Spaces:
Runtime error
Runtime error
File size: 1,349 Bytes
10bed7b 88b191b 10bed7b c7d63a8 10bed7b 079c194 c7d63a8 10bed7b c7d63a8 10bed7b c7d63a8 10bed7b c7d63a8 10bed7b c7d63a8 10bed7b |
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 |
import gradio as gr
from transformers import GPT2Tokenizer
from thirdai import bolt, licensing
licensing.activate("7511CC-0E24D7-69439D-5D6CBA-33AAFD-V3")
tokenizer = GPT2Tokenizer.from_pretrained("gpt2")
model = bolt.GenerativeModel.load("./generative.model")
def generate(prompt, beam_width, temperature):
prompt = tokenizer.encode(prompt)
stream = model.streaming_generation(
input_tokens=prompt,
prediction_chunk_size=2,
max_predictions=80,
beam_width=beam_width,
temperature=temperature if temperature > 0 else None,
)
for res in stream:
yield tokenizer.decode(res)
with gr.Blocks() as demo:
prompt = gr.Textbox(label="Prompt", autofocus=True)
output = gr.TextArea(label="Output")
beam_width = gr.Slider(minimum=1, maximum=10, step=1, value=3, label="Beam Width")
temperature = gr.Slider(
minimum=0,
maximum=3,
step=0.1,
value=1.2,
label="Temperature (0 means temperature isn't used)",
)
prompt.submit(generate, inputs=[prompt, beam_width, temperature], outputs=[output])
btn = gr.Button(value="Generate")
btn.click(generate, inputs=[prompt, beam_width, temperature], outputs=[output])
gr.ClearButton(components=[prompt, output])
if __name__ == "__main__":
demo.queue()
demo.launch()
|