File size: 1,428 Bytes
47fcff2 d3a5649 79cade0 d3a5649 8534d32 1cdf2e9 79cade0 a5bb25c d3a5649 79cade0 d3a5649 79cade0 d3a5649 2efa6f5 a5bb25c 47fcff2 d3a5649 |
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 |
import gradio as gr
from huggingface_hub import InferenceClient
# Initialize the InferenceClient with the model name
# client = InferenceClient("mistralai/Mistral-7B-Instruct-v0.3")
client = InferenceClient("meta-llama/Llama-3.3-70B-Instruct")
def respond(
message,
history,
system_message,
max_tokens,
temperature,
top_p,
):
# Create a list of messages with the system message and user input
messages = [{"role": "system", "content": system_message}, {"role": "user", "content": message}]
# Get the response from the model
response = client.chat_completion(
messages,
max_tokens=max_tokens,
stream=False,
temperature=temperature,
top_p=top_p,
)
# Return the response
return response.choices[0].message.content
# Create a ChatInterface with the respond function and additional inputs
demo = gr.ChatInterface(
respond,
additional_inputs=[
gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
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)",
),
],
)
if __name__ == "__main__":
demo.launch() |