Update app.py

app.py

@@ -50,22 +50,22 @@ huggingface_token = os.getenv("HUGGINGFACE_TOKEN")
 # )
 # from huggingface_hub import snapshot_download
 
-# snapshot_download(
-#     repo_id="stepfun-ai/Step-3.5-Flash-GGUF-Q4_K_S",
-#     repo_type="model",
-#     local_dir="./models/stepfun",
-#     # allow_patterns=["UD-TQ1_0/*"],   # 👈 folder inside repo
-#     token=huggingface_token      # only if gated/private
-# )
+snapshot_download(
+    repo_id="stepfun-ai/Step-3.5-Flash-GGUF-Q4_K_S",
+    repo_type="model",
+    local_dir="./models/stepfun",
+    # allow_patterns=["UD-TQ1_0/*"],   # 👈 folder inside repo
+    token=huggingface_token      # only if gated/private
+)
 
 
 
-llm = Llama.from_pretrained(
-    repo_id="stepfun-ai/Step-3.5-Flash-GGUF-Q4_K_S",
-     filename="step3p5_flash_Q4_K_S-00001-of-00012.gguf",
-    allow_patterns=["UD-TQ1_0/*.gguf"],
-    verbose=False
-)
+# llm = Llama.from_pretrained(
+#     repo_id="stepfun-ai/Step-3.5-Flash-GGUF-Q4_K_S",
+#      filename="step3p5_flash_Q4_K_S-00001-of-00012.gguf",
+#     allow_patterns=["UD-TQ1_0/*.gguf"],
+#     verbose=False
+# )
 
 
 
@@ -170,7 +170,7 @@ demo = gr.ChatInterface(
                 "gemma-2-27b-it-Q5_K_M.gguf",
                 # "2b_it_v2.gguf",
                 "GLM-4.7-Flash-UD-Q8_K_XL.gguf",
-                "stepfun/step3p5_flash_Q4_K_S-00001-of-00012.gguf"
+                "stepfun"
             ],
             value="GLM-4.7-Flash-UD-Q8_K_XL.gguf",
             label="Model",