File size: 1,532 Bytes
b259079 d8ce1f0 0ea7176 d8ce1f0 0ea7176 b259079 0ea7176 b259079 9bac514 0ea7176 9bac514 0ea7176 d8ce1f0 0ea7176 d8ce1f0 0ea7176 9bac514 0ea7176 |
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 |
import gradio as gr
from transformers import AutoTokenizer, AutoModelForCausalLM
# Load the tokenizer and model
print("Loading tokenizer...")
tokenizer = AutoTokenizer.from_pretrained("kolbeins/model")
print("Tokenizer loaded.")
print("Loading model...")
model = AutoModelForCausalLM.from_pretrained("kolbeins/model")
print("Model loaded.")
def chat(input_txt):
"""
Function to generate a response using the model for the given input text.
"""
try:
print("Tokenizing input...")
# Tokenizing the input text, making sure to add special tokens if necessary
inputs = tokenizer(input_txt, return_tensors="pt", padding=True, truncation=True, max_length=512)
print(f"Tokenized inputs: {inputs}")
print("Generating output...")
# Generate the output using the model
outputs = model.generate(**inputs)
print(f"Generated output: {outputs}")
print("Decoding output...")
# Decode the output (the model generates token IDs, so we need to decode them back to text)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(f"Decoded response: {response}")
# Return the generated response
return response
except Exception as e:
print(f"Error during inference: {e}")
return f"Error: {e}"
# Define the Gradio interface for the chatbot
demo = gr.Interface(fn=chat, inputs="text", outputs="text")
# Launch the interface
print("Launching Gradio interface...")
demo.launch()
|