Update app.py

app.py

@@ -76,10 +76,10 @@ tokenizer.padding_side = "right"
 #         print("=" * 80)
 
 
-# model = AutoModelForCausalLM.from_pretrained(
-#     model_name,
-#     quantization_config=bnb_config,
-# )
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+   
+)
 stop_list = [" \n\nAnswer:", " \n", " \n\n"]
 stop_token_ids = [tokenizer(x,  return_tensors='pt', add_special_tokens=False)['input_ids'] for x in stop_list]
 stop_token_ids = [torch.LongTensor(x).to("cuda") for x in stop_token_ids]
@@ -107,7 +107,7 @@ text_generation_pipeline = pipeline(
 )
 mistral_llm = HuggingFacePipeline(pipeline=text_generation_pipeline)
 # # # load chroma from disk
-db3 = Chroma(persist_directory="/content/gdrive/MyDrive/diploma/all_emb/chroma/", embedding_function=instructor_embeddings)
+db3 = Chroma(persist_directory="/chroma/", embedding_function=instructor_embeddings)