update config kwargs

app.py

@@ -56,8 +56,8 @@ def load_model():
         truncation=True,
         padding=True, )
     ankerbot_model.to("cuda") 
-    generator = pipeline(task="text-generation", model=ankerbot_model, tokenizer=ankerbot_tokenizer, torch_dtype=torch.float16, attn_implementation="eager", use_flash_attention_2=False) # True for flash-attn2 else False
-    generator_mini = pipeline(task="text-generation", model=ankerbot_model, tokenizer=ankerbot_tokenizer, torch_dtype=torch.float16, attn_implementation="eager", use_flash_attention_2=False) # True for flash-attn2 else False
+    generator = pipeline(task="text-generation", model=ankerbot_model, tokenizer=ankerbot_tokenizer, torch_dtype=torch.float16, trust_remote_code=False) # True for flash-attn2 else False
+    generator_mini = pipeline(task="text-generation", model=ankerbot_model, tokenizer=ankerbot_tokenizer, torch_dtype=torch.float16, trust_remote_code=False) # True for flash-attn2 else False
     return (generator, generator_mini)
     
 _model_cache = None