File size: 1,633 Bytes
b363565 169280e b363565 ee422cf 930ba37 169280e ee422cf 2220a33 ee422cf 2220a33 ee422cf 930ba37 ee422cf |
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 |
import gradio as gr
from transformers import GPT2Tokenizer, GPT2LMHeadModel
# Load the model and tokenizer
model_name = "migueldeguzmandev/gpt2xl-standard-test-purposes-only"
tokenizer = GPT2Tokenizer.from_pretrained(model_name)
model = GPT2LMHeadModel.from_pretrained(model_name)
# Set the pad token ID to the EOS token ID
model.config.pad_token_id = model.config.eos_token_id
# Define the inference function
def generate_response(input_text, temperature):
# Tokenize the input text
inputs = tokenizer(input_text, return_tensors="pt")
input_ids = inputs["input_ids"]
attention_mask = inputs["attention_mask"]
# Generate the model's response
output = model.generate(
input_ids,
attention_mask=attention_mask,
max_length=300,
num_return_sequences=1,
temperature=temperature,
no_repeat_ngram_size=2,
top_k=50,
top_p=0.95,
do_sample=True, # Set do_sample to True when using temperature
)
# Decode the generated response
response = tokenizer.decode(output[0], skip_special_tokens=True)
return response.replace(input_text, "").strip()
# Create the Gradio interface
interface = gr.Interface(
fn=generate_response,
inputs=[
gr.Textbox(label="User Input"),
gr.Slider(minimum=0.000000000000000000000000000000000001, maximum=1.0, value=0.7, step=0.1, label="Temperature"),
],
outputs=gr.Textbox(label="Model Response"),
title="Basemodel GPT2XL, for test purposes only",
description=(
"""
"""
),
)
# Launch the interface without the share option
interface.launch() |