Add missing ckpt in config docs (#16900)

* add missing ckpt in config docs

* add more missing ckpt in config docs

* fix wrong ckpts

* fix realm ckpt

* fix s2t2

* fix xlm_roberta ckpt

* Fix for deberta v2

* Apply suggestions from code review
Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>

* use only one checkpoint for DPR

* Apply suggestions from code review
Co-authored-by: NielsRogge <48327001+NielsRogge@users.noreply.github.com>
Co-authored-by: ydshieh <ydshieh@users.noreply.github.com>
Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>
Co-authored-by: NielsRogge <48327001+NielsRogge@users.noreply.github.com>

src/transformers/models/megatron_bert/configuration_megatron_bert.py

@@ -30,7 +30,7 @@ class MegatronBertConfig(PretrainedConfig):
     This is the configuration class to store the configuration of a [`MegatronBertModel`]. It is used to instantiate a
     MEGATRON_BERT model according to the specified arguments, defining the model architecture. Instantiating a
     configuration with the defaults will yield a similar configuration to that of the MEGATRON_BERT
-    [megatron-bert-uncased-345m](https://huggingface.co/nvidia/megatron-bert-uncased-345m) architecture.
+    [nvidia/megatron-bert-uncased-345m](https://huggingface.co/nvidia/megatron-bert-uncased-345m) architecture.
 
     Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
     documentation from [`PretrainedConfig`] for more information.

src/transformers/models/mobilebert/configuration_mobilebert.py

@@ -21,7 +21,7 @@ from ...utils import logging
 logger = logging.get_logger(__name__)
 
 MOBILEBERT_PRETRAINED_CONFIG_ARCHIVE_MAP = {
-    "mobilebert-uncased": "https://huggingface.co/google/mobilebert-uncased/resolve/main/config.json"
+    "google/mobilebert-uncased": "https://huggingface.co/google/mobilebert-uncased/resolve/main/config.json"
 }
 
 
@@ -29,6 +29,8 @@ class MobileBertConfig(PretrainedConfig):
     r"""
     This is the configuration class to store the configuration of a [`MobileBertModel`] or a [`TFMobileBertModel`]. It
     is used to instantiate a MobileBERT model according to the specified arguments, defining the model architecture.
+    Instantiating a configuration with the defaults will yield a similar configuration to that of the MobileBERT
+    [google/mobilebert-uncased](https://huggingface.co/google/mobilebert-uncased) architecture.
 
     Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
     documentation from [`PretrainedConfig`] for more information.

src/transformers/models/mpnet/configuration_mpnet.py

@@ -31,7 +31,7 @@ class MPNetConfig(PretrainedConfig):
     This is the configuration class to store the configuration of a [`MPNetModel`] or a [`TFMPNetModel`]. It is used to
     instantiate a MPNet model according to the specified arguments, defining the model architecture. Instantiating a
     configuration with the defaults will yield a similar configuration to that of the MPNet
-    [mpnet-base](https://huggingface.co/mpnet-base) architecture.
+    [microsoft/mpnet-base](https://huggingface.co/microsoft/mpnet-base) architecture.
 
     Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
     documentation from [`PretrainedConfig`] for more information.

src/transformers/models/openai/configuration_openai.py

@@ -28,8 +28,8 @@ class OpenAIGPTConfig(PretrainedConfig):
     """
     This is the configuration class to store the configuration of a [`OpenAIGPTModel`] or a [`TFOpenAIGPTModel`]. It is
     used to instantiate a GPT model according to the specified arguments, defining the model architecture.
-    Instantiating a configuration with the defaults will yield a similar configuration to that of the
-    [GPT](https://huggingface.co/openai-gpt) architecture from OpenAI.
+    Instantiating a configuration with the defaults will yield a similar configuration to that of the GPT
+    [openai-gpt](https://huggingface.co/openai-gpt) architecture from OpenAI.
 
     Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
     documentation from [`PretrainedConfig`] for more information.

src/transformers/models/prophetnet/configuration_prophetnet.py

@@ -29,7 +29,9 @@ PROPHETNET_PRETRAINED_CONFIG_ARCHIVE_MAP = {
 class ProphetNetConfig(PretrainedConfig):
     r"""
     This is the configuration class to store the configuration of a [`ProphetNetModel`]. It is used to instantiate a
-    ProphetNet model according to the specified arguments, defining the model architecture.
+    ProphetNet model according to the specified arguments, defining the model architecture. Instantiating a
+    configuration with the defaults will yield a similar configuration to that of the ProphetNet
+    [microsoft/prophetnet-large-uncased](https://huggingface.co/microsoft/prophetnet-large-uncased) architecture.
 
     Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
     documentation from [`PretrainedConfig`] for more information.

src/transformers/models/realm/configuration_realm.py

@@ -46,7 +46,8 @@ class RealmConfig(PretrainedConfig):
 
     It is used to instantiate an REALM model according to the specified arguments, defining the model architecture.
     Instantiating a configuration with the defaults will yield a similar configuration to that of the REALM
-    [realm-cc-news-pretrained](https://huggingface.co/google/realm-cc-news-pretrained-embedder) architecture.
+    [google/realm-cc-news-pretrained-embedder](https://huggingface.co/google/realm-cc-news-pretrained-embedder)
+    architecture.
 
     Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
     documentation from [`PretrainedConfig`] for more information.

src/transformers/models/reformer/configuration_reformer.py

@@ -30,7 +30,9 @@ REFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP = {
 class ReformerConfig(PretrainedConfig):
     r"""
     This is the configuration class to store the configuration of a [`ReformerModel`]. It is used to instantiate a
-    Reformer model according to the specified arguments, defining the model architecture.
+    Reformer model according to the specified arguments, defining the model architecture. Instantiating a configuration
+    with the defaults will yield a similar configuration to that of the ReFormer
+    [google/reformer-crime-and-punishment](https://huggingface.co/google/reformer-crime-and-punishment) architecture.
 
     Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
     documentation from [`PretrainedConfig`] for more information.

src/transformers/models/regnet/configuration_regnet.py

@@ -21,7 +21,7 @@ from ...utils import logging
 logger = logging.get_logger(__name__)
 
 REGNET_PRETRAINED_CONFIG_ARCHIVE_MAP = {
-    "regnety-40": "https://huggingface.co/zuppif/regnety-040/blob/main/config.json",
+    "facebook/regnet-y-040": "https://huggingface.co/facebook/regnet-y-040/blob/main/config.json",
 }
 
 
@@ -29,8 +29,8 @@ class RegNetConfig(PretrainedConfig):
     r"""
     This is the configuration class to store the configuration of a [`RegNetModel`]. It is used to instantiate a RegNet
     model according to the specified arguments, defining the model architecture. Instantiating a configuration with the
-    defaults will yield a similar configuration to that of the
-    [facebook/regnet-y-40](https://huggingface.co/facebook/regnet-y-40) architecture.
+    defaults will yield a similar configuration to that of the RegNet
+    [facebook/regnet-y-040](https://huggingface.co/facebook/regnet-y-040) architecture.
 
     Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
     documentation from [`PretrainedConfig`] for more information.

src/transformers/models/rembert/configuration_rembert.py

@@ -30,7 +30,8 @@ class RemBertConfig(PretrainedConfig):
     r"""
     This is the configuration class to store the configuration of a [`RemBertModel`]. It is used to instantiate an
     RemBERT model according to the specified arguments, defining the model architecture. Instantiating a configuration
-    with the defaults will yield a similar configuration to that of the remert-large architecture.
+    with the defaults will yield a similar configuration to that of the RemBERT
+    [google/rembert](https://huggingface.co/google/rembert) architecture.
 
     Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
     documentation from [`PretrainedConfig`] for more information.

src/transformers/models/resnet/configuration_resnet.py

@@ -21,7 +21,7 @@ from ...utils import logging
 logger = logging.get_logger(__name__)
 
 RESNET_PRETRAINED_CONFIG_ARCHIVE_MAP = {
-    "resnet-50": "https://huggingface.co/microsoft/resnet-50/blob/main/config.json",
+    "microsoft/resnet-50": "https://huggingface.co/microsoft/resnet-50/blob/main/config.json",
 }
 
 
@@ -29,8 +29,8 @@ class ResNetConfig(PretrainedConfig):
     r"""
     This is the configuration class to store the configuration of a [`ResNetModel`]. It is used to instantiate an
     ResNet model according to the specified arguments, defining the model architecture. Instantiating a configuration
-    with the defaults will yield a similar configuration to that of the
-    [resnet-50](https://huggingface.co/microsoft/resnet-50) architecture.
+    with the defaults will yield a similar configuration to that of the ResNet
+    [microsoft/resnet-50](https://huggingface.co/microsoft/resnet-50) architecture.
 
     Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
     documentation from [`PretrainedConfig`] for more information.

src/transformers/models/retribert/configuration_retribert.py

@@ -22,14 +22,16 @@ logger = logging.get_logger(__name__)
 
 # TODO: upload to AWS
 RETRIBERT_PRETRAINED_CONFIG_ARCHIVE_MAP = {
-    "retribert-base-uncased": "https://huggingface.co/distilbert-base-uncased/resolve/main/config.json",
+    "yjernite/retribert-base-uncased": "https://huggingface.co/yjernite/retribert-base-uncased/resolve/main/config.json",
 }
 
 
 class RetriBertConfig(PretrainedConfig):
     r"""
     This is the configuration class to store the configuration of a [`RetriBertModel`]. It is used to instantiate a
-    RetriBertModel model according to the specified arguments, defining the model architecture.
+    RetriBertModel model according to the specified arguments, defining the model architecture. Instantiating a
+    configuration with the defaults will yield a similar configuration to that of the RetriBERT
+    [yjernite/retribert-base-uncased](https://huggingface.co/yjernite/retribert-base-uncased) architecture.
 
     Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
     documentation from [`PretrainedConfig`] for more information.

src/transformers/models/roberta/configuration_roberta.py

@@ -38,7 +38,8 @@ class RobertaConfig(BertConfig):
     r"""
     This is the configuration class to store the configuration of a [`RobertaModel`] or a [`TFRobertaModel`]. It is
     used to instantiate a RoBERTa model according to the specified arguments, defining the model architecture.
-
+    Instantiating a configuration with the defaults will yield a similar configuration to that of the RoBERTa
+    [roberta-base](https://huggingface.co/roberta-base) architecture.
 
     Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
     documentation from [`PretrainedConfig`] for more information.

src/transformers/models/speech_to_text_2/configuration_speech_to_text_2.py

@@ -21,7 +21,7 @@ from ...utils import logging
 logger = logging.get_logger(__name__)
 
 SPEECH_TO_TEXT_2_PRETRAINED_CONFIG_ARCHIVE_MAP = {
-    "facebook/s2t-small-librispeech-asr": "https://huggingface.co/facebook/s2t-wav2vec2-large-en-de/resolve/main/config.json",
+    "facebook/s2t-wav2vec2-large-en-de": "https://huggingface.co/facebook/s2t-wav2vec2-large-en-de/resolve/main/config.json",
     # See all Speech2Text models at https://huggingface.co/models?filter=speech2text2
 }
 
@@ -31,7 +31,7 @@ class Speech2Text2Config(PretrainedConfig):
     This is the configuration class to store the configuration of a [`Speech2Text2ForCausalLM`]. It is used to
     instantiate an Speech2Text2 model according to the specified arguments, defining the model architecture.
     Instantiating a configuration with the defaults will yield a similar configuration to that of the Speech2Text2
-    [facebook/s2t-small-librispeech-asr](https://huggingface.co/facebook/s2t-small-librispeech-asr) architecture.
+    [facebook/s2t-wav2vec2-large-en-de](https://huggingface.co/facebook/s2t-wav2vec2-large-en-de) architecture.
 
     Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
     documentation from [`PretrainedConfig`] for more information.

src/transformers/models/squeezebert/configuration_squeezebert.py

@@ -30,7 +30,9 @@ SQUEEZEBERT_PRETRAINED_CONFIG_ARCHIVE_MAP = {
 class SqueezeBertConfig(PretrainedConfig):
     r"""
     This is the configuration class to store the configuration of a [`SqueezeBertModel`]. It is used to instantiate a
-    SqueezeBERT model according to the specified arguments, defining the model architecture.
+    SqueezeBERT model according to the specified arguments, defining the model architecture. Instantiating a
+    configuration with the defaults will yield a similar configuration to that of the SqueezeBERT
+    [squeezebert/squeezebert-uncased](https://huggingface.co/squeezebert/squeezebert-uncased) architecture.
 
     Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
     documentation from [`PretrainedConfig`] for more information.

src/transformers/models/tapas/configuration_tapas.py

@@ -38,7 +38,9 @@ class TapasConfig(PretrainedConfig):
     r"""
     This is the configuration class to store the configuration of a [`TapasModel`]. It is used to instantiate a TAPAS
     model according to the specified arguments, defining the model architecture. Instantiating a configuration with the
-    defaults will yield a similar configuration to that of the TAPAS *tapas-base-finetuned-sqa* architecture.
+    defaults will yield a similar configuration to that of the TAPAS
+    [google/tapas-base-finetuned-sqa](https://huggingface.co/google/tapas-base-finetuned-sqa) architecture.
+
     Configuration objects inherit from [`PreTrainedConfig`] and can be used to control the model outputs. Read the
     documentation from [`PretrainedConfig`] for more information.
 

src/transformers/models/transfo_xl/configuration_transfo_xl.py

@@ -30,8 +30,8 @@ class TransfoXLConfig(PretrainedConfig):
     """
     This is the configuration class to store the configuration of a [`TransfoXLModel`] or a [`TFTransfoXLModel`]. It is
     used to instantiate a Transformer-XL model according to the specified arguments, defining the model architecture.
-    Instantiating a configuration with the defaults will yield a similar configuration to that of the [Transformer
-    XL](https://huggingface.co/transfo-xl-wt103) architecture.
+    Instantiating a configuration with the defaults will yield a similar configuration to that of the TransfoXL
+    [transfo-xl-wt103](https://huggingface.co/transfo-xl-wt103) architecture.
 
     Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
     documentation from [`PretrainedConfig`] for more information.

src/transformers/models/trocr/configuration_trocr.py

@@ -21,7 +21,7 @@ from ...utils import logging
 logger = logging.get_logger(__name__)
 
 TROCR_PRETRAINED_CONFIG_ARCHIVE_MAP = {
-    "microsoft/trocr-base": "https://huggingface.co/microsoft/trocr-base/resolve/main/config.json",
+    "microsoft/trocr-base-handwritten": "https://huggingface.co/microsoft/trocr-base-handwritten/resolve/main/config.json",
     # See all TrOCR models at https://huggingface.co/models?filter=trocr
 }
 
@@ -31,7 +31,7 @@ class TrOCRConfig(PretrainedConfig):
     This is the configuration class to store the configuration of a [`TrOCRForCausalLM`]. It is used to instantiate an
     TrOCR model according to the specified arguments, defining the model architecture. Instantiating a configuration
     with the defaults will yield a similar configuration to that of the TrOCR
-    [microsoft/trocr-base](https://huggingface.co/microsoft/trocr-base) architecture.
+    [microsoft/trocr-base-handwritten](https://huggingface.co/microsoft/trocr-base-handwritten) architecture.
 
     Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
     documentation from [`PretrainedConfig`] for more information.

src/transformers/models/unispeech/configuration_unispeech.py

@@ -24,7 +24,7 @@ from ...utils import logging
 logger = logging.get_logger(__name__)
 
 UNISPEECH_PRETRAINED_CONFIG_ARCHIVE_MAP = {
-    "facebook/unispeech-base-960h": "https://huggingface.co/facebook/unispeech-base-960h/resolve/main/config.json",
+    "microsoft/unispeech-large-1500h-cv": "https://huggingface.co/microsoft/unispeech-large-1500h-cv/resolve/main/config.json",
     # See all UniSpeech models at https://huggingface.co/models?filter=unispeech
 }
 
@@ -34,7 +34,7 @@ class UniSpeechConfig(PretrainedConfig):
     This is the configuration class to store the configuration of a [`UniSpeechModel`]. It is used to instantiate an
     UniSpeech model according to the specified arguments, defining the model architecture. Instantiating a
     configuration with the defaults will yield a similar configuration to that of the UniSpeech
-    [facebook/unispeech-base-960h](https://huggingface.co/facebook/unispeech-base-960h) architecture.
+    [microsoft/unispeech-large-1500h-cv](https://huggingface.co/microsoft/unispeech-large-1500h-cv) architecture.
 
     Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
     documentation from [`PretrainedConfig`] for more information.

src/transformers/models/unispeech_sat/configuration_unispeech_sat.py

@@ -24,7 +24,7 @@ from ...utils import logging
 logger = logging.get_logger(__name__)
 
 UNISPEECH_SAT_PRETRAINED_CONFIG_ARCHIVE_MAP = {
-    "facebook/unispeech_sat-base-960h": "https://huggingface.co/facebook/unispeech_sat-base-960h/resolve/main/config.json",
+    "microsoft/unispeech-sat-base-100h-libri-ft": "https://huggingface.co/microsoft/unispeech-sat-base-100h-libri-ft/resolve/main/config.json",
     # See all UniSpeechSat models at https://huggingface.co/models?filter=unispeech_sat
 }
 
@@ -34,7 +34,8 @@ class UniSpeechSatConfig(PretrainedConfig):
     This is the configuration class to store the configuration of a [`UniSpeechSatModel`]. It is used to instantiate an
     UniSpeechSat model according to the specified arguments, defining the model architecture. Instantiating a
     configuration with the defaults will yield a similar configuration to that of the UniSpeechSat
-    [facebook/unispeech_sat-base-960h](https://huggingface.co/facebook/unispeech_sat-base-960h) architecture.
+    [microsoft/unispeech-sat-base-100h-libri-ft](https://huggingface.co/microsoft/unispeech-sat-base-100h-libri-ft)
+    architecture.
 
     Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
     documentation from [`PretrainedConfig`] for more information.
@@ -173,10 +174,10 @@ class UniSpeechSatConfig(PretrainedConfig):
     ```python
     >>> from transformers import UniSpeechSatModel, UniSpeechSatConfig
 
-    >>> # Initializing a UniSpeechSat facebook/unispeech_sat-base-960h style configuration
+    >>> # Initializing a UniSpeechSat microsoft/unispeech-sat-base-100h-libri-ft style configuration
     >>> configuration = UniSpeechSatConfig()
 
-    >>> # Initializing a model from the facebook/unispeech_sat-base-960h style configuration
+    >>> # Initializing a model from the microsoft/unispeech-sat-base-100h-libri-ft style configuration
     >>> model = UniSpeechSatModel(configuration)
 
     >>> # Accessing the model configuration

src/transformers/models/unispeech_sat/modeling_unispeech_sat.py

@@ -1103,10 +1103,11 @@ UNISPEECH_SAT_INPUTS_DOCSTRING = r"""
 
             `attention_mask` should only be passed if the corresponding processor has `config.return_attention_mask ==
             True`. For all models whose processor has `config.return_attention_mask == False`, such as
-            [unispeech_sat-base](https://huggingface.co/facebook/unispeech_sat-base-960h), `attention_mask` should
-            **not** be passed to avoid degraded performance when doing batched inference. For such models
-            `input_values` should simply be padded with 0 and passed without `attention_mask`. Be aware that these
-            models also yield slightly different results depending on whether `input_values` is padded or not.
+            [microsoft/unispeech-sat-base-100h-libri-ft](https://huggingface.co/microsoft/unispeech-sat-base-100h-libri-ft),
+            `attention_mask` should **not** be passed to avoid degraded performance when doing batched inference. For
+            such models `input_values` should simply be padded with 0 and passed without `attention_mask`. Be aware
+            that these models also yield slightly different results depending on whether `input_values` is padded or
+            not.
 
             </Tip>