File size: 1,684 Bytes
146f13b de7bf1e 7736908 de7bf1e 7736908 3feea3d 7736908 de7bf1e 7736908 de7bf1e 7736908 de7bf1e |
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 |
!pip install transformers
import gradio as gr
from huggingface_hub import InferenceClient
from transformers import pipeline
system_message = "You are a friendly chatbot."
def respond(message, history=None, system_message=system_message, max_tokens=512, temperature=0.7, top_p=0.95):
if history is None:
history = []
if isinstance(history, str):
history = json.loads(history)
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})
response = ""
client = InferenceClient(pipeline("text-generation", model="ibm-granite/granite-8b-code-instruct"))
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,
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() |