Fix Gradio Demo

app.py

@@ -324,82 +324,68 @@ def process_model(model_id, q_method, use_imatrix, imatrix_q_method, private_rep
 css="""/* Custom CSS to allow scrolling */
 .gradio-container {overflow-y: auto;}
 """
-# Create Gradio interface
-with gr.Blocks(css=css) as demo: 
-    gr.Markdown("You must be logged in to use GGUF-my-repo.")
-    gr.LoginButton(min_width=250)
-
-    model_id = HuggingfaceHubSearch(
-        label="Hub Model ID",
-        placeholder="Search for model id on Huggingface",
-        search_type="model",
-    )
-
-    q_method = gr.Dropdown(
-        ["Q2_K", "Q3_K_S", "Q3_K_M", "Q3_K_L", "Q4_0", "Q4_K_S", "Q4_K_M", "Q5_0", "Q5_K_S", "Q5_K_M", "Q6_K", "Q8_0"],
-        label="Quantization Method",
-        info="GGML quantization type",
-        value="Q4_K_M",
-        filterable=False,
-        visible=True
-    )
-
-    imatrix_q_method = gr.Dropdown(
-        ["IQ3_M", "IQ3_XXS", "Q4_K_M", "Q4_K_S", "IQ4_NL", "IQ4_XS", "Q5_K_M", "Q5_K_S"],
-        label="Imatrix Quantization Method",
-        info="GGML imatrix quants type",
-        value="IQ4_NL", 
-        filterable=False,
-        visible=False
-    )
-
-    use_imatrix = gr.Checkbox(
-        value=False,
-        label="Use Imatrix Quantization",
-        info="Use importance matrix for quantization."
-    )
-
-    private_repo = gr.Checkbox(
-        value=False,
-        label="Private Repo",
-        info="Create a private repo under your username."
-    )
-
-    train_data_file = gr.File(
-        label="Training Data File",
-        file_types=["txt"],
-        visible=False
-    )
-
-    split_model = gr.Checkbox(
-        value=False,
-        label="Split Model",
-        info="Shard the model using gguf-split."
-    )
-
-    split_max_tensors = gr.Number(
-        value=256,
-        label="Max Tensors per File",
-        info="Maximum number of tensors per file when splitting model.",
-        visible=False
-    )
-
-    split_max_size = gr.Textbox(
-        label="Max File Size",
-        info="Maximum file size when splitting model (--split-max-size). May leave empty to use the default. Accepted suffixes: M, G. Example: 256M, 5G",
-        visible=False
-    )
-
-    def update_visibility(use_imatrix):
-        return gr.update(visible=not use_imatrix), gr.update(visible=use_imatrix), gr.update(visible=use_imatrix)
-    
-    use_imatrix.change(
-        fn=update_visibility,
-        inputs=use_imatrix,
-        outputs=[q_method, imatrix_q_method, train_data_file]
-    )
-
-    iface = gr.Interface(
+model_id = HuggingfaceHubSearch(
+    label="Hub Model ID",
+    placeholder="Search for model id on Huggingface",
+    search_type="model",
+)
+
+q_method = gr.Dropdown(
+    ["Q2_K", "Q3_K_S", "Q3_K_M", "Q3_K_L", "Q4_0", "Q4_K_S", "Q4_K_M", "Q5_0", "Q5_K_S", "Q5_K_M", "Q6_K", "Q8_0"],
+    label="Quantization Method",
+    info="GGML quantization type",
+    value="Q4_K_M",
+    filterable=False,
+    visible=True
+)
+
+imatrix_q_method = gr.Dropdown(
+    ["IQ3_M", "IQ3_XXS", "Q4_K_M", "Q4_K_S", "IQ4_NL", "IQ4_XS", "Q5_K_M", "Q5_K_S"],
+    label="Imatrix Quantization Method",
+    info="GGML imatrix quants type",
+    value="IQ4_NL", 
+    filterable=False,
+    visible=False
+)
+
+use_imatrix = gr.Checkbox(
+    value=False,
+    label="Use Imatrix Quantization",
+    info="Use importance matrix for quantization."
+)
+
+private_repo = gr.Checkbox(
+    value=False,
+    label="Private Repo",
+    info="Create a private repo under your username."
+)
+
+train_data_file = gr.File(
+    label="Training Data File",
+    file_types=["txt"],
+    visible=False
+)
+
+split_model = gr.Checkbox(
+    value=False,
+    label="Split Model",
+    info="Shard the model using gguf-split."
+)
+
+split_max_tensors = gr.Number(
+    value=256,
+    label="Max Tensors per File",
+    info="Maximum number of tensors per file when splitting model.",
+    visible=False
+)
+
+split_max_size = gr.Textbox(
+    label="Max File Size",
+    info="Maximum file size when splitting model (--split-max-size). May leave empty to use the default. Accepted suffixes: M, G. Example: 256M, 5G",
+    visible=False
+)
+
+iface = gr.Interface(
         fn=process_model,
         inputs=[
             model_id,
@@ -421,6 +407,13 @@ with gr.Blocks(css=css) as demo:
         api_name=False
     )
 
+# Create Gradio interface
+with gr.Blocks(css=css) as demo: 
+    gr.Markdown("You must be logged in to use GGUF-my-repo.")
+    gr.LoginButton(min_width=250)
+
+    iface.render()
+
     def update_split_visibility(split_model):
         return gr.update(visible=split_model), gr.update(visible=split_model)
 
@@ -430,6 +423,15 @@ with gr.Blocks(css=css) as demo:
         outputs=[split_max_tensors, split_max_size]
     )
 
+    def update_visibility(use_imatrix):
+        return gr.update(visible=not use_imatrix), gr.update(visible=use_imatrix), gr.update(visible=use_imatrix)
+    
+    use_imatrix.change(
+        fn=update_visibility,
+        inputs=use_imatrix,
+        outputs=[q_method, imatrix_q_method, train_data_file]
+    )
+
 def restart_space():
     HfApi().restart_space(repo_id="ggml-org/gguf-my-repo", token=HF_TOKEN, factory_reboot=True)