Merge pull request #1723 from huggingface/fix-1623

Fix #1623

examples/distillation/run_squad_w_distillation.py

@@ -506,9 +506,15 @@ def main():
 
     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(args.model_name_or_path, from_tf=bool('.ckpt' in args.model_name_or_path), config=config)
+    config = config_class.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(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(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)
 
     if args.teacher_type is not None:
         assert args.teacher_name_or_path is not None
@@ -516,8 +522,11 @@ def main():
         assert args.alpha_ce + args.alpha_squad > 0.
         assert args.teacher_type != 'distilbert', "We constraint teachers not to be of type DistilBERT."
         teacher_config_class, teacher_model_class, _ = MODEL_CLASSES[args.teacher_type]
-        teacher_config = teacher_config_class.from_pretrained(args.teacher_name_or_path)
-        teacher = teacher_model_class.from_pretrained(args.teacher_name_or_path, config=teacher_config)
+        teacher_config = teacher_config_class.from_pretrained(args.teacher_name_or_path,
+                                                              cache_dir=args.cache_dir if args.cache_dir else None)
+        teacher = teacher_model_class.from_pretrained(args.teacher_name_or_path,
+                                                      config=teacher_config,
+                                                      cache_dir=args.cache_dir if args.cache_dir else None)
         teacher.to(args.device)
     else:
         teacher = None
@@ -553,8 +562,10 @@ 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, do_lower_case=args.do_lower_case)
+        model = model_class.from_pretrained(args.output_dir, cache_dir=args.cache_dir if args.cache_dir else None)
+        tokenizer = tokenizer_class.from_pretrained(args.output_dir,
+                                                    do_lower_case=args.do_lower_case,
+                                                    cache_dir=args.cache_dir if args.cache_dir else None)
         model.to(args.device)
 
 
@@ -571,7 +582,7 @@ 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)
+            model = model_class.from_pretrained(checkpoint, cache_dir=args.cache_dir if args.cache_dir else None)
             model.to(args.device)
 
             # Evaluate

examples/run_bertology.py

@@ -304,10 +304,16 @@ def main():
             break
     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,
-                                          num_labels=num_labels, finetuning_task=args.task_name,
-                                          output_attentions=True)
-    tokenizer = tokenizer_class.from_pretrained(args.tokenizer_name if args.tokenizer_name else args.model_name_or_path)
-    model = model_class.from_pretrained(args.model_name_or_path, from_tf=bool('.ckpt' in args.model_name_or_path), config=config)
+                                          num_labels=num_labels,
+                                          finetuning_task=args.task_name,
+                                          output_attentions=True,
+                                          cache_dir=args.cache_dir if args.cache_dir else None)
+    tokenizer = tokenizer_class.from_pretrained(args.tokenizer_name if args.tokenizer_name else args.model_name_or_path,
+                                                cache_dir=args.cache_dir if args.cache_dir else None)
+    model = model_class.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)
 
     if args.local_rank == 0:
         torch.distributed.barrier()  # Make sure only the first process in distributed training will download model & vocab

examples/run_glue.py

@@ -477,9 +477,17 @@ def main():
 
     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, num_labels=num_labels, finetuning_task=args.task_name)
-    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(args.model_name_or_path, from_tf=bool('.ckpt' in args.model_name_or_path), config=config)
+    config = config_class.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(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(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)
 
     if args.local_rank == 0:
         torch.distributed.barrier()  # Make sure only the first process in distributed training will download model & vocab
@@ -514,7 +522,7 @@ def main():
 
         # 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, do_lower_case=args.do_lower_case)
+        tokenizer = tokenizer_class.from_pretrained(args.output_dir)
         model.to(args.device)
 
 

examples/run_lm_finetuning.py

@@ -471,12 +471,18 @@ def main():
         torch.distributed.barrier()  # Barrier to make sure only the first process in distributed training download model & vocab
 
     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)
+    config = config_class.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(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)
     if args.block_size <= 0:
         args.block_size = tokenizer.max_len_single_sentence  # Our input block size will be the max possible for the model
     args.block_size = min(args.block_size, tokenizer.max_len_single_sentence)
-    model = model_class.from_pretrained(args.model_name_or_path, from_tf=bool('.ckpt' in args.model_name_or_path), config=config)
+    model = model_class.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)
     model.to(args.device)
 
     if args.local_rank == 0:

examples/run_multiple_choice.py

@@ -464,9 +464,17 @@ def main():
 
     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, num_labels=num_labels, finetuning_task=args.task_name)
-    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(args.model_name_or_path, from_tf=bool('.ckpt' in args.model_name_or_path), config=config)
+    config = config_class.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(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(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)
 
     if args.local_rank == 0:
         torch.distributed.barrier()  # Make sure only the first process in distributed training will download model & vocab

examples/run_ner.py

@@ -428,11 +428,15 @@ def main():
     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,
-                                          num_labels=num_labels)
+                                          num_labels=num_labels,
+                                          cache_dir=args.cache_dir if args.cache_dir else None)
     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(args.model_name_or_path, from_tf=bool(".ckpt" in args.model_name_or_path),
-                                        config=config)
+                                                do_lower_case=args.do_lower_case,
+                                                cache_dir=args.cache_dir if args.cache_dir else None)
+    model = model_class.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)
 
     if args.local_rank == 0:
         torch.distributed.barrier()  # Make sure only the first process in distributed training will download model & vocab

examples/run_squad.py

@@ -477,9 +477,15 @@ def main():
 
     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(args.model_name_or_path, from_tf=bool('.ckpt' in args.model_name_or_path), config=config)
+    config = config_class.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(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(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)
 
     if args.local_rank == 0:
         torch.distributed.barrier()  # Make sure only the first process in distributed training will download model & vocab

templates/adding_a_new_example_script/run_xxx.py

@@ -472,9 +472,15 @@ def main():
 
     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(args.model_name_or_path, from_tf=bool('.ckpt' in args.model_name_or_path), config=config)
+    config = config_class.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(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(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)
 
     if args.local_rank == 0:
         torch.distributed.barrier()  # Make sure only the first process in distributed training will download model & vocab