {user_msg}\n"
if assistant_msg:
prompt += f"Assistant: {assistant_msg}\n"
prompt += f"User: {message}\nAssistant:"
# Set generation parameters (you can adjust as needed or add sliders)
max_tokens = 200
temperature = 0.7
top_p = 0.9
# Use text_generation to get the response
response = ""
for partial in client.text_generation(
prompt=prompt,
max_new_tokens=max_tokens,
temperature=temperature,
top_p=top_p,
stream=True
):
token = partial.token.text
response += token
return response
# Create a Gradio ChatInterface similar to the guide:
# Gradio will handle the `history` automatically, and pass (message, history) to mini_chatbot.
demo_chatbot = gr.ChatInterface(
fn=mini_chatbot,
title="My Chatbot",
description="Enter text to start chatting with the merged LoRA model."
)
if __name__ == "__main__":
demo_chatbot.launch()
|