Update app.py

app.py

@@ -123,8 +123,10 @@ def load_model(_docs):
                              top_p=0.95,
                              repetition_penalty=1.15,
                              streamer=streamer,)
-    llm = HuggingFacePipeline(pipeline=text_pipeline, model_kwargs={"temperature": 0.1})
-
+    #llm = HuggingFacePipeline(pipeline=text_pipeline, model_kwargs={"temperature": 0.1})
+    
+    llm = HuggingFaceHub(repo_id="mistralai/Mixtral-8x7B-Instruct-v0.1", model_kwargs={"temperature": 0.1, "max_new_tokens": 1024, "top_k": 3, "load_in_8bit": True})
+    
     # SYSTEM_PROMPT = ("Use the following pieces of context to answer the question at the end. "
     #                  "If you don't know the answer, just say that you don't know, "
     #                  "don't try to make up an answer.")