Update agents/research_agent.py

agents/research_agent.py

@@ -13,7 +13,7 @@ class ResearchAgent:
         model_name = getattr(settings, "HF_MODEL_RESEARCH", "google/flan-t5-large")
         
         self.tokenizer = AutoTokenizer.from_pretrained(model_name)
-        self.model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
+        self.model = AutoModelForSeq2SeqLM.from_pretrained(model_name, torch_dtype=torch.float16)
 
         self.device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
         self.model.to(self.device)