app.py

import gradio as gr
from transformers import AutoTokenizer, PreTrainedTokenizer, AutoConfig
import torch
from custom_model import CustomModel

# Load the model and tokenizer
model_name = "deepseek-ai/DeepSeek-V3"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
config = AutoConfig.from_pretrained(model_name, trust_remote_code=True)
model = CustomModel.from_pretrained(model_name, config=config, trust_remote_code=True)

def classify_text(text):
    inputs = tokenizer(text, return_tensors="pt")
    outputs = model(**inputs)
    logits = outputs.logits
    probabilities = torch.softmax(logits, dim=-1).tolist()[0]
    predicted_class = torch.argmax(logits, dim=-1).item()
    return {
        "Predicted Class": predicted_class,
        "Probabilities": probabilities
    }

# Create a Gradio interface
iface = gr.Interface(
    fn=classify_text,
    inputs=gr.inputs.Textbox(lines=2, placeholder="Enter text here..."),
    outputs=[
        gr.outputs.Label(label="Predicted Class"),
        gr.outputs.Label(label="Probabilities")
    ],
    title="DeepSeek-V3 Text Classification",
    description="Classify text using the DeepSeek-V3 model."
)

# Launch the interface
iface.launch()