Update app.py

app.py

@@ -25,7 +25,7 @@ def main():
 
         model = "daryl149/llama-2-7b-chat-hf"
         tokenizer = AutoTokenizer.from_pretrained(model)
-        pipeline = transformers.pipeline("text-generation", model=model, tokenizer=tokenizer, torch_dtype=torch.bfloat16, trust_remote_code=True, device_map="auto", do_sample=True, top_k=1, num_return_sequences=1, eos_token_id=tokenizer.eos_token_id)
+        pipeline = transformers.pipeline("text-generation", model=model, tokenizer=tokenizer, torch_dtype=torch.bfloat16, device_map="auto", do_sample=True, top_k=1, num_return_sequences=1, eos_token_id=tokenizer.eos_token_id,offload_folder="offload")
 
         llm = HuggingFacePipeline(pipeline=pipeline, model_kwargs={'temperature': 0})
         embeddings = HuggingFaceEmbeddings(model_name='sentence-transformers/all-MiniLM-L6-v2')