Update src/streamlit_app.py

src/streamlit_app.py

@@ -76,8 +76,14 @@ def gpt_chat(sys_msg: str, user_msg: str, **kwargs):
 class SimpleEncoder:
     def __init__(self):
         self.device = "cuda" if torch.cuda.is_available() else "cpu"
-        self.tokenizer = AutoTokenizer.from_pretrained("sentence-transformers/all-MiniLM-L6-v2")
-        self.model = AutoModel.from_pretrained("sentence-transformers/all-MiniLM-L6-v2").to(self.device)
+        self.tokenizer = AutoTokenizer.from_pretrained(
+            "sentence-transformers/all-MiniLM-L6-v2",
+            cache_dir="/tmp/hf_cache"
+        )
+        self.model = AutoModel.from_pretrained(
+            "sentence-transformers/all-MiniLM-L6-v2",
+            cache_dir="/tmp/hf_cache"
+        ).to(self.device)
         self.model.eval()
 
     def encode(self, texts, batch_size: int = 16):