Spaces:
Sleeping
Sleeping
File size: 1,070 Bytes
96c0fed 5acce1c 88dbfe8 ce5bb83 526d3d2 96c0fed 9329502 b9c6949 1786fdc 8a00090 a0a8dca d1921b9 a0a8dca 9329502 a0a8dca 1786fdc a0a8dca 526d3d2 1786fdc e5f53e6 ce5bb83 526d3d2 96c0fed |
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
import random
from huggingface_hub import InferenceClient
client = InferenceClient("google/gemma-3-27b-it")
##change the LLM
def respond(message, history):
messages = [{"role":"system","content":"You are a sarcastic chatbot"}]
if history :
messages.extend(history)
messages.append({"role":"user","content": message})
response = ""
for message in client.chat_completion(
messages,
max_tokens = 400,
stream = True
):
token = message.choices[0].delta.content
response += token
yield response
# top_p & temperature
#return response["choices"][0]["message"]["content"].strip()
#def random_message (message, history):
# choices = ('yes','no','i dont think so','be so for real','yep', 'woooow', 'hmmmm', 'idk', 'idc', 'yaaay', 'why would i know')
# wow = random.choice(choices)
# theme = soft
# return wow
chatbot = gr.ChatInterface(respond, type = "messages", title = "chatty")
chatbot.launch(debug=True)
# repeats messages.
|