Update app.py

app.py

@@ -16,11 +16,11 @@ print(llama_cpp.__version__)
 
 huggingface_token = os.getenv("HUGGINGFACE_TOKEN")
 
-hf_hub_download(
-    repo_id="bartowski/gemma-2-9b-it-GGUF",
-    filename="gemma-2-9b-it-Q5_K_M.gguf",
-    local_dir="./models"
-)
+# hf_hub_download(
+#     repo_id="bartowski/gemma-2-9b-it-GGUF",
+#     filename="gemma-2-9b-it-Q5_K_M.gguf",
+#     local_dir="./models"
+# )
 
 hf_hub_download(
     repo_id="bartowski/gemma-2-27b-it-GGUF",
@@ -28,16 +28,23 @@ hf_hub_download(
     local_dir="./models"
 )
 
-hf_hub_download(
-    repo_id="google/gemma-2-2b-it-GGUF",
-    filename="2b_it_v2.gguf",
-    local_dir="./models",
-    token=huggingface_token
-)
+# hf_hub_download(
+#     repo_id="google/gemma-2-2b-it-GGUF",
+#     filename="2b_it_v2.gguf",
+#     local_dir="./models",
+#     token=huggingface_token
+# )
+
+# hf_hub_download(
+#     repo_id="unsloth/GLM-4.7-Flash-GGUF",
+#     filename="GLM-4.7-Flash-Q2_K.gguf",
+#     local_dir="./models",
+#     token=huggingface_token
+# )
 
 hf_hub_download(
-    repo_id="unsloth/GLM-4.7-Flash-GGUF",
-    filename="GLM-4.7-Flash-Q2_K.gguf",
+    repo_id="TeichAI/GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill-GGUF",
+    filename="glm-4.7-flash-claude-4.5-opus.q8_0.gguf",
     local_dir="./models",
     token=huggingface_token
 )
@@ -147,10 +154,10 @@ demo = gr.ChatInterface(
     additional_inputs=[
         gr.Dropdown(
             [
-                "gemma-2-9b-it-Q5_K_M.gguf",
+                # "gemma-2-9b-it-Q5_K_M.gguf",
                 "gemma-2-27b-it-Q5_K_M.gguf",
-                "2b_it_v2.gguf",
-                "GLM-4.7-Flash-Q2_K.gguf"
+                # "2b_it_v2.gguf",
+                "glm-4.7-flash-claude-4.5-opus.q8_0.gguf"
             ],
             value="2b_it_v2.gguf",
             label="Model",