Update app.py

app.py

@@ -1,22 +1,20 @@
 import gradio as gr
-from transformers import AutoModelForCausalLM, AutoTokenizer
+from llama_cpp import Llama
 
-model_name = "TheBloke/MythoMax-L2-13B-GGUF"
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(model_name)
+# Load model (gunakan versi GGUF yang ringan)
+model_path = "TheBloke/MythoMax-L2-13B-GGUF/mythomax.gguf"
+llm = Llama(model_path=model_path, n_ctx=2048)
 
 def chat(input_text):
-    inputs = tokenizer(input_text, return_tensors="pt")
-    output = model.generate(**inputs, max_new_tokens=100)
-    response = tokenizer.decode(output[0], skip_special_tokens=True)
-    return response
+    output = llm(input_text, max_tokens=100)
+    return output["choices"][0]["text"]
 
 iface = gr.Interface(
     fn=chat,
     inputs="text",
     outputs="text",
     title="Dika AI - MythoMax Lite",
-    description="Chatbot AI berbasis MythoMax 13B GGUF, optimized for Hugging Face free tier!"
+    description="Chatbot AI berbasis MythoMax 13B GGUF, optimized for Hugging Face CPU!"
 )
 
 iface.launch()