Update app.py

app.py

@@ -7,10 +7,10 @@
 | - Import Python      |        | - Define interface      |        | - Transcribe audio            |        | - XTTS model generates  |
 |   libraries          |        |   components            |        |   to text using               |        |   spoken response from  |
 | - Initialize models: |--------> - Configure audio and   |------->|   Faster Whisper ASR          |------->|   LLM's text response   |
-|   Whisper, Mistral,  |        |   text interaction      |        | - Transcribed text            |        |                         |
+|   Whisper, SaulLM,   |        |   text interaction      |        | - Transcribed text            |        |                         |
 |   XTTS               |        | - Launch interface      |        |   is added to                 |        |                         |
 |                      |        |                         |        |   chatbot's history           |        |                         |
-|                      |        |                         |        | - Mistral LLM                 |        |                         |
+|                      |        |                         |        | - SaulLM LLM                  |        |                         |
 |                      |        |                         |        |   processes chatbot           |        |                         |
 |                      |        |                         |        |   history to generate         |        |                         |
 |                      |        |                         |        |   response                    |        |                         |
@@ -48,7 +48,7 @@ whisper_model = WhisperModel("large-v3", device="cuda", compute_type="float16")
 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=4096, n_batch=128,verbose=False)
+saul_instruct_llm = Llama(model_path=saul_model_path,n_gpu_layers=35,max_new_tokens=256, context_window=16384, n_ctx=16384, n_batch=128,verbose=False)
 
 # Load XTTS Model
 print("Loading XTTS model")
@@ -170,7 +170,6 @@ with gr.Blocks(title="Voice chat with Saul-Instruct-v1-GGUF") as demo:
             It relies on the following models :
             - Speech to Text Model: [Faster-Whisper-large-v3](https://huggingface.co/Systran/faster-whisper-large-v3) an ASR model, to transcribe recorded audio to text.
             - Legal Large Language Model: [MaziyarPanahi/Saul-Instruct-v1-GGUF](https://huggingface.co/MaziyarPanahi/Saul-Instruct-v1-GGUF/blob/main/Saul-Instruct-v1.Q4_K_M.gguf) a LLM to generate legal chatbot responses. 
-            - Large Language Model: [Mistral-7b-instruct-v0.1-quantized](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-GGUF) a LLM to generate the chatbot responses. 
             - Text to Speech Model: [XTTS-v2](https://huggingface.co/spaces/coqui/xtts) a TTS model, to generate the voice of the chatbot.
 
             Note: