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/albert/configuration_albert.py

@@ -38,7 +38,7 @@ class AlbertConfig(PretrainedConfig):
     This is the configuration class to store the configuration of a [`AlbertModel`] or a [`TFAlbertModel`]. It is used
     to instantiate an ALBERT 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 ALBERT
-    [xxlarge](https://huggingface.co/albert-xxlarge-v2) architecture.
+    [albert-xxlarge-v2](https://huggingface.co/albert-xxlarge-v2) 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/beit/configuration_beit.py

@@ -26,7 +26,7 @@ from ...utils import logging
 logger = logging.get_logger(__name__)
 
 BEIT_PRETRAINED_CONFIG_ARCHIVE_MAP = {
-    "microsoft/beit-base-patch16-224-in22k": "https://huggingface.co/microsoft/beit-base-patch16-224-in22k/resolve/main/config.json",
+    "microsoft/beit-base-patch16-224-pt22k": "https://huggingface.co/microsoft/beit-base-patch16-224-pt22k/resolve/main/config.json",
     # See all BEiT models at https://huggingface.co/models?filter=beit
 }
 
@@ -36,7 +36,7 @@ class BeitConfig(PretrainedConfig):
     This is the configuration class to store the configuration of a [`BeitModel`]. It is used to instantiate an BEiT
     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 BEiT
-    [microsoft/beit-base-patch16-224-in22k](https://huggingface.co/microsoft/beit-base-patch16-224-in22k) architecture.
+    [microsoft/beit-base-patch16-224-pt22k](https://huggingface.co/microsoft/beit-base-patch16-224-pt22k) architecture.
 
     Args:
         vocab_size (`int`, *optional*, defaults to 8092):
@@ -104,10 +104,10 @@ class BeitConfig(PretrainedConfig):
     ```python
     >>> from transformers import BeitModel, BeitConfig
 
-    >>> # Initializing a BEiT beit-base-patch16-224-in22k style configuration
+    >>> # Initializing a BEiT beit-base-patch16-224-pt22k style configuration
     >>> configuration = BeitConfig()
 
-    >>> # Initializing a model from the beit-base-patch16-224-in22k style configuration
+    >>> # Initializing a model from the beit-base-patch16-224-pt22k style configuration
     >>> model = BeitModel(configuration)
 
     >>> # Accessing the model configuration

src/transformers/models/bert_generation/configuration_bert_generation.py

@@ -21,6 +21,9 @@ class BertGenerationConfig(PretrainedConfig):
     r"""
     This is the configuration class to store the configuration of a [`BertGenerationPreTrainedModel`]. It is used to
     instantiate a BertGeneration 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 BertGeneration
+    [google/bert_for_seq_generation_L-24_bbc_encoder](https://huggingface.co/google/bert_for_seq_generation_L-24_bbc_encoder)
+    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/camembert/configuration_camembert.py

@@ -35,7 +35,8 @@ CAMEMBERT_PRETRAINED_CONFIG_ARCHIVE_MAP = {
 class CamembertConfig(RobertaConfig):
     """
     This class overrides [`RobertaConfig`]. Please check the superclass for the appropriate documentation alongside
-    usage examples.
+    usage examples. Instantiating a configuration with the defaults will yield a similar configuration to that of the
+    Camembert [camembert-base](https://huggingface.co/camembert-base) architecture.
     """
 
     model_type = "camembert"

src/transformers/models/deberta_v2/configuration_deberta_v2.py

@@ -33,7 +33,7 @@ class DebertaV2Config(PretrainedConfig):
     This is the configuration class to store the configuration of a [`DebertaV2Model`]. It is used to instantiate a
     DeBERTa-v2 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 DeBERTa
-    [microsoft/deberta-v2-xlarge](https://huggingface.co/microsoft/deberta-base) architecture.
+    [microsoft/deberta-v2-xlarge](https://huggingface.co/microsoft/deberta-v2-xlarge) 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/dpr/configuration_dpr.py

@@ -35,7 +35,11 @@ class DPRConfig(PretrainedConfig):
     [`DPRConfig`] is the configuration class to store the configuration of a *DPRModel*.
 
     This is the configuration class to store the configuration of a [`DPRContextEncoder`], [`DPRQuestionEncoder`], or a
-    [`DPRReader`]. It is used to instantiate the components of the DPR model.
+    [`DPRReader`]. It is used to instantiate the components of the DPR model according to the specified arguments,
+    defining the model component architectures. Instantiating a configuration with the defaults will yield a similar
+    configuration to that of the DPRContextEncoder
+    [facebook/dpr-ctx_encoder-single-nq-base](https://huggingface.co/facebook/dpr-ctx_encoder-single-nq-base)
+    architecture.
 
     This class is a subclass of [`BertConfig`]. Please check the superclass for the documentation of all kwargs.
 

src/transformers/models/flaubert/configuration_flaubert.py

@@ -36,6 +36,8 @@ class FlaubertConfig(XLMConfig):
     """
     This is the configuration class to store the configuration of a [`FlaubertModel`] or a [`TFFlaubertModel`]. It is
     used to instantiate a FlauBERT 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 FlauBERT
+    [flaubert/flaubert_base_uncased](https://huggingface.co/flaubert/flaubert_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/fnet/configuration_fnet.py

@@ -32,7 +32,7 @@ class FNetConfig(PretrainedConfig):
     This is the configuration class to store the configuration of a [`FNetModel`]. It is used to instantiate an FNet
     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 FNet
-    [fnet-base](https://huggingface.co/google/fnet-base) architecture.
+    [google/fnet-base](https://huggingface.co/google/fnet-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/fsmt/configuration_fsmt.py

@@ -41,7 +41,9 @@ class DecoderConfig(PretrainedConfig):
 class FSMTConfig(PretrainedConfig):
     r"""
     This is the configuration class to store the configuration of a [`FSMTModel`]. It is used to instantiate a FSMT
-    model according to the specified arguments, defining the model architecture.
+    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 FSMT
+    [facebook/wmt19-en-ru](https://huggingface.co/facebook/wmt19-en-ru) 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/glpn/configuration_glpn.py

@@ -21,8 +21,8 @@ from ...utils import logging
 logger = logging.get_logger(__name__)
 
 GLPN_PRETRAINED_CONFIG_ARCHIVE_MAP = {
-    "vinvino02/glpn-kitti": "https://huggingface.co/vinvino02/gdpdepth-kitti/resolve/main/config.json",
-    # See all GLPN models at https://huggingface.co/models?filter=gdpdepth
+    "vinvino02/glpn-kitti": "https://huggingface.co/vinvino02/glpn-kitti/resolve/main/config.json",
+    # See all GLPN models at https://huggingface.co/models?filter=glpn
 }
 
 
@@ -31,7 +31,7 @@ class GLPNConfig(PretrainedConfig):
     This is the configuration class to store the configuration of a [`GLPNModel`]. It is used to instantiate an GLPN
     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 GLPN
-    [kaist/gdpdepth-kitti](https://huggingface.co/kaist/gdpdepth-kitti) architecture.
+    [vinvino02/glpn-kitti](https://huggingface.co/vinvino02/glpn-kitti) architecture.
 
     Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
     documentation from [`PretrainedConfig`] for more information.
@@ -81,10 +81,10 @@ class GLPNConfig(PretrainedConfig):
     ```python
     >>> from transformers import GLPNModel, GLPNConfig
 
-    >>> # Initializing a GLPN kaist/gdpdepth-kitti style configuration
+    >>> # Initializing a GLPN vinvino02/glpn-kitti style configuration
     >>> configuration = GLPNConfig()
 
-    >>> # Initializing a model from the kaist/gdpdepth-kitti style configuration
+    >>> # Initializing a model from the vinvino02/glpn-kitti style configuration
     >>> model = GLPNModel(configuration)
 
     >>> # Accessing the model configuration

src/transformers/models/gpt2/configuration_gpt2.py

@@ -40,7 +40,7 @@ class GPT2Config(PretrainedConfig):
     This is the configuration class to store the configuration of a [`GPT2Model`] or a [`TFGPT2Model`]. It is used to
     instantiate a GPT-2 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-2
-    [small](https://huggingface.co/gpt2) architecture.
+    [gpt2](https://huggingface.co/gpt2) 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/gpt_neo/configuration_gpt_neo.py

@@ -36,7 +36,7 @@ class GPTNeoConfig(PretrainedConfig):
     This is the configuration class to store the configuration of a [`GPTNeoModel`]. It is used to instantiate a GPT
     Neo 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 GPTNeo
-    [gpt-neo-1.3B](https://huggingface.co/EleutherAI/gpt-neo-1.3B) architecture.
+    [EleutherAI/gpt-neo-1.3B](https://huggingface.co/EleutherAI/gpt-neo-1.3B) 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/gptj/configuration_gptj.py

@@ -35,7 +35,7 @@ class GPTJConfig(PretrainedConfig):
     This is the configuration class to store the configuration of a [`GPTJModel`]. It is used to instantiate a GPT-J
     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-J
-    [gpt-j-6B](https://huggingface.co/EleutherAI/gpt-j-6B) architecture. Configuration objects inherit from
+    [EleutherAI/gpt-j-6B](https://huggingface.co/EleutherAI/gpt-j-6B) 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/ibert/configuration_ibert.py

@@ -36,7 +36,9 @@ IBERT_PRETRAINED_CONFIG_ARCHIVE_MAP = {
 class IBertConfig(PretrainedConfig):
     """
     This is the configuration class to store the configuration of a [`IBertModel`]. It is used to instantiate a I-BERT
-    model according to the specified arguments,
+    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 IBERT
+    [kssteven/ibert-roberta-base](https://huggingface.co/kssteven/ibert-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/layoutlm/configuration_layoutlm.py

@@ -27,8 +27,8 @@ from ..bert.configuration_bert import BertConfig
 logger = logging.get_logger(__name__)
 
 LAYOUTLM_PRETRAINED_CONFIG_ARCHIVE_MAP = {
-    "layoutlm-base-uncased": "https://huggingface.co/microsoft/layoutlm-base-uncased/resolve/main/config.json",
-    "layoutlm-large-uncased": "https://huggingface.co/microsoft/layoutlm-large-uncased/resolve/main/config.json",
+    "microsoft/layoutlm-base-uncased": "https://huggingface.co/microsoft/layoutlm-base-uncased/resolve/main/config.json",
+    "microsoft/layoutlm-large-uncased": "https://huggingface.co/microsoft/layoutlm-large-uncased/resolve/main/config.json",
 }
 
 
@@ -37,7 +37,7 @@ class LayoutLMConfig(BertConfig):
     This is the configuration class to store the configuration of a [`LayoutLMModel`]. It is used to instantiate a
     LayoutLM 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 LayoutLM
-    [layoutlm-base-uncased](https://huggingface.co/microsoft/layoutlm-base-uncased) architecture.
+    [microsoft/layoutlm-base-uncased](https://huggingface.co/microsoft/layoutlm-base-uncased) architecture.
 
     Configuration objects inherit from [`BertConfig`] and can be used to control the model outputs. Read the
     documentation from [`BertConfig`] for more information.

src/transformers/models/longformer/configuration_longformer.py

@@ -37,8 +37,9 @@ class LongformerConfig(RobertaConfig):
 
     This is the configuration class to store the configuration of a [`LongformerModel`]. It is used to instantiate an
     Longformer 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 with a sequence length 4,096.
+    configuration with the defaults will yield a similar configuration to that of the LongFormer
+    [allenai/longformer-base-4096](https://huggingface.co/allenai/longformer-base-4096) architecture with a sequence
+    length 4,096.
 
     The [`LongformerConfig`] class directly inherits [`RobertaConfig`]. It reuses the same defaults. Please check the
     parent class for more information.

src/transformers/models/luke/configuration_luke.py

@@ -29,7 +29,9 @@ LUKE_PRETRAINED_CONFIG_ARCHIVE_MAP = {
 class LukeConfig(PretrainedConfig):
     r"""
     This is the configuration class to store the configuration of a [`LukeModel`]. It is used to instantiate a LUKE
-    model according to the specified arguments, defining the model architecture.
+    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 LUKE
+    [studio-ousia/luke-base](https://huggingface.co/studio-ousia/luke-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/lxmert/configuration_lxmert.py

@@ -22,14 +22,16 @@ from ...utils import logging
 logger = logging.get_logger(__name__)
 
 LXMERT_PRETRAINED_CONFIG_ARCHIVE_MAP = {
-    "unc-nlp/lxmert-base-uncased": "",
+    "unc-nlp/lxmert-base-uncased": "https://huggingface.co/unc-nlp/lxmert-base-uncased/resolve/main/config.json",
 }
 
 
 class LxmertConfig(PretrainedConfig):
     r"""
     This is the configuration class to store the configuration of a [`LxmertModel`] or a [`TFLxmertModel`]. It is used
-    to instantiate a LXMERT model according to the specified arguments, defining the model architecture.
+    to instantiate a LXMERT 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 Lxmert
+    [unc-nlp/lxmert-base-uncased](https://huggingface.co/unc-nlp/lxmert-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/m2m_100/configuration_m2m_100.py

@@ -36,7 +36,7 @@ class M2M100Config(PretrainedConfig):
     This is the configuration class to store the configuration of a [`M2M100Model`]. It is used to instantiate an
     M2M100 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 M2M100
-    [m2m100_418M](https://huggingface.co/facebook/m2m100_418M) architecture.
+    [facebook/m2m100_418M](https://huggingface.co/facebook/m2m100_418M) 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/maskformer/configuration_maskformer.py

@@ -35,9 +35,9 @@ class MaskFormerConfig(PretrainedConfig):
     r"""
     This is the configuration class to store the configuration of a [`MaskFormerModel`]. It is used to instantiate a
     MaskFormer 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/maskformer-swin-base-ade" architecture trained on
-    [ADE20k-150](https://huggingface.co/datasets/scene_parse_150).
+    configuration with the defaults will yield a similar configuration to that of the MaskFormer
+    [facebook/maskformer-swin-base-ade](https://huggingface.co/facebook/maskformer-swin-base-ade) architecture trained
+    on [ADE20k-150](https://huggingface.co/datasets/scene_parse_150).
 
     Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
     documentation from [`PretrainedConfig`] for more information.