Update app.py

app.py

@@ -48,13 +48,13 @@ whisper_model = WhisperModel("large-v3", device="cuda", compute_type="float16")
 print("Loading Mistral LLM")
 hf_hub_download(repo_id="TheBloke/Mistral-7B-Instruct-v0.1-GGUF", local_dir=".", filename="mistral-7b-instruct-v0.1.Q5_K_M.gguf")
 mistral_model_path="./mistral-7b-instruct-v0.1.Q5_K_M.gguf"
-mistral_llm = Llama(model_path=mistral_model_path,n_gpu_layers=35,max_new_tokens=256, context_window=4096, n_ctx=4096,n_batch=128,verbose=False)
+mistral_llm = Llama(model_path=mistral_model_path,n_gpu_layers=35,max_new_tokens=256, context_window=4096, n_ctx=4096, n_batch=128,verbose=False)
 
 # Load Saul-Instruct-v1-GGUF.Q4_K_M
 print("Loading Saul-Instruct-v1-GGUF.Q4_K_M")
 hf_hub_download(repo_id="MaziyarPanahi/Saul-Instruct-v1-GGUF", local_dir=".", filename="Saul-Instruct-v1.Q4_K_M.gguf")
 saul_model_path="./Saul-Instruct-v1.Q4_K_M.gguf"
-saul_instruct_llm = Llama(model_path=saul_model_path,n_gpu_layers=35,max_new_tokens=256, context_window=4096, n_ctx=32768,n_batch=128,verbose=False)
+saul_instruct_llm = Llama(model_path=saul_model_path,n_gpu_layers=35,max_new_tokens=256, context_window=4096, n_ctx=4096, n_batch=128,verbose=False)
 
 # Load XTTS Model
 print("Loading XTTS model")