Update app.py

app.py

@@ -11,8 +11,8 @@ from huggingface_hub import hf_hub_download
 # Variables
 HF_TOKEN = os.environ.get("HF_TOKEN")
 
-REPO = "HuggingFaceTB/SmolLM2-1.7B-Instruct-GGUF"
-FILE = "smollm2-1.7b-instruct-q4_k_m.gguf"
+REPO = "Novaciano/Llama-3.2_1b_Uncensored_RP_Aesir_GGUF"
+FILE = "Llama-3.2_1b_Uncensored_RP_Aesir.gguf"
 
 TIMEOUT = 60
 
@@ -21,7 +21,7 @@ MAX_SEED = 9007199254740991
 model = Llama(
     model_path=hf_hub_download(repo_id=REPO, filename=FILE, token=HF_TOKEN),
     n_ctx=32768,
-    # n_threads=48,
+    n_threads=4,
     n_batch=512,
     n_gpu_layers=0,
     verbose=True