app.py

# import gradio as gr

# def greet(name):
#     return "Hello " + name + "!!"

# demo = gr.Interface(fn=greet, inputs="text", outputs="text")
# demo.launch()



import gradio as gr
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Almawave/Velvet-14B")
model = AutoModelForCausalLM.from_pretrained("Almawave/Velvet-14B")

def generate_text(input_text):
    input_ids = tokenizer.encode(input_text, return_tensors="pt")
    attention_mask = torch.ones(input_ids.shape)

    output = model.generate(
        input_ids,
        attention_mask=attention_mask,
        max_length=200,
        do_sample=True,
        top_k=10,
        num_return_sequences=1,
        eos_token_id=tokenizer.eos_token_id,
    )

    output_text = tokenizer.decode(output[0], skip_special_tokens=True)
    print(output_text)

    # Remove Prompt Echo from Generated Text
    cleaned_output_text = output_text.replace(input_text, "")
    return cleaned_output_text


text_generation_interface = gr.Interface(
    fn=generate_text,
    inputs=[
        gr.inputs.Textbox(label="Input Text"),
    ],
    outputs=gr.inputs.Textbox(label="Generated Text"),
    title="Falcon-7B Instruct",
).launch()