model changed to gguf

app/views.py

@@ -39,4 +39,4 @@ with gr.Blocks(
         
 
 # mounting at the path
-app = gr.mount_gradio_app(app, llama2bot.queue(concurrency_count=20), path="/llama2")
+app = gr.mount_gradio_app(app, llama2bot, path="/llama2")

src/chains.py

@@ -1,9 +1,14 @@
 from langchain.llms import CTransformers
-from langchain import PromptTemplate, LLMChain
+# from langchain import PromptTemplate, LLMChain
+from langchain.chains import LLMChain
+from langchain.prompts import PromptTemplate
 from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
 
+ggufmodel = f"TheBloke/Llama-2-7B-Chat-GGUF"
+ggufmodelfile = f"llama-2-7b-chat.Q5_K_M.gguf"
 
-llm = CTransformers(model="TheBloke/Llama-2-7B-Chat-GGML", model_file = 'llama-2-7b-chat.ggmlv3.q2_K.bin', callbacks=[StreamingStdOutCallbackHandler()])
+# llm = CTransformers(model="TheBloke/Llama-2-7B-Chat-GGML", model_file = 'llama-2-7b-chat.ggmlv3.q2_K.bin', callbacks=[StreamingStdOutCallbackHandler()])
+llm = CTransformers(model=ggufmodel, model_file = ggufmodelfile, callbacks=[StreamingStdOutCallbackHandler()])
 
 
 template = """