Spaces:
Sleeping
Sleeping
File size: 2,569 Bytes
a36f63d 358ed93 a36f63d 358ed93 a36f63d 358ed93 a36f63d 358ed93 a36f63d 358ed93 a36f63d 358ed93 a36f63d 358ed93 a36f63d 358ed93 a36f63d 358ed93 a36f63d 358ed93 a36f63d 358ed93 |
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 72 73 74 75 |
import os
import gradio as gr
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
# Load your model and tokenizer from Hugging Face
model_name = 'redael/model_udc'
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model.to(device)
# Function to generate response
def generate_response(message, history, system_message, max_tokens, temperature, top_p):
# Prepare the conversation history
messages = [{"role": "system", "content": system_message}]
for user_msg, bot_msg in history:
if user_msg:
messages.append({"role": "user", "content": user_msg})
if bot_msg:
messages.append({"role": "assistant", "content": bot_msg})
messages.append({"role": "user", "content": message})
# Tokenize and prepare the input
prompt = "\n".join([f"{msg['role'].capitalize()}: {msg['content']}" for msg in messages])
inputs = tokenizer(prompt, return_tensors='pt', padding=True, truncation=True, max_length=512).to(device)
# Generate the response
outputs = model.generate(
inputs['input_ids'],
max_length=max_tokens,
num_return_sequences=1,
pad_token_id=tokenizer.eos_token_id,
temperature=temperature,
top_p=top_p,
early_stopping=True,
do_sample=True # Enable sampling
)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
# Clean up the response
response = response.split("Assistant:")[-1].strip()
response_lines = response.split('\n')
clean_response = []
for line in response_lines:
if "User:" not in line and "Assistant:" not in line:
clean_response.append(line)
response = ' '.join(clean_response)
return [(message, response)]
# Create the Gradio chat interface
demo = gr.ChatInterface(
fn=generate_response,
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)",
),
],
title="Chatbot",
description="Ask anything to the chatbot."
)
if __name__ == "__main__":
demo.launch() |