Spaces:
Running
Running
File size: 1,378 Bytes
7073eba 7e3c3ff 00d7a2e 07f8c16 007bdd0 4b69c94 dcb550c 4b69c94 7e3c3ff 2798e6f 07f8c16 2798e6f 4b69c94 2798e6f 827c0a2 4b69c94 827c0a2 07f8c16 827c0a2 |
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 |
import gradio as gr
from transformers import AutoTokenizer, TFBlenderbotForConditionalGeneration
import tensorflow as tf
print("Loading the model......")
model_name = "WICKED4950/Irisonego5"
strategy = tf.distribute.MirroredStrategy()
tf.config.optimizer.set_jit(True) # Enable XLA
tokenizer = AutoTokenizer.from_pretrained(model_name)
with strategy.scope():
model = TFBlenderbotForConditionalGeneration.from_pretrained(model_name)
print("Interface getting done....")
# Define the chatbot function
def predict(user_input):
# Tokenize input text
inputs = tokenizer(user_input, return_tensors="tf", padding=True, truncation=True)
# Generate the response using the model
response_ids = model.generate(
inputs['input_ids'],
max_length=128, # Set max length of response
do_sample=True, # Sampling for variability
top_k=15, # Consider top 50 tokens
top_p=0.95, # Nucleus sampling
temperature=0.8 # Adjusts creativity of response
)
# Decode the response
response = tokenizer.decode(response_id[0], skip_special_tokens=True)
return response
# Gradio interface
iface = gr.Interface(fn=predict,
inputs="text",
outputs="text",
title="Your Chatbot")
print("Deploying")
iface.launch()
|