Improve model tester (#19984)

* part 1

* part 2

* part 3

* fix

* For CANINE

* For ESMFold

Co-authored-by: ydshieh <ydshieh@users.noreply.github.com>

tests/models/xlm/test_modeling_xlm.py

@@ -42,35 +42,62 @@ class XLMModelTester:
     def __init__(
         self,
         parent,
+        batch_size=13,
+        seq_length=7,
+        is_training=True,
+        use_input_lengths=True,
+        use_token_type_ids=True,
+        use_labels=True,
+        gelu_activation=True,
+        sinusoidal_embeddings=False,
+        causal=False,
+        asm=False,
+        n_langs=2,
+        vocab_size=99,
+        n_special=0,
+        hidden_size=32,
+        num_hidden_layers=5,
+        num_attention_heads=4,
+        hidden_dropout_prob=0.1,
+        attention_probs_dropout_prob=0.1,
+        max_position_embeddings=512,
+        type_sequence_label_size=2,
+        initializer_range=0.02,
+        num_labels=2,
+        num_choices=4,
+        summary_type="last",
+        use_proj=True,
+        scope=None,
+        bos_token_id=0,
     ):
         self.parent = parent
-        self.batch_size = 13
-        self.seq_length = 7
-        self.is_training = True
-        self.use_input_lengths = True
-        self.use_token_type_ids = True
-        self.use_labels = True
-        self.gelu_activation = True
-        self.sinusoidal_embeddings = False
-        self.causal = False
-        self.asm = False
-        self.n_langs = 2
-        self.vocab_size = 99
-        self.n_special = 0
-        self.hidden_size = 32
-        self.num_hidden_layers = 5
-        self.num_attention_heads = 4
-        self.hidden_dropout_prob = 0.1
-        self.attention_probs_dropout_prob = 0.1
-        self.max_position_embeddings = 512
-        self.type_sequence_label_size = 2
-        self.initializer_range = 0.02
-        self.num_labels = 2
-        self.num_choices = 4
-        self.summary_type = "last"
-        self.use_proj = True
-        self.scope = None
-        self.bos_token_id = 0
+        self.batch_size = batch_size
+        self.seq_length = seq_length
+        self.is_training = is_training
+        self.use_input_lengths = use_input_lengths
+        self.use_token_type_ids = use_token_type_ids
+        self.use_labels = use_labels
+        self.gelu_activation = gelu_activation
+        self.sinusoidal_embeddings = sinusoidal_embeddings
+        self.causal = causal
+        self.asm = asm
+        self.n_langs = n_langs
+        self.vocab_size = vocab_size
+        self.n_special = n_special
+        self.hidden_size = hidden_size
+        self.num_hidden_layers = num_hidden_layers
+        self.num_attention_heads = num_attention_heads
+        self.hidden_dropout_prob = hidden_dropout_prob
+        self.attention_probs_dropout_prob = attention_probs_dropout_prob
+        self.max_position_embeddings = max_position_embeddings
+        self.type_sequence_label_size = type_sequence_label_size
+        self.initializer_range = initializer_range
+        self.num_labels = num_labels
+        self.num_choices = num_choices
+        self.summary_type = summary_type
+        self.use_proj = use_proj
+        self.scope = scope
+        self.bos_token_id = bos_token_id
 
     def prepare_config_and_inputs(self):
         input_ids = ids_tensor([self.batch_size, self.seq_length], self.vocab_size)