Update app.py

app.py

@@ -66,8 +66,8 @@ from langchain.chains import create_retrieval_chain
 #from langchain_community.llms import Ollama
 #READER_MODEL=Ollama(model="meta-llama/Meta-Llama-Guard-2-8B")
 
-from transformers import AutoModelForCausalLM, BitsAndBytesConfig
-lll_model = AutoModelForCausalLM.from_pretrained("unsloth/llama-3-8b-bnb-4bit")
+from transformers import AutoModelForSeq2SeqLM, BitsAndBytesConfig
+lll_model = AutoModelForCausalLM.from_pretrained("unsloth/llama-3-8b-bnb-4bit",low_cpu_mem_usage=True,max_shard_size="1GB")
 
 #READER_MODEL = "HuggingFaceH4/zephyr-7b-beta"