Update app.py

app.py

@@ -11,39 +11,7 @@ from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStream
 MODEL_ID = "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B"
 CHAT_TEMPLATE = "َAuto"
 MODEL_NAME = MODEL_ID.split("/")[-1]
-CONTEXT_LENGTH = 16000
-  
-
-
-latex_delimiters_set = [{
-        "left": "\\(",
-        "right": "\\)",
-        "display": False 
-    }, {
-        "left": "\\begin{equation}",
-        "right": "\\end{equation}",
-        "display": True 
-    }, {
-        "left": "\\begin{align}",
-        "right": "\\end{align}",
-        "display": True
-    }, {
-        "left": "\\begin{alignat}",
-        "right": "\\end{alignat}",
-        "display": True
-    }, {
-        "left": "\\begin{gather}",
-        "right": "\\end{gather}",
-        "display": True
-    }, {
-        "left": "\\begin{CD}",
-        "right": "\\end{CD}",
-        "display": True
-    }, {
-        "left": "\\[",
-        "right": "\\]",
-        "display": True
-    }]
+CONTEXT_LENGTH = 4096
 
 
 def predict(message, history, system_prompt, temperature, max_new_tokens, top_k, repetition_penalty, top_p):
@@ -100,7 +68,7 @@ gr.ChatInterface(
     additional_inputs=[
         gr.Textbox("You are a useful assistant. first recognize user request and then reply carfuly and thinking", label="System prompt"),
         gr.Slider(0, 1, 0.6, label="Temperature"),
-        gr.Slider(0, 32000, 10000, label="Max new tokens"),
+        gr.Slider(0, 4096, 512, label="Max new tokens"),
         gr.Slider(1, 80, 40, label="Top K sampling"),
         gr.Slider(0, 2, 1.1, label="Repetition penalty"),
         gr.Slider(0, 1, 0.95, label="Top P sampling"),