Update all references to canonical models (#29001)

* Script & Manual edition

* Update

examples/legacy/seq2seq/README.md

@@ -170,7 +170,7 @@ If 'translation' is in your task name, the computed metric will be BLEU. Otherwi
 For t5, you need to specify --task translation_{src}_to_{tgt} as follows:
 ```bash
 export DATA_DIR=wmt_en_ro
-./run_eval.py t5-base \
+./run_eval.py google-t5/t5-base \
     $DATA_DIR/val.source t5_val_generations.txt \
     --reference_path $DATA_DIR/val.target \
     --score_path enro_bleu.json \

examples/legacy/seq2seq/old_test_datasets.py

@@ -28,7 +28,7 @@ from transformers.testing_utils import TestCasePlus, slow
 from utils import FAIRSEQ_AVAILABLE, DistributedSortishSampler, LegacySeq2SeqDataset, Seq2SeqDataset
 
 
-BERT_BASE_CASED = "bert-base-cased"
+BERT_BASE_CASED = "google-bert/bert-base-cased"
 PEGASUS_XSUM = "google/pegasus-xsum"
 ARTICLES = [" Sam ate lunch today.", "Sams lunch ingredients."]
 SUMMARIES = ["A very interesting story about what I ate for lunch.", "Avocado, celery, turkey, coffee"]

examples/legacy/seq2seq/pack_dataset.py

@@ -74,7 +74,7 @@ def pack_data_dir(tok, data_dir: Path, max_tokens, save_path):
 
 def packer_cli():
     parser = argparse.ArgumentParser()
-    parser.add_argument("--tok_name", type=str, help="like facebook/bart-large-cnn,t5-base, etc.")
+    parser.add_argument("--tok_name", type=str, help="like facebook/bart-large-cnn,google-t5/t5-base, etc.")
     parser.add_argument("--max_seq_len", type=int, default=128)
     parser.add_argument("--data_dir", type=str)
     parser.add_argument("--save_path", type=str)

examples/legacy/seq2seq/run_distributed_eval.py

@@ -124,7 +124,7 @@ def run_generate():
     parser.add_argument(
         "--model_name",
         type=str,
-        help="like facebook/bart-large-cnn,t5-base, etc.",
+        help="like facebook/bart-large-cnn,google-t5/t5-base, etc.",
         default="sshleifer/distilbart-xsum-12-3",
     )
     parser.add_argument("--save_dir", type=str, help="where to save", default="tmp_gen")

examples/legacy/seq2seq/run_eval.py

@@ -100,7 +100,7 @@ def run_generate(verbose=True):
     """
 
     parser = argparse.ArgumentParser()
-    parser.add_argument("model_name", type=str, help="like facebook/bart-large-cnn,t5-base, etc.")
+    parser.add_argument("model_name", type=str, help="like facebook/bart-large-cnn,google-t5/t5-base, etc.")
     parser.add_argument("input_path", type=str, help="like cnn_dm/test.source")
     parser.add_argument("save_path", type=str, help="where to save summaries")
     parser.add_argument("--reference_path", type=str, required=False, help="like cnn_dm/test.target")