Update all references to canonical models (#29001)

* Script & Manual edition

* Update

examples/research_projects/pplm/run_pplm.py

@@ -61,7 +61,7 @@ DISCRIMINATOR_MODELS_PARAMS = {
         "embed_size": 1024,
         "class_vocab": {"non_clickbait": 0, "clickbait": 1},
         "default_class": 1,
-        "pretrained_model": "gpt2-medium",
+        "pretrained_model": "openai-community/gpt2-medium",
     },
     "sentiment": {
         "url": "https://s3.amazonaws.com/models.huggingface.co/bert/pplm/discriminators/SST_classifier_head.pt",
@@ -69,7 +69,7 @@ DISCRIMINATOR_MODELS_PARAMS = {
         "embed_size": 1024,
         "class_vocab": {"very_positive": 2, "very_negative": 3},
         "default_class": 3,
-        "pretrained_model": "gpt2-medium",
+        "pretrained_model": "openai-community/gpt2-medium",
     },
 }
 
@@ -585,7 +585,7 @@ def set_generic_model_params(discrim_weights, discrim_meta):
 
 
 def run_pplm_example(
-    pretrained_model="gpt2-medium",
+    pretrained_model="openai-community/gpt2-medium",
     cond_text="",
     uncond=False,
     num_samples=1,
@@ -738,7 +738,7 @@ if __name__ == "__main__":
         "--pretrained_model",
         "-M",
         type=str,
-        default="gpt2-medium",
+        default="openai-community/gpt2-medium",
         help="pretrained model name or path to local checkpoint",
     )
     parser.add_argument("--cond_text", type=str, default="The lake", help="Prefix texts to condition on")

examples/research_projects/pplm/run_pplm_discrim_train.py

@@ -45,7 +45,7 @@ max_length_seq = 100
 class Discriminator(nn.Module):
     """Transformer encoder followed by a Classification Head"""
 
-    def __init__(self, class_size, pretrained_model="gpt2-medium", cached_mode=False, device="cpu"):
+    def __init__(self, class_size, pretrained_model="openai-community/gpt2-medium", cached_mode=False, device="cpu"):
         super().__init__()
         self.tokenizer = GPT2Tokenizer.from_pretrained(pretrained_model)
         self.encoder = GPT2LMHeadModel.from_pretrained(pretrained_model)
@@ -218,7 +218,7 @@ def get_cached_data_loader(dataset, batch_size, discriminator, shuffle=False, de
 def train_discriminator(
     dataset,
     dataset_fp=None,
-    pretrained_model="gpt2-medium",
+    pretrained_model="openai-community/gpt2-medium",
     epochs=10,
     batch_size=64,
     log_interval=10,
@@ -502,7 +502,10 @@ if __name__ == "__main__":
         help="File path of the dataset to use. Needed only in case of generic datadset",
     )
     parser.add_argument(
-        "--pretrained_model", type=str, default="gpt2-medium", help="Pretrained model to use as encoder"
+        "--pretrained_model",
+        type=str,
+        default="openai-community/gpt2-medium",
+        help="Pretrained model to use as encoder",
     )
     parser.add_argument("--epochs", type=int, default=10, metavar="N", help="Number of training epochs")
     parser.add_argument(