Update app.py

app.py

@@ -1,11 +1,10 @@
-#%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")
+model = AutoModelForCausalLM.from_pretrained("https://huggingface.co/kshabana/GOAT-llama3.1-v0.1/resolve/main/GOAT-llama3.1-v0.1-Q4_K_M.gguf")
 
 def generate_response(user_input):
     inputs = tokenizer.encode(user_input, return_tensors="pt")