[examples] Use AutoModels in more examples

examples/run_squad.py

@@ -30,29 +30,12 @@ from torch.utils.data.distributed import DistributedSampler
 from tqdm import tqdm, trange
 
 from transformers import (
+    MODEL_FOR_QUESTION_ANSWERING_MAPPING,
     WEIGHTS_NAME,
     AdamW,
-    AlbertConfig,
-    AlbertForQuestionAnswering,
-    AlbertTokenizer,
-    BertConfig,
-    BertForQuestionAnswering,
-    BertTokenizer,
-    CamembertConfig,
-    CamembertForQuestionAnswering,
-    CamembertTokenizer,
-    DistilBertConfig,
-    DistilBertForQuestionAnswering,
-    DistilBertTokenizer,
-    RobertaConfig,
-    RobertaForQuestionAnswering,
-    RobertaTokenizer,
-    XLMConfig,
-    XLMForQuestionAnswering,
-    XLMTokenizer,
-    XLNetConfig,
-    XLNetForQuestionAnswering,
-    XLNetTokenizer,
+    AutoConfig,
+    AutoModelForQuestionAnswering,
+    AutoTokenizer,
     get_linear_schedule_with_warmup,
     squad_convert_examples_to_features,
 )
@@ -72,23 +55,10 @@ except ImportError:
 
 logger = logging.getLogger(__name__)
 
-ALL_MODELS = sum(
-    (
-        tuple(conf.pretrained_config_archive_map.keys())
-        for conf in (BertConfig, CamembertConfig, RobertaConfig, XLNetConfig, XLMConfig)
-    ),
-    (),
-)
+MODEL_CONFIG_CLASSES = list(MODEL_FOR_QUESTION_ANSWERING_MAPPING.keys())
+MODEL_TYPES = tuple(conf.model_type for conf in MODEL_CONFIG_CLASSES)
 
-MODEL_CLASSES = {
-    "bert": (BertConfig, BertForQuestionAnswering, BertTokenizer),
-    "camembert": (CamembertConfig, CamembertForQuestionAnswering, CamembertTokenizer),
-    "roberta": (RobertaConfig, RobertaForQuestionAnswering, RobertaTokenizer),
-    "xlnet": (XLNetConfig, XLNetForQuestionAnswering, XLNetTokenizer),
-    "xlm": (XLMConfig, XLMForQuestionAnswering, XLMTokenizer),
-    "distilbert": (DistilBertConfig, DistilBertForQuestionAnswering, DistilBertTokenizer),
-    "albert": (AlbertConfig, AlbertForQuestionAnswering, AlbertTokenizer),
-}
+ALL_MODELS = sum((tuple(conf.pretrained_config_archive_map.keys()) for conf in MODEL_CONFIG_CLASSES), (),)
 
 
 def set_seed(args):
@@ -513,7 +483,7 @@ def main():
         default=None,
         type=str,
         required=True,
-        help="Model type selected in the list: " + ", ".join(MODEL_CLASSES.keys()),
+        help="Model type selected in the list: " + ", ".join(MODEL_TYPES),
     )
     parser.add_argument(
         "--model_name_or_path",
@@ -757,17 +727,16 @@ def main():
         torch.distributed.barrier()
 
     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,
         cache_dir=args.cache_dir if args.cache_dir else None,
     )
-    tokenizer = tokenizer_class.from_pretrained(
+    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,
     )
-    model = model_class.from_pretrained(
+    model = AutoModelForQuestionAnswering.from_pretrained(
         args.model_name_or_path,
         from_tf=bool(".ckpt" in args.model_name_or_path),
         config=config,
@@ -817,8 +786,8 @@ 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)  # , force_download=True)
-        tokenizer = tokenizer_class.from_pretrained(args.output_dir, do_lower_case=args.do_lower_case)
+        model = AutoModelForQuestionAnswering.from_pretrained(args.output_dir)  # , force_download=True)
+        tokenizer = AutoTokenizer.from_pretrained(args.output_dir, do_lower_case=args.do_lower_case)
         model.to(args.device)
 
     # Evaluation - we can ask to evaluate all the checkpoints (sub-directories) in a directory
@@ -842,7 +811,7 @@ 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)  # , force_download=True)
+            model = AutoModelForQuestionAnswering.from_pretrained(checkpoint)  # , force_download=True)
             model.to(args.device)
 
             # Evaluate