Update app.py

app.py

@@ -208,7 +208,7 @@ def predict(
     temperature,
     repetition_penalty,
     max_length_tokens,
-    max_context_length_tokens,
+    # max_context_length_tokens,
     model_select_dropdown,
 ):
     """
@@ -247,7 +247,7 @@ def predict(
         # history,
         vl_chat_processor,
         tokenizer,
-        max_length=max_context_length_tokens,
+        # max_length=max_context_length_tokens,
     )
     prompts = convert_conversation_to_prompts(conversation)
 
@@ -296,7 +296,7 @@ def retry(
     temperature,
     repetition_penalty,
     max_length_tokens,
-    max_context_length_tokens,
+    # max_context_length_tokens,
     model_select_dropdown,
 ):
     if len(history) == 0:
@@ -318,7 +318,7 @@ def retry(
         temperature,
         repetition_penalty,
         max_length_tokens,
-        max_context_length_tokens,
+        # max_context_length_tokens,
         model_select_dropdown,
     )
 
@@ -403,14 +403,14 @@ def build_demo(MODELS):
                         interactive=True,
                         label="Max Generation Tokens",
                     )
-                    max_context_length_tokens = gr.Slider(
-                        minimum=0,
-                        maximum=2048,
-                        value=2048,
-                        step=128,
-                        interactive=True,
-                        label="Max History Tokens",
-                    )
+                    #  max_context_length_tokens = gr.Slider(
+                    #     minimum=0,
+                    #     maximum=2048,
+                    #     value=2048,
+                    #     step=128,
+                    #     interactive=True,
+                    #     label="Max History Tokens",
+                    # )
                     model_select_dropdown = gr.Dropdown(
                         label="Select Models",
                         choices=MODELS,