app.py

"""
import gradio as gr
from transformers import AutoModelForCausalLM, AutoTokenizer

# Load your fine-tuned model and tokenizer
model_name = "crystal99/my-fine-tuned-model"
model = AutoModelForCausalLM.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Define the text generation function
def generate_text(prompt):
    inputs = tokenizer(prompt, return_tensors="pt")
    outputs = model.generate(inputs['input_ids'], max_length=100, num_return_sequences=1)
    generated_text = tokenizer.decode(outputs[0], skip_special_tokens=False)
    return generated_text

# Set up the Gradio interface
iface = gr.Interface(fn=generate_text, inputs="text", outputs="text", title="Text Generator using Fine-Tuned Model")

# Launch the Gradio interface
iface.launch()
"""

import gradio as gr
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load your fine-tuned model and tokenizer
model_name = "crystal99/my-fine-tuned-model"
model = AutoModelForCausalLM.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Move model to GPU if available and enable fp16 for faster inference
device = "cuda" if torch.cuda.is_available() else "cpu"
model.to(device)

# Define the text generation function
def generate_text(prompt):
    # Prevent gradient calculation to speed up inference
    with torch.no_grad():
        inputs = tokenizer(f"<|STARTOFTEXT|> <|USER|> {prompt} <|BOT|>", return_tensors="pt").to(device)
        outputs = model.generate(inputs['input_ids'], max_length=100, num_return_sequences=1, do_sample=False)
        generated_text = tokenizer.decode(outputs[0], skip_special_tokens=False)
    return generated_text

# Set up the Gradio interface
iface = gr.Interface(fn=generate_text, inputs="text", outputs="text", title="Text Generator using Fine-Tuned Model")

# Launch the Gradio interface
iface.launch()