Update app.py

app.py

@@ -146,8 +146,8 @@ zephyr_model_path="./zephyr-7b-beta.Q5_K_M.gguf"
 
 #print("Downloading Yi-6B")
 #Yi-6B
-hf_hub_download(repo_id="TheBloke/Yi-6B-GGUF", local_dir=".", filename="yi-6b.Q5_K_M.gguf")
-yi_model_path="./yi-6b.Q5_K_M.gguf"
+#hf_hub_download(repo_id="TheBloke/Yi-6B-GGUF", local_dir=".", filename="yi-6b.Q5_K_M.gguf")
+#yi_model_path="./yi-6b.Q5_K_M.gguf"
 
 
 from llama_cpp import Llama
@@ -167,8 +167,8 @@ llm_mistral = InferenceClient("mistralai/Mistral-7B-Instruct-v0.1")
 print("Running LLM Zephyr")
 llm_zephyr = Llama(model_path=zephyr_model_path,n_gpu_layers=round(GPU_LAYERS/2),max_new_tokens=256, context_window=4096, n_ctx=4096,n_batch=128,verbose=LLAMA_VERBOSE)
 
-print("Running Yi LLM")
-llm_yi = Llama(model_path=yi_model_path,n_gpu_layers=round(GPU_LAYERS/2),max_new_tokens=256, context_window=4096, n_ctx=4096,n_batch=128,verbose=LLAMA_VERBOSE)
+#print("Running Yi LLM")
+#llm_yi = Llama(model_path=yi_model_path,n_gpu_layers=round(GPU_LAYERS/2),max_new_tokens=256, context_window=4096, n_ctx=4096,n_batch=128,verbose=LLAMA_VERBOSE)
 
 
 # Mistral formatter
@@ -744,7 +744,7 @@ EXAMPLES = [
     
 ]
 
-MODELS = ["Mistral 7B Instruct","Zephyr 7B Beta", "Yi 6B"]
+MODELS = ["Mistral 7B Instruct","Zephyr 7B Beta"]
 
 OTHER_HTML=f"""<div>
 <a style="display:inline-block" href='https://github.com/coqui-ai/TTS'><img src='https://img.shields.io/github/stars/coqui-ai/TTS?style=social' /></a>
@@ -851,7 +851,6 @@ It relies on following models :
 Speech to Text : [Whisper-large-v2](https://sanchit-gandhi-whisper-large-v2.hf.space/) as an ASR model, to transcribe recorded audio to text. It is called through a [gradio client](https://www.gradio.app/docs/client).
 LLM Mistral    : [Mistral-7b-instruct](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) as the chat model. 
 LLM Zephyr     : [Zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) as the chat model. GGUF Q5_K_M quantized version used locally via llama_cpp from [huggingface.co/TheBloke](https://huggingface.co/TheBloke/zephyr-7B-beta-GGUF).
-LLM Yi         : [Yi-6B](https://huggingface.co/01-ai/Yi-6B) as the chat model. GGUF Q5_K_M quantized version used locally via llama_cpp from [huggingface.co/TheBloke](https://huggingface.co/TheBloke/Yi-6B-GGUF).
 Text to Speech : [Coqui's XTTS V2](https://huggingface.co/spaces/coqui/xtts) as a Multilingual TTS model, to generate the chatbot answers. This time, the model is hosted locally.
 
 Note: