app.py

import gradio as gr

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-7b-chat-hf")
model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-2-7b-chat-hf")

def eval_text(text):
    # Encode the input text
    input_ids = tokenizer.encode(text, return_tensors="pt")

# Generate text
    out = model.generate(
        input_ids,
        min_length=100,
        max_length=100,
        eos_token_id=5,
        pad_token_id=1,
        top_k=10,
        top_p=0.0,
        no_repeat_ngram_size=5
    )

# Decode the generated output
    generated_text = list(map(tokenizer.decode, out))[0]
    print(generated_text)


    return(f"Result: {generation[0]['generated_text']}")


demo = gr.Interface(fn=eval_text, inputs="text", outputs="text", title="Llama2")
    
demo.launch(share=True)