File size: 2,726 Bytes
4afb7a5 013b8fb 4afb7a5 013b8fb 4afb7a5 5793084 292985d 5793084 4afb7a5 325ada3 4afb7a5 5793084 325ada3 5793084 325ada3 292985d 5793084 292985d 4afb7a5 013b8fb 5793084 4afb7a5 013b8fb dce5482 013b8fb dce5482 013b8fb 4afb7a5 |
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 |
import gradio as gr
from huggingface_hub import InferenceClient
client = InferenceClient("microsoft/Phi-3.5-mini-instruct")
# Predefined prompts
prompts = [
"Tell me a joke about programming",
"Write a short story about a time-traveling robot",
"Explain quantum computing to a 5-year-old",
"Create a recipe for the most unusual pizza",
"Describe an alien civilization's first contact with Earth"
]
def respond(
message,
history: list[tuple[str, str]],
system_message,
max_tokens,
temperature,
top_p,
):
if not message:
return []
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})
prompt = "\n".join([m["content"] for m in messages])
response = ""
try:
for chunk in client.text_generation(
prompt,
max_new_tokens=max_tokens,
stream=True,
temperature=temperature,
top_p=top_p,
):
if isinstance(chunk, str):
response += chunk
else:
response += chunk.token.text if hasattr(chunk, 'token') else chunk.generated_text
yield [(message, response)]
except Exception as e:
yield [(message, f"An error occurred: {str(e)}")]
def update_textbox(prompt):
return gr.update(value=prompt)
with gr.Blocks() as demo:
chatbot = gr.Chatbot()
msg = gr.Textbox(label="Type your message or select a prompt")
with gr.Row():
prompt_dropdown = gr.Dropdown(choices=[""] + prompts, label="Select a premade prompt", value="")
submit = gr.Button("Submit")
clear = gr.ClearButton([msg, chatbot])
with gr.Accordion("Advanced options", open=False):
system = gr.Textbox(value="You are a friendly Chatbot.", label="System message")
max_tokens = gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens")
temperature = gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature")
top_p = gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)")
prompt_dropdown.change(update_textbox, inputs=[prompt_dropdown], outputs=[msg])
submit.click(respond, [msg, chatbot, system, max_tokens, temperature, top_p], chatbot)
msg.submit(respond, [msg, chatbot, system, max_tokens, temperature, top_p], chatbot)
clear.click(lambda: None, None, chatbot, queue=False)
if __name__ == "__main__":
demo.launch() |