attempt to fix memory error

app.py

@@ -32,18 +32,23 @@ MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
 
 embeddings = HuggingFaceHubEmbeddings()
 
-# model_id = "HuggingFaceH4/zephyr-7b-beta"
-model_id = "meta-llama/Llama-2-7b-chat-hf"
+model_id = "HuggingFaceH4/zephyr-7b-beta"
+# model_id = "meta-llama/Llama-2-7b-chat-hf"
 
-model = AutoModelForCausalLM.from_pretrained(
-    model_id, 
-    device_map="auto",
-    low_cpu_mem_usage=True
-)
+# model = AutoModelForCausalLM.from_pretrained(
+#     model_id, 
+#     device_map="auto",
+#     low_cpu_mem_usage=True
+# )
 
 print( "initalized model")
 
+# tokenizer = AutoTokenizer.from_pretrained(model_id)
+
+
+
 tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id)
 
 pipe = pipeline("text-generation", model=model, tokenizer=tokenizer, max_new_tokens=10)
 hf = HuggingFacePipeline(pipeline=pipe)