Kill model archive maps (#4636)

* Kill model archive maps

* Fixup

* Also kill model_archive_map for MaskedBertPreTrainedModel

* Unhook config_archive_map

* Tokenizers: align with model id changes

* make style && make quality

* Fix CI

examples/contrib/run_swag.py

@@ -31,14 +31,8 @@ from torch.utils.data import DataLoader, RandomSampler, SequentialSampler, Tenso
 from torch.utils.data.distributed import DistributedSampler
 from tqdm import tqdm, trange
 
-from transformers import (
-    WEIGHTS_NAME,
-    AdamW,
-    BertConfig,
-    BertForMultipleChoice,
-    BertTokenizer,
-    get_linear_schedule_with_warmup,
-)
+from transformers import WEIGHTS_NAME, AdamW, AutoConfig, AutoTokenizer, get_linear_schedule_with_warmup
+from transformers.modeling_auto import AutoModelForMultipleChoice
 
 
 try:
@@ -49,12 +43,6 @@ except ImportError:
 
 logger = logging.getLogger(__name__)
 
-ALL_MODELS = sum((tuple(conf.pretrained_config_archive_map.keys()) for conf in [BertConfig]), ())
-
-MODEL_CLASSES = {
-    "bert": (BertConfig, BertForMultipleChoice, BertTokenizer),
-}
-
 
 class SwagExample(object):
     """A single training/test example for the SWAG dataset."""
@@ -492,19 +480,12 @@ def main():
         required=True,
         help="SWAG csv for predictions. E.g., val.csv or test.csv",
     )
-    parser.add_argument(
-        "--model_type",
-        default=None,
-        type=str,
-        required=True,
-        help="Model type selected in the list: " + ", ".join(MODEL_CLASSES.keys()),
-    )
     parser.add_argument(
         "--model_name_or_path",
         default=None,
         type=str,
         required=True,
-        help="Path to pre-trained model or shortcut name selected in the list: " + ", ".join(ALL_MODELS),
+        help="Path to pretrained model or model identifier from huggingface.co/models",
     )
     parser.add_argument(
         "--output_dir",
@@ -536,9 +517,6 @@ def main():
     parser.add_argument(
         "--evaluate_during_training", action="store_true", help="Rul evaluation during training at each logging step."
     )
-    parser.add_argument(
-        "--do_lower_case", action="store_true", help="Set this flag if you are using an uncased model."
-    )
 
     parser.add_argument("--per_gpu_train_batch_size", default=8, type=int, help="Batch size per GPU/CPU for training.")
     parser.add_argument(
@@ -652,13 +630,9 @@ def main():
     if args.local_rank not in [-1, 0]:
         torch.distributed.barrier()  # Make sure only the first process in distributed training will download model & vocab
 
-    args.model_type = args.model_type.lower()
-    config_class, model_class, tokenizer_class = MODEL_CLASSES[args.model_type]
-    config = config_class.from_pretrained(args.config_name if args.config_name else args.model_name_or_path)
-    tokenizer = tokenizer_class.from_pretrained(
-        args.tokenizer_name if args.tokenizer_name else args.model_name_or_path, do_lower_case=args.do_lower_case
-    )
-    model = model_class.from_pretrained(
+    config = AutoConfig.from_pretrained(args.config_name if args.config_name else args.model_name_or_path)
+    tokenizer = AutoTokenizer.from_pretrained(args.tokenizer_name if args.tokenizer_name else args.model_name_or_path,)
+    model = AutoModelForMultipleChoice.from_pretrained(
         args.model_name_or_path, from_tf=bool(".ckpt" in args.model_name_or_path), config=config
     )
 
@@ -694,8 +668,8 @@ def main():
         torch.save(args, os.path.join(args.output_dir, "training_args.bin"))
 
         # Load a trained model and vocabulary that you have fine-tuned
-        model = model_class.from_pretrained(args.output_dir)
-        tokenizer = tokenizer_class.from_pretrained(args.output_dir)
+        model = AutoModelForMultipleChoice.from_pretrained(args.output_dir)
+        tokenizer = AutoTokenizer.from_pretrained(args.output_dir)
         model.to(args.device)
 
     # Evaluation - we can ask to evaluate all the checkpoints (sub-directories) in a directory
@@ -718,8 +692,8 @@ def main():
         for checkpoint in checkpoints:
             # Reload the model
             global_step = checkpoint.split("-")[-1] if len(checkpoints) > 1 else ""
-            model = model_class.from_pretrained(checkpoint)
-            tokenizer = tokenizer_class.from_pretrained(checkpoint)
+            model = AutoModelForMultipleChoice.from_pretrained(checkpoint)
+            tokenizer = AutoTokenizer.from_pretrained(checkpoint)
             model.to(args.device)
 
             # Evaluate