File size: 3,077 Bytes
ab646de fddcd12 ab646de fddcd12 ab646de fddcd12 ab646de fddcd12 ab646de |
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 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 |
import gradio as gr
from huggingface_hub import InferenceClient
"""
For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
"""
client = InferenceClient("meta-llama/Llama-3.2-3B-Instruct")
def respond(
message,
history: list[tuple[str, str]],
system_message,
max_tokens,
temperature,
top_p,
):
messages = [{"role": "system", "content": system_message}]
for val in history:
if val[0]:
messages.append({"role": "user", "content": val[0]})
if val[1]:
messages.append({"role": "assistant", "content": val[1]})
messages.append({"role": "user", "content": message})
response = ""
for message in client.chat_completion(
messages,
max_tokens=max_tokens,
stream=True,
temperature=temperature,
top_p=top_p,
):
token = message.choices[0].delta.content
response += token
yield response
# CSS for styling the interface
css = """
body {
background-color: #06688E; /* Dark background */
color: white; /* Text color for better visibility */
}
.gr-button {
background-color: #42B3CE !important; /* White button color */
color: black !important; /* Black text for contrast */
border: none !important;
padding: 8px 16px !important;
border-radius: 5px !important;
}
.gr-button:hover {
background-color: #e0e0e0 !important; /* Slightly lighter button on hover */
}
.gr-slider-container {
color: white !important; /* Slider labels in white */
}
"""
# Function to trigger different AI models based on button click
def trigger_model(model_name, message, history, system_message, max_tokens, temperature, top_p):
if model_name == "Llama":
# Here, you can choose the llama model to generate a response
return respond(message, history, system_message, max_tokens, temperature, top_p)
elif model_name == "Chatgpt":
# Placeholder for ChatGPT function (if needed)
return "ChatGPT response goes here."
elif model_name == "Claude":
# Placeholder for Claude function (if needed)
return "Claude response goes here."
else:
return "Model not found."
# Define the Gradio interface
demo = gr.Interface(
fn=trigger_model,
inputs=[
gr.Textbox(value="Hello!", label="User Message"),
gr.Textbox(value="System message", label="System Message", visible=False),
gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
gr.Slider(
minimum=0.1,
maximum=1.0,
value=0.95,
step=0.05,
label="Top-p (nucleus sampling)"
),
gr.Button("Chatgpt"),
gr.Button("Llama"),
gr.Button("Claude"),
],
outputs="text",
css=css, # Pass the custom CSS here
)
if __name__ == "__main__":
demo.launch(share=True)
|