File size: 1,744 Bytes
30b9b7b 33764a2 30b9b7b 5f2a910 30b9b7b b8995e8 30b9b7b d2880e2 30b9b7b d2794c7 b0426c3 5986f5c 346e6da 30b9b7b 53260c7 30b9b7b |
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 |
import gradio as gr
from huggingface_hub import InferenceClient
client = InferenceClient("BenBranyon/zephyr-sumbot-all-songs")
def respond(
message,
history: list[tuple[str, str]],
max_tokens,
temperature,
top_p,
):
messages = [{"role": "system", "content": "You are a rap lyric generation bot representing the imagination of the artist Sumkilla. Try to avoid words that would offend anyone. Try to rhyme as much as possible."}]
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": "Write a rap about " + 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
demo = gr.ChatInterface(
respond,
chatbot=gr.Chatbot(placeholder="<strong>Sumbot</strong><br>Hello human. What would you like me to rap about today?"),
retry_btn=None,
textbox=gr.Textbox(placeholder="Subject of the song", container=False, scale=7),
css="styles.css",
additional_inputs=[
gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
gr.Slider(minimum=0.1, maximum=4.0, value=0.6, 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() |