Update app.py

app.py

@@ -10,46 +10,15 @@ from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
 
 subprocess.run('pip install flash-attn --no-build-isolation', env={'FLASH_ATTENTION_SKIP_CUDA_BUILD': "TRUE"}, shell=True)
 
-MODEL_ID = "nikravan/Marco_o1_q4"
+MODEL_ID = "nikravan/Marco-o1-q4"
 CHAT_TEMPLATE = "ChatML"
 MODEL_NAME = MODEL_ID.split("/")[-1]
 CONTEXT_LENGTH = 16000
 
-# Estableciendo valores directamente para las variables
-COLOR = "blue"
+COLOR = "black"  # تغییر رنگ به مشکی
 EMOJI = "🤖"
 DESCRIPTION = f"This is the {MODEL_NAME} model designed for testing thinking for general AI tasks."
 
-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
-    }]
-
 
 @spaces.GPU()
 def predict(message, history, system_prompt, temperature, max_new_tokens, top_k, repetition_penalty, top_p):
@@ -73,7 +42,6 @@ def predict(message, history, system_prompt, temperature, max_new_tokens, top_k,
         instruction += f' {message} [/INST]'
     else:
         raise Exception("Incorrect chat template, select 'Auto', 'ChatML' or 'Mistral Instruct'")
-    print(instruction)
     
     streamer = TextIteratorStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
     enc = tokenizer(instruction, return_tensors="pt", padding=True, truncation=True)
@@ -102,7 +70,8 @@ def predict(message, history, system_prompt, temperature, max_new_tokens, top_k,
         if new_token in stop_tokens:
             break
         result = "".join(outputs)
-        yield f"$$ {result} $$"
+        # تغییر قالب به Markdown و LaTeX
+        yield f"### $$ {result} $$"
 
 
 device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
@@ -133,3 +102,4 @@ gr.ChatInterface(
     ],
     theme=gr.themes.Soft(primary_hue=COLOR),
 ).queue().launch()
+