Spaces:
Runtime error
Runtime error
File size: 3,893 Bytes
f8d7d68 90b7b96 f8d7d68 90b7b96 f8d7d68 90b7b96 f8d7d68 90b7b96 f8d7d68 90b7b96 f8d7d68 90b7b96 f8d7d68 90b7b96 |
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 99 100 101 102 103 104 105 |
import gradio as gr
from transformers import pipeline, AutoTokenizer
# Define examples and model configuration
examples = [
"Give me a recipe for pizza with pineapple",
"Write me a tweet about the new OpenVINO release",
"Explain the difference between CPU and GPU",
"Give five ideas for a great weekend with family",
"Do Androids dream of Electric sheep?",
"Who is Dolly?",
"Please give me advice on how to write resume?",
"Name 3 advantages to being a cat",
"Write instructions on how to become a good AI engineer",
"Write a love letter to my best friend",
]
# Define the model and its tokenizer
model_name = "susnato/phi-2" # Replace with your actual model identifier
tokenizer = AutoTokenizer.from_pretrained(model_name)
generator = pipeline("text-generation", model=model_name, tokenizer=tokenizer)
def run_generation(user_text, top_p, temperature, top_k, max_new_tokens, performance):
prompt = f"Instruct:{user_text}\nOutput:"
response = generator(prompt, max_length=max_new_tokens, top_p=top_p, temperature=temperature, top_k=top_k)[0]["generated_text"]
return response, "N/A" # Replace "N/A" with actual performance metrics if available
def reset_textbox(*args):
return "", "", ""
def main():
with gr.Blocks() as demo:
gr.Markdown(
"# Question Answering with OpenVINO\n"
"Provide instruction which describes a task below or select among predefined examples and model writes response that performs requested task."
)
with gr.Row():
with gr.Column(scale=4):
user_text = gr.Textbox(
placeholder="Write an email about an alpaca that likes flan",
label="User instruction",
)
model_output = gr.Textbox(label="Model response", interactive=False)
performance = gr.Textbox(label="Performance", lines=1, interactive=False)
with gr.Column(scale=1):
button_clear = gr.Button(value="Clear")
button_submit = gr.Button(value="Submit")
gr.Examples(examples, user_text)
with gr.Column(scale=1):
max_new_tokens = gr.Slider(
minimum=1,
maximum=1000,
value=256,
step=1,
interactive=True,
label="Max New Tokens",
)
top_p = gr.Slider(
minimum=0.05,
maximum=1.0,
value=0.92,
step=0.05,
interactive=True,
label="Top-p (nucleus sampling)",
)
top_k = gr.Slider(
minimum=0,
maximum=50,
value=0,
step=1,
interactive=True,
label="Top-k",
)
temperature = gr.Slider(
minimum=0.1,
maximum=5.0,
value=0.8,
step=0.1,
interactive=True,
label="Temperature",
)
user_text.submit(
run_generation,
[user_text, top_p, temperature, top_k, max_new_tokens, performance],
[model_output, performance],
)
button_submit.click(
run_generation,
[user_text, top_p, temperature, top_k, max_new_tokens, performance],
[model_output, performance],
)
button_clear.click(
reset_textbox,
[user_text, model_output, performance],
[user_text, model_output, performance],
)
return demo
if __name__ == "__main__":
iface = main()
iface.launch(share=True)
|