[examples] Use AutoModels in more examples

examples/run_glue.py

@@ -30,32 +30,12 @@ from torch.utils.data.distributed import DistributedSampler
 from tqdm import tqdm, trange
 
 from transformers import (
+    MODEL_FOR_SEQUENCE_CLASSIFICATION_MAPPING,
     WEIGHTS_NAME,
     AdamW,
-    AlbertConfig,
-    AlbertForSequenceClassification,
-    AlbertTokenizer,
-    BertConfig,
-    BertForSequenceClassification,
-    BertTokenizer,
-    DistilBertConfig,
-    DistilBertForSequenceClassification,
-    DistilBertTokenizer,
-    FlaubertConfig,
-    FlaubertForSequenceClassification,
-    FlaubertTokenizer,
-    RobertaConfig,
-    RobertaForSequenceClassification,
-    RobertaTokenizer,
-    XLMConfig,
-    XLMForSequenceClassification,
-    XLMRobertaConfig,
-    XLMRobertaForSequenceClassification,
-    XLMRobertaTokenizer,
-    XLMTokenizer,
-    XLNetConfig,
-    XLNetForSequenceClassification,
-    XLNetTokenizer,
+    AutoConfig,
+    AutoModelForSequenceClassification,
+    AutoTokenizer,
     get_linear_schedule_with_warmup,
 )
 from transformers import glue_compute_metrics as compute_metrics
@@ -72,33 +52,10 @@ except ImportError:
 
 logger = logging.getLogger(__name__)
 
-ALL_MODELS = sum(
-    (
-        tuple(conf.pretrained_config_archive_map.keys())
-        for conf in (
-            BertConfig,
-            XLNetConfig,
-            XLMConfig,
-            RobertaConfig,
-            DistilBertConfig,
-            AlbertConfig,
-            XLMRobertaConfig,
-            FlaubertConfig,
-        )
-    ),
-    (),
-)
+MODEL_CONFIG_CLASSES = list(MODEL_FOR_SEQUENCE_CLASSIFICATION_MAPPING.keys())
+MODEL_TYPES = tuple(conf.model_type for conf in MODEL_CONFIG_CLASSES)
 
-MODEL_CLASSES = {
-    "bert": (BertConfig, BertForSequenceClassification, BertTokenizer),
-    "xlnet": (XLNetConfig, XLNetForSequenceClassification, XLNetTokenizer),
-    "xlm": (XLMConfig, XLMForSequenceClassification, XLMTokenizer),
-    "roberta": (RobertaConfig, RobertaForSequenceClassification, RobertaTokenizer),
-    "distilbert": (DistilBertConfig, DistilBertForSequenceClassification, DistilBertTokenizer),
-    "albert": (AlbertConfig, AlbertForSequenceClassification, AlbertTokenizer),
-    "xlmroberta": (XLMRobertaConfig, XLMRobertaForSequenceClassification, XLMRobertaTokenizer),
-    "flaubert": (FlaubertConfig, FlaubertForSequenceClassification, FlaubertTokenizer),
-}
+ALL_MODELS = sum((tuple(conf.pretrained_config_archive_map.keys()) for conf in MODEL_CONFIG_CLASSES), (),)
 
 
 def set_seed(args):
@@ -442,7 +399,7 @@ 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",
@@ -622,19 +579,18 @@ def main():
         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,
     )
-    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 = AutoModelForSequenceClassification.from_pretrained(
         args.model_name_or_path,
         from_tf=bool(".ckpt" in args.model_name_or_path),
         config=config,
@@ -673,14 +629,14 @@ 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)
+        tokenizer = AutoTokenizer.from_pretrained(args.output_dir, do_lower_case=args.do_lower_case)
         checkpoints = [args.output_dir]
         if args.eval_all_checkpoints:
             checkpoints = list(
@@ -692,7 +648,7 @@ 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())