Upload app.py

app.py

@@ -57,8 +57,8 @@ embedding_model_bge = "BAAI/bge-base-en-v1.5"
 #save_path_bge = "./models/bge-base-en-v1.5"
 faiss_index_path = "./qa_faiss_embedding.index"
 chunked_text_path = "./chunked_text_RAG_text.txt"
-#READER_MODEL_NAME = "google/gemma-2-9b-it"
-READER_MODEL_NAME = "google/gemma-2b-it"
+READER_MODEL_NAME = "google/gemma-2-9b-it"
+#READER_MODEL_NAME = "google/gemma-2b-it"
 log_file_path = "./diagnosis_logs.csv"
 feedback_file_path = "./feedback_logs.csv"
 
@@ -157,18 +157,18 @@ emotion_classifier = hf_pipeline("text-classification", model="nateraw/bert-base
 # )
 
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-# tokenizer = AutoTokenizer.from_pretrained(READER_MODEL_NAME)
-# #model = AutoModelForCausalLM.from_pretrained(READER_MODEL_NAME)
-# model = AutoModelForCausalLM.from_pretrained(READER_MODEL_NAME).to(device)
-
-model_id = "mistralai/Mistral-7B-Instruct-v0.1"
-#model_id = "TheBloke/Gemma-2-7B-IT-GGUF"
-tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained(
-    model_id,
-    torch_dtype=torch.float16,
-    device_map="auto",
-).to(device)
+tokenizer = AutoTokenizer.from_pretrained(READER_MODEL_NAME)
+#model = AutoModelForCausalLM.from_pretrained(READER_MODEL_NAME)
+model = AutoModelForCausalLM.from_pretrained(READER_MODEL_NAME).to(device)
+
+# model_id = "mistralai/Mistral-7B-Instruct-v0.1"
+# #model_id = "TheBloke/Gemma-2-7B-IT-GGUF"
+# tokenizer = AutoTokenizer.from_pretrained(model_id)
+# model = AutoModelForCausalLM.from_pretrained(
+#     model_id,
+#     torch_dtype=torch.float16,
+#     device_map="auto",
+# ).to(device)
 
 READER_LLM = pipeline(
     model=model,