Fix wrong (non-existing) checkpoints

src/transformers/models/apertus/configuration_apertus.py

@@ -23,7 +23,7 @@
 from ...utils import auto_docstring
 
 
-@auto_docstring(checkpoint="swiss-ai/Apertus-8B")
+@auto_docstring(checkpoint="swiss-ai/Apertus-8B-Instruct-2509")
 class ApertusConfig(PreTrainedConfig):
     r"""
     ```python

src/transformers/models/apertus/modeling_apertus.py

@@ -459,8 +459,8 @@ def forward(
         ```python
         >>> from transformers import AutoTokenizer, ApertusForCausalLM
 
-        >>> model = ApertusForCausalLM.from_pretrained("swiss-ai/Apertus-8B")
-        >>> tokenizer = AutoTokenizer.from_pretrained("swiss-ai/Apertus-8B")
+        >>> model = ApertusForCausalLM.from_pretrained("swiss-ai/Apertus-8B-Instruct-2509")
+        >>> tokenizer = AutoTokenizer.from_pretrained("swiss-ai/Apertus-8B-Instruct-2509")
 
         >>> prompt = "Hey, are you conscious? Can you talk to me?"
         >>> inputs = tokenizer(prompt, return_tensors="pt")

src/transformers/models/apertus/modular_apertus.py

@@ -42,7 +42,7 @@
 logger = logging.get_logger(__name__)
 
 
-@auto_docstring(checkpoint="swiss-ai/Apertus-8B")
+@auto_docstring(checkpoint="swiss-ai/Apertus-8B-Instruct-2509")
 class ApertusConfig(PreTrainedConfig):
     r"""
     ```python
@@ -260,8 +260,8 @@ def forward(self, **super_kwargs):
         ```python
         >>> from transformers import AutoTokenizer, ApertusForCausalLM
 
-        >>> model = ApertusForCausalLM.from_pretrained("swiss-ai/Apertus-8B")
-        >>> tokenizer = AutoTokenizer.from_pretrained("swiss-ai/Apertus-8B")
+        >>> model = ApertusForCausalLM.from_pretrained("swiss-ai/Apertus-8B-Instruct-2509")
+        >>> tokenizer = AutoTokenizer.from_pretrained("swiss-ai/Apertus-8B-Instruct-2509")
 
         >>> prompt = "Hey, are you conscious? Can you talk to me?"
         >>> inputs = tokenizer(prompt, return_tensors="pt")

src/transformers/models/chameleon/configuration_chameleon.py

@@ -21,7 +21,7 @@
 logger = logging.get_logger(__name__)
 
 
-@auto_docstring(checkpoint="meta/chameleon-7B")
+@auto_docstring(checkpoint="facebook/chameleon-7b")
 class ChameleonVQVAEConfig(PreTrainedConfig):
     r"""
     base_channels (`int`, *optional*, defaults to 128):
@@ -76,7 +76,7 @@ def __init__(
         self.initializer_range = initializer_range
 
 
-@auto_docstring(checkpoint="meta/chameleon-7B")
+@auto_docstring(checkpoint="facebook/chameleon-7b")
 class ChameleonConfig(PreTrainedConfig):
     r"""
     model_parallel_size (`int`, *optional*, defaults to 1):

src/transformers/models/dab_detr/configuration_dab_detr.py

@@ -22,7 +22,7 @@
 logger = logging.get_logger(__name__)
 
 
-@auto_docstring(checkpoint="IDEA-Research/dab_detr-base")
+@auto_docstring(checkpoint="IDEA-Research/dab-detr-resnet-50")
 class DabDetrConfig(PreTrainedConfig):
     r"""
     num_queries (`int`, *optional*, defaults to 300):
@@ -56,10 +56,10 @@ class DabDetrConfig(PreTrainedConfig):
     ```python
     >>> from transformers import DabDetrConfig, DabDetrModel
 
-    >>> # Initializing a DAB-DETR IDEA-Research/dab_detr-base style configuration
+    >>> # Initializing a DAB-DETR IDEA-Research/dab-detr-resnet-50 style configuration
     >>> configuration = DabDetrConfig()
 
-    >>> # Initializing a model (with random weights) from the IDEA-Research/dab_detr-base style configuration
+    >>> # Initializing a model (with random weights) from the IDEA-Research/dab-detr-resnet-50 style configuration
     >>> model = DabDetrModel(configuration)
 
     >>> # Accessing the model configuration

src/transformers/models/dab_detr/modeling_dab_detr.py

@@ -1248,8 +1248,8 @@ def forward(
         >>> with httpx.stream("GET", url) as response:
         ...     image = Image.open(BytesIO(response.read()))
 
-        >>> image_processor = AutoImageProcessor.from_pretrained("IDEA-Research/dab_detr-base")
-        >>> model = AutoModel.from_pretrained("IDEA-Research/dab_detr-base")
+        >>> image_processor = AutoImageProcessor.from_pretrained("IDEA-Research/dab-detr-resnet-50")
+        >>> model = AutoModel.from_pretrained("IDEA-Research/dab-detr-resnet-50")
 
         >>> # prepare image for the model
         >>> inputs = image_processor(images=image, return_tensors="pt")

src/transformers/models/edgetam/configuration_edgetam.py

@@ -22,7 +22,7 @@
 from ..auto import CONFIG_MAPPING, AutoConfig
 
 
-@auto_docstring(checkpoint="facebook/EdgeTAM")
+@auto_docstring(checkpoint="yonigozlan/EdgeTAM-hf")
 class EdgeTamVisionConfig(PreTrainedConfig):
     r"""
     backbone_channel_list (`List[int]`, *optional*, defaults to `[384, 192, 96, 48]`):
@@ -98,7 +98,7 @@ def __init__(
         super().__init__(**kwargs)
 
 
-@auto_docstring(checkpoint="facebook/EdgeTAM")
+@auto_docstring(checkpoint="yonigozlan/EdgeTAM-hf")
 class EdgeTamPromptEncoderConfig(PreTrainedConfig):
     r"""
     mask_input_channels (`int`, *optional*, defaults to 16):
@@ -134,7 +134,7 @@ def __init__(
         self.scale = scale
 
 
-@auto_docstring(checkpoint="facebook/EdgeTAM")
+@auto_docstring(checkpoint="yonigozlan/EdgeTAM-hf")
 class EdgeTamMaskDecoderConfig(PreTrainedConfig):
     r"""
     mlp_dim (`int`, *optional*, defaults to 2048):
@@ -192,7 +192,7 @@ def __init__(
         self.attention_downsample_rate = attention_downsample_rate
 
 
-@auto_docstring(checkpoint="facebook/EdgeTAM")
+@auto_docstring(checkpoint="yonigozlan/EdgeTAM-hf")
 class EdgeTamConfig(PreTrainedConfig):
     r"""
     prompt_encoder_config (Union[`dict`, `EdgeTamPromptEncoderConfig`], *optional*):

src/transformers/models/edgetam/modular_edgetam.py

@@ -36,7 +36,7 @@
 )
 
 
-@auto_docstring(checkpoint="facebook/EdgeTAM")
+@auto_docstring(checkpoint="yonigozlan/EdgeTAM-hf")
 class EdgeTamVisionConfig(PreTrainedConfig):
     r"""
     backbone_channel_list (`List[int]`, *optional*, defaults to `[384, 192, 96, 48]`):
@@ -112,17 +112,17 @@ def __init__(
         super().__init__(**kwargs)
 
 
-@auto_docstring(checkpoint="facebook/EdgeTAM")
+@auto_docstring(checkpoint="yonigozlan/EdgeTAM-hf")
 class EdgeTamPromptEncoderConfig(Sam2PromptEncoderConfig):
     pass
 
 
-@auto_docstring(checkpoint="facebook/EdgeTAM")
+@auto_docstring(checkpoint="yonigozlan/EdgeTAM-hf")
 class EdgeTamMaskDecoderConfig(Sam2MaskDecoderConfig):
     pass
 
 
-@auto_docstring(checkpoint="facebook/EdgeTAM")
+@auto_docstring(checkpoint="yonigozlan/EdgeTAM-hf")
 class EdgeTamConfig(Sam2Config):
     r"""
     prompt_encoder_config (Union[`dict`, `EdgeTamPromptEncoderConfig`], *optional*):

src/transformers/models/edgetam_video/configuration_edgetam_video.py

@@ -23,7 +23,7 @@
 from ..auto import CONFIG_MAPPING, AutoConfig
 
 
-@auto_docstring(checkpoint="facebook/EdgeTAM")
+@auto_docstring(checkpoint="yonigozlan/EdgeTAM-hf")
 class EdgeTamVideoPromptEncoderConfig(PreTrainedConfig):
     r"""
     mask_input_channels (`int`, *optional*, defaults to 16):
@@ -59,7 +59,7 @@ def __init__(
         self.scale = scale
 
 
-@auto_docstring(checkpoint="facebook/EdgeTAM")
+@auto_docstring(checkpoint="yonigozlan/EdgeTAM-hf")
 class EdgeTamVideoMaskDecoderConfig(PreTrainedConfig):
     r"""
     mlp_dim (`int`, *optional*, defaults to 2048):
@@ -117,7 +117,7 @@ def __init__(
         self.attention_downsample_rate = attention_downsample_rate
 
 
-@auto_docstring(checkpoint="facebook/EdgeTAM")
+@auto_docstring(checkpoint="yonigozlan/EdgeTAM-hf")
 class EdgeTamVideoConfig(PreTrainedConfig):
     r"""
     prompt_encoder_config (Union[`dict`, `EdgeTamVideoPromptEncoderConfig`], *optional*):

src/transformers/models/edgetam_video/modular_edgetam_video.py

@@ -57,17 +57,17 @@
 )
 
 
-@auto_docstring(checkpoint="facebook/EdgeTAM")
+@auto_docstring(checkpoint="yonigozlan/EdgeTAM-hf")
 class EdgeTamVideoPromptEncoderConfig(Sam2VideoPromptEncoderConfig):
     pass
 
 
-@auto_docstring(checkpoint="facebook/EdgeTAM")
+@auto_docstring(checkpoint="yonigozlan/EdgeTAM-hf")
 class EdgeTamVideoMaskDecoderConfig(Sam2VideoMaskDecoderConfig):
     pass
 
 
-@auto_docstring(checkpoint="facebook/EdgeTAM")
+@auto_docstring(checkpoint="yonigozlan/EdgeTAM-hf")
 class EdgeTamVideoConfig(Sam2VideoConfig):
     r"""
     prompt_encoder_config (Union[`dict`, `EdgeTamVideoPromptEncoderConfig`], *optional*):

src/transformers/models/falcon_h1/configuration_falcon_h1.py

@@ -21,7 +21,7 @@
 logger = logging.get_logger(__name__)
 
 
-@auto_docstring(checkpoint="ibm-fms/FalconH1-9.8b-2.2T-hf")
+@auto_docstring(checkpoint="tiiuae/Falcon-H1-1.5B-Deep-Instruct")
 class FalconH1Config(PreTrainedConfig):
     r"""
     num_logits_to_keep (`int` or `None`, *optional*, defaults to 1):

src/transformers/models/gemma3/configuration_gemma3.py

@@ -29,7 +29,7 @@
 logger = logging.get_logger(__name__)
 
 
-@auto_docstring(checkpoint="google/gemma3_text-7b")
+@auto_docstring(checkpoint="google/gemma-3-4b-it")
 class Gemma3TextConfig(PreTrainedConfig):
     r"""
     final_logit_softcapping (`float`, *optional*):
@@ -174,7 +174,7 @@ def convert_rope_params_to_dict(self, ignore_keys_at_rope_validation=None, **kwa
         return kwargs
 
 
-@auto_docstring(checkpoint="google/gemma3_text-7b")
+@auto_docstring(checkpoint="google/gemma-3-4b-it")
 class Gemma3Config(PreTrainedConfig):
     r"""
     mm_tokens_per_image (`int`, *optional*, defaults to 256):

src/transformers/models/gemma3/modular_gemma3.py

@@ -59,7 +59,7 @@
 logger = logging.get_logger(__name__)
 
 
-@auto_docstring(checkpoint="google/gemma3_text-7b")
+@auto_docstring(checkpoint="google/gemma-3-4b-it")
 class Gemma3TextConfig(Gemma2Config, PreTrainedConfig):
     r"""
     final_logit_softcapping (`float`, *optional*):
@@ -198,7 +198,7 @@ def convert_rope_params_to_dict(self, ignore_keys_at_rope_validation=None, **kwa
         return kwargs
 
 
-@auto_docstring(checkpoint="google/gemma3_text-7b")
+@auto_docstring(checkpoint="google/gemma-3-4b-it")
 class Gemma3Config(PreTrainedConfig):
     r"""
     mm_tokens_per_image (`int`, *optional*, defaults to 256):

src/transformers/models/glm4_moe/configuration_glm4_moe.py

@@ -23,7 +23,7 @@
 from ...utils import auto_docstring
 
 
-@auto_docstring(checkpoint="THUDM/GLM-4-100B-A10B")
+@auto_docstring(checkpoint="zai-org/GLM-4.5")
 class Glm4MoeConfig(PreTrainedConfig):
     r"""
     n_group (`int`, *optional*, defaults to 1):

src/transformers/models/glm4_moe/modular_glm4_moe.py

@@ -36,7 +36,7 @@
 logger = logging.get_logger(__name__)
 
 
-@auto_docstring(checkpoint="THUDM/GLM-4-100B-A10B")
+@auto_docstring(checkpoint="zai-org/GLM-4.5")
 class Glm4MoeConfig(PreTrainedConfig):
     r"""
     n_group (`int`, *optional*, defaults to 1):

src/transformers/models/glm4_moe_lite/configuration_glm4_moe_lite.py

@@ -24,7 +24,7 @@
 from ...utils import auto_docstring
 
 
-@auto_docstring(checkpoint="THUDM/GLM-4-100B-A10B")
+@auto_docstring(checkpoint="zai-org/GLM-4.5")
 class Glm4MoeLiteConfig(PreTrainedConfig):
     r"""
     rope_interleave (`bool`, *optional*, defaults to `True`):

src/transformers/models/glm4_moe_lite/modular_glm4_moe_lite.py

@@ -33,7 +33,7 @@
 )
 
 
-@auto_docstring(checkpoint="THUDM/GLM-4-100B-A10B")
+@auto_docstring(checkpoint="zai-org/GLM-4.5")
 class Glm4MoeLiteConfig(PreTrainedConfig):
     r"""
     rope_interleave (`bool`, *optional*, defaults to `True`):

src/transformers/models/helium/configuration_helium.py

@@ -19,7 +19,7 @@
 from ...utils import auto_docstring
 
 
-@auto_docstring(checkpoint="kyutai/helium-2b")
+@auto_docstring(checkpoint="kyutai/helium-1-preview")
 class HeliumConfig(PreTrainedConfig):
     r"""
     Example:

src/transformers/models/instructblip/configuration_instructblip.py

@@ -22,18 +22,18 @@
 logger = logging.get_logger(__name__)
 
 
-@auto_docstring(checkpoint="Salesforce/instruct-blip-flan-t5")
+@auto_docstring(checkpoint="Salesforce/instructblip-flan-t5-xl")
 class InstructBlipVisionConfig(PreTrainedConfig):
     r"""
     Example:
 
     ```python
     >>> from transformers import InstructBlipVisionConfig, InstructBlipVisionModel
 
-    >>> # Initializing a InstructBlipVisionConfig with Salesforce/instruct-blip-flan-t5 style configuration
+    >>> # Initializing a InstructBlipVisionConfig with Salesforce/instructblip-flan-t5-xl style configuration
     >>> configuration = InstructBlipVisionConfig()
 
-    >>> # Initializing a InstructBlipVisionModel (with random weights) from the Salesforce/instruct-blip-flan-t5 style configuration
+    >>> # Initializing a InstructBlipVisionModel (with random weights) from the Salesforce/instructblip-flan-t5-xl style configuration
     >>> model = InstructBlipVisionModel(configuration)
 
     >>> # Accessing the model configuration
@@ -73,7 +73,7 @@ def __init__(
         self.qkv_bias = qkv_bias
 
 
-@auto_docstring(checkpoint="Salesforce/instruct-blip-flan-t5")
+@auto_docstring(checkpoint="Salesforce/instructblip-flan-t5-xl")
 class InstructBlipQFormerConfig(PreTrainedConfig):
     r"""
     cross_attention_frequency (`int`, *optional*, defaults to 2):
@@ -86,10 +86,10 @@ class InstructBlipQFormerConfig(PreTrainedConfig):
     ```python
     >>> from transformers import InstructBlipQFormerConfig, InstructBlipQFormerModel
 
-    >>> # Initializing a InstructBLIP Salesforce/instruct-blip-flan-t5 style configuration
+    >>> # Initializing a InstructBLIP Salesforce/instructblip-flan-t5-xl style configuration
     >>> configuration = InstructBlipQFormerConfig()
 
-    >>> # Initializing a model (with random weights) from the Salesforce/instruct-blip-flan-t5 style configuration
+    >>> # Initializing a model (with random weights) from the Salesforce/instructblip-flan-t5-xl style configuration
     >>> model = InstructBlipQFormerModel(configuration)
     >>> # Accessing the model configuration
     >>> configuration = model.config
@@ -134,7 +134,7 @@ def __init__(
         self.encoder_hidden_size = encoder_hidden_size
 
 
-@auto_docstring(checkpoint="Salesforce/instruct-blip-flan-t5")
+@auto_docstring(checkpoint="Salesforce/instructblip-flan-t5-xl")
 class InstructBlipConfig(PreTrainedConfig):
     r"""
     qformer_config (`dict`, *optional*):
@@ -153,10 +153,10 @@ class InstructBlipConfig(PreTrainedConfig):
     ...     InstructBlipForConditionalGeneration,
     ... )
 
-    >>> # Initializing a InstructBlipConfig with Salesforce/instruct-blip-flan-t5 style configuration
+    >>> # Initializing a InstructBlipConfig with Salesforce/instructblip-flan-t5-xl style configuration
     >>> configuration = InstructBlipConfig()
 
-    >>> # Initializing a InstructBlipForConditionalGeneration (with random weights) from the Salesforce/instruct-blip-flan-t5 style configuration
+    >>> # Initializing a InstructBlipForConditionalGeneration (with random weights) from the Salesforce/instructblip-flan-t5-xl style configuration
     >>> model = InstructBlipForConditionalGeneration(configuration)
 
     >>> # Accessing the model configuration