Update app.py

app.py

@@ -8,6 +8,15 @@ model_name = "kazuma313/lora_model_dokter_consultasi_q4_k_m"
 model_file = "lora_model_dokter_consultasi_q4_k_m-unsloth.Q4_K_M.gguf" # this is the specific model file we'll use in this example. It's a 4-bit quant, but other levels of quantization are available in the model repo if preferred
 model_path = hf_hub_download(model_name, filename=model_file)
 
+llm = Llama(
+    model_path=model_path,
+    n_ctx=2048,  # Context length to use
+    # n_threads=4,            # Number of CPU threads to use
+    # n_gpu_layers=0        # Number of model layers to offload to GPU
+    # chat_format="chatml",
+    verbose=False
+
+)
 
 prompt_template="""<|begin_of_text|>Dibawah ini adalah percakapan antara dokter dengan pasiennya yang ingin berkonsultasi terkait kesehatan. Tuliskan jawaban yang tepat dan lengkap sesuai sesuai pertanyaan dari pasien.<|end_of_text|>