app.py

#%pip install transformers
import gradio as gr
from transformers import AutoModelForCausalLM, AutoTokenizer

# Load the LLaMA 3 model and tokenizer
model_name = "kshabana/GOAT-llama3.1-v0.1"  # Replace with the actual model path if different
model = AutoModelForCausalLM.from_pretrained("GOAT-llama3.1-v0.1-Q4_K_M.gguf")
tokenizer = AutoTokenizer.from_pretrained("tokenizer.json")

def generate_response(user_input):
    inputs = tokenizer.encode(user_input, return_tensors="pt")
    outputs = model.generate(inputs, max_length=50, num_return_sequences=1)
    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return response

interface = gr.Interface(fn=generate_response, inputs="text", outputs="text")
interface.launch()