Update app.py

app.py

@@ -21,6 +21,10 @@ MODELS = [
     {
         "url": "https://huggingface.co/Novaciano/Llama-3.2_1b_Uncensored_RP_Aesir_GGUF/resolve/main/Llama-3.2_1b_Uncensored_RP_Aesir.gguf",
         "name": "llama3.2-1b-rp"
+    },
+    {
+        "url": "https://huggingface.co/Novaciano/Uncensored-1b-Creative_Writing_RP-GGUF/resolve/main/Uncensored-1b-Creative_Writing_RP.gguf",
+        "name": "uncensored-1b-creative_writing_rp"
     }
 ]
 
@@ -47,7 +51,7 @@ class LLMManager:
                 llm_instance = Llama(
                     model_path=temp_path,
                     n_ctx=MAX_CONTEXT_TOKENS,
-                    n_batch=128,
+                    n_batch=256,
                     n_threads=6,
                     n_threads_batch=6,
                     use_mlock=True,