Update app.py

app.py

@@ -181,7 +181,7 @@ quantization_config = BitsAndBytesConfig(
 
 
 
-model_id = "Daemontatox/MawaredT3" 
+model_id = "Daemontatox/Mawared_GS" 
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 
 model = AutoModelForCausalLM.from_pretrained(
@@ -189,7 +189,7 @@ model = AutoModelForCausalLM.from_pretrained(
          torch_dtype=torch.float16,
          device_map="cuda",
          attn_implementation="flash_attention_2",
-         quantization_config=quantization_config
+         #quantization_config=quantization_config
 )
 
 pipe = pipeline("text-generation", model=model, tokenizer=tokenizer, max_new_tokens=8192 )