Update app.py

app.py

@@ -8,7 +8,7 @@ import time
 repo_id = "bartowski/Qwen2.5-1.5B-Instruct-GGUF"
 filename = "Qwen2.5-1.5B-Instruct-Q8_0.gguf"
 
-CONTEXT_SIZE = 2048
+CONTEXT_SIZE = 1024
 N_THREADS = 2 #FreeのCPUは２なので
 
 llm = None
@@ -23,7 +23,7 @@ def load_model(progress=gr.Progress()):
     llm = Llama(
         model_path=model_path,
         n_threads=N_THREADS,
-        n_batch=32,
+        n_batch=8,
         verbose=False,
         n_ctx=CONTEXT_SIZE,
     )