app.py

import gradio as gr
from transformers import AutoModelForCausalLM, AutoTokenizer

# Load the model and tokenizer
model_name = "cognitivecomputations/dolphin-2.9.3-mistral-nemo-12b"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

# Define the prediction function
def predict(input_text):
    inputs = tokenizer(input_text, return_tensors="pt")
    outputs = model.generate(**inputs)
    generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return generated_text

# Create the Gradio interface
iface = gr.Interface(
    fn=predict,
    inputs=gr.inputs.Textbox(lines=2, placeholder="Enter your text here..."),
    outputs="text",
    title="Dolphin-2.9.3-Mistral-Nemo-12b Text Generation",
    description="Generate text using the Dolphin-2.9.3-Mistral-Nemo-12b model from Hugging Face."
)

# Launch the interface
iface.launch()