Update app.py

app.py

@@ -10,7 +10,7 @@ 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 = "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
+MODEL_ID = "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B"
 CHAT_TEMPLATE = "َAuto"
 MODEL_NAME = MODEL_ID.split("/")[-1]
 CONTEXT_LENGTH = 16000
@@ -102,7 +102,7 @@ tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
 model = AutoModelForCausalLM.from_pretrained(
     MODEL_ID,
     device_map="auto",
-    quantization_config=quantization_config,
+    #quantization_config=quantization_config,
     attn_implementation="flash_attention_2",
 )