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/text-classification/run_xnli.py

@@ -13,7 +13,7 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-""" Finetuning multi-lingual models on XNLI (Bert, DistilBERT, XLM).
+""" Finetuning multi-lingual models on XNLI (e.g. Bert, DistilBERT, XLM).
     Adapted from `examples/text-classification/run_glue.py`"""
 
 
@@ -32,15 +32,9 @@ from tqdm import tqdm, trange
 from transformers import (
     WEIGHTS_NAME,
     AdamW,
-    BertConfig,
-    BertForSequenceClassification,
-    BertTokenizer,
-    DistilBertConfig,
-    DistilBertForSequenceClassification,
-    DistilBertTokenizer,
-    XLMConfig,
-    XLMForSequenceClassification,
-    XLMTokenizer,
+    AutoConfig,
+    AutoModelForSequenceClassification,
+    AutoTokenizer,
     get_linear_schedule_with_warmup,
 )
 from transformers import glue_convert_examples_to_features as convert_examples_to_features
@@ -57,16 +51,6 @@ except ImportError:
 
 logger = logging.getLogger(__name__)
 
-ALL_MODELS = sum(
-    (tuple(conf.pretrained_config_archive_map.keys()) for conf in (BertConfig, DistilBertConfig, XLMConfig)), ()
-)
-
-MODEL_CLASSES = {
-    "bert": (BertConfig, BertForSequenceClassification, BertTokenizer),
-    "xlm": (XLMConfig, XLMForSequenceClassification, XLMTokenizer),
-    "distilbert": (DistilBertConfig, DistilBertForSequenceClassification, DistilBertTokenizer),
-}
-
 
 def set_seed(args):
     random.seed(args.seed)
@@ -377,19 +361,12 @@ def main():
         required=True,
         help="The input data dir. Should contain the .tsv files (or other data files) for the task.",
     )
-    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(
         "--language",
@@ -421,7 +398,7 @@ def main():
     )
     parser.add_argument(
         "--cache_dir",
-        default="",
+        default=None,
         type=str,
         help="Where do you want to store the pre-trained models downloaded from s3",
     )
@@ -562,24 +539,23 @@ 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(
+    config = AutoConfig.from_pretrained(
         args.config_name if args.config_name else args.model_name_or_path,
         num_labels=num_labels,
         finetuning_task=args.task_name,
-        cache_dir=args.cache_dir if args.cache_dir else None,
+        cache_dir=args.cache_dir,
     )
-    tokenizer = tokenizer_class.from_pretrained(
+    args.model_type = config.model_type
+    tokenizer = AutoTokenizer.from_pretrained(
         args.tokenizer_name if args.tokenizer_name else args.model_name_or_path,
         do_lower_case=args.do_lower_case,
-        cache_dir=args.cache_dir if args.cache_dir else None,
+        cache_dir=args.cache_dir,
     )
-    model = model_class.from_pretrained(
+    model = AutoModelForSequenceClassification.from_pretrained(
         args.model_name_or_path,
         from_tf=bool(".ckpt" in args.model_name_or_path),
         config=config,
-        cache_dir=args.cache_dir if args.cache_dir else None,
+        cache_dir=args.cache_dir,
     )
 
     if args.local_rank == 0:
@@ -614,14 +590,13 @@ 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 = AutoModelForSequenceClassification.from_pretrained(args.output_dir)
+        tokenizer = AutoTokenizer.from_pretrained(args.output_dir)
         model.to(args.device)
 
     # Evaluation
     results = {}
     if args.do_eval and args.local_rank in [-1, 0]:
-        tokenizer = tokenizer_class.from_pretrained(args.output_dir, do_lower_case=args.do_lower_case)
         checkpoints = [args.output_dir]
         if args.eval_all_checkpoints:
             checkpoints = list(
@@ -633,7 +608,7 @@ def main():
             global_step = checkpoint.split("-")[-1] if len(checkpoints) > 1 else ""
             prefix = checkpoint.split("/")[-1] if checkpoint.find("checkpoint") != -1 else ""
 
-            model = model_class.from_pretrained(checkpoint)
+            model = AutoModelForSequenceClassification.from_pretrained(checkpoint)
             model.to(args.device)
             result = evaluate(args, model, tokenizer, prefix=prefix)
             result = dict((k + "_{}".format(global_step), v) for k, v in result.items())