Spaces:
Sleeping
Sleeping
File size: 2,059 Bytes
ad2530a 2142d8e ad2530a 2142d8e ad2530a 2142d8e ad2530a 2142d8e ad2530a 2142d8e ad2530a 2142d8e ad2530a 2142d8e ad2530a 2142d8e |
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 |
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
import gradio as gr
# Load DialoGPT model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("microsoft/DialoGPT-large")
model = AutoModelForCausalLM.from_pretrained("microsoft/DialoGPT-large")
def respond(
message,
history: list[tuple[str, str]],
system_message,
max_tokens,
temperature,
top_p,
):
# Prepare the context from history
chat_history = ""
for user_input, bot_response in history:
if user_input:
chat_history += f"User: {user_input}\n"
if bot_response:
chat_history += f"Bot: {bot_response}\n"
# Append the new user message
chat_history += f"User: {message}\n"
# Tokenize the input
input_ids = tokenizer.encode(chat_history, return_tensors="pt")
# Generate response
output_ids = model.generate(
input_ids,
max_length=max_tokens + len(input_ids[0]),
temperature=temperature,
top_p=top_p,
pad_token_id=tokenizer.eos_token_id,
)
# Decode the output and get the response
output = tokenizer.decode(output_ids[0], skip_special_tokens=True)
# Extract the bot's response
bot_response = output.split("User:")[-1].split("Bot:")[-1].strip()
history.append((message, bot_response)) # Update history
yield bot_response
"""
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
"""
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()
|