[Fix] add docstring

Anti-Entrophic · Anti-Entrophic · commit 0b99b669ba31 · 2025-07-29T16:19:52.000+08:00
diff --git a/docs/source/en/_toctree.yml b/docs/source/en/_toctree.yml
@@ -521,6 +521,8 @@
         title: HGNet-V2
       - local: model_doc/ibert
         title: I-BERT
+      - local: model_doc/interns1
+        title: InternS1
       - local: model_doc/jamba
         title: Jamba
       - local: model_doc/jetmoe
diff --git a/docs/source/en/model_doc/interns1.md b/docs/source/en/model_doc/interns1.md
@@ -0,0 +1,56 @@
+<!--Copyright 2025 The HuggingFace Team. All rights reserved.
+
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+
+⚠️ Note that this file is in Markdown but contain specific syntax for our doc-builder (similar to MDX) that may not be
+rendered properly in your Markdown viewer.
+
+-->
+
+## InternS1Config
+
+[[autodoc]] InternS1Config
+
+## InternS1VisionConfig
+
+[[autodoc]] InternS1VisionConfig
+
+## InternS1Model
+
+[[autodoc]] InternS1Model
+    - forward
+
+## InternS1ForConditionalGeneration
+
+[[autodoc]] InternS1ForConditionalGeneration
+    - forward
+
+## InternS1VisionModel
+
+[[autodoc]] InternS1VisionModel
+    - forward
+
+## InternS1Processor
+
+[[autodoc]] InternS1Processor
+    - __call__
+    - decode
+    - batch_decode
+
+## InternS1Tokenizer
+
+[[autodoc]] InternS1Tokenizer
+    - __call__
+    - tokenize
+    - decode
+
+## InternS1VideoProcessor
+
+[[autodoc]] InternS1VideoProcessor
diff --git a/src/transformers/models/__init__.py b/src/transformers/models/__init__.py
@@ -161,8 +161,8 @@
     from .informer import *
     from .instructblip import *
     from .instructblipvideo import *
-    from .internvl import *
     from .interns1 import *
+    from .internvl import *
     from .jamba import *
     from .janus import *
     from .jetmoe import *
diff --git a/src/transformers/models/auto/configuration_auto.py b/src/transformers/models/auto/configuration_auto.py
@@ -196,10 +196,10 @@
         ("informer", "InformerConfig"),
         ("instructblip", "InstructBlipConfig"),
         ("instructblipvideo", "InstructBlipVideoConfig"),
-        ("internvl", "InternVLConfig"),
-        ("internvl_vision", "InternVLVisionConfig"),
         ("interns1", "InternS1Config"),
         ("interns1_vision", "InternS1VisionConfig"),
+        ("internvl", "InternVLConfig"),
+        ("internvl_vision", "InternVLVisionConfig"),
         ("jamba", "JambaConfig"),
         ("janus", "JanusConfig"),
         ("jetmoe", "JetMoeConfig"),
@@ -602,10 +602,10 @@
         ("informer", "Informer"),
         ("instructblip", "InstructBLIP"),
         ("instructblipvideo", "InstructBlipVideo"),
-        ("internvl", "InternVL"),
-        ("internvl_vision", "InternVLVision"),
         ("interns1", "InternS1"),
         ("interns1_vision", "InternS1Vision"),
+        ("internvl", "InternVL"),
+        ("internvl_vision", "InternVLVision"),
         ("jamba", "Jamba"),
         ("janus", "Janus"),
         ("jetmoe", "JetMoe"),
diff --git a/src/transformers/models/auto/modeling_auto.py b/src/transformers/models/auto/modeling_auto.py
@@ -185,10 +185,10 @@
         ("informer", "InformerModel"),
         ("instructblip", "InstructBlipModel"),
         ("instructblipvideo", "InstructBlipVideoModel"),
-        ("internvl", "InternVLModel"),
-        ("internvl_vision", "InternVLVisionModel"),
         ("interns1", "InternS1Model"),
         ("interns1_vision", "InternS1VisionModel"),
+        ("internvl", "InternVLModel"),
+        ("internvl_vision", "InternVLVisionModel"),
         ("jamba", "JambaModel"),
         ("janus", "JanusModel"),
         ("jetmoe", "JetMoeModel"),
@@ -960,8 +960,8 @@
         ("idefics2", "Idefics2ForConditionalGeneration"),
         ("idefics3", "Idefics3ForConditionalGeneration"),
         ("instructblip", "InstructBlipForConditionalGeneration"),
-        ("internvl", "InternVLForConditionalGeneration"),
         ("interns1", "InternS1ForConditionalGeneration"),
+        ("internvl", "InternVLForConditionalGeneration"),
         ("janus", "JanusForConditionalGeneration"),
         ("kosmos-2", "Kosmos2ForConditionalGeneration"),
         ("llama4", "Llama4ForConditionalGeneration"),
diff --git a/src/transformers/models/auto/processing_auto.py b/src/transformers/models/auto/processing_auto.py
@@ -83,8 +83,8 @@
         ("idefics3", "Idefics3Processor"),
         ("instructblip", "InstructBlipProcessor"),
         ("instructblipvideo", "InstructBlipVideoProcessor"),
-        ("internvl", "InternVLProcessor"),
         ("interns1", "InternS1Processor"),
+        ("internvl", "InternVLProcessor"),
         ("janus", "JanusProcessor"),
         ("kosmos-2", "Kosmos2Processor"),
         ("kyutai_speech_to_text", "KyutaiSpeechToTextProcessor"),
diff --git a/src/transformers/models/auto/tokenization_auto.py b/src/transformers/models/auto/tokenization_auto.py
@@ -317,8 +317,8 @@
         ("idefics3", ("LlamaTokenizer", "LlamaTokenizerFast" if is_tokenizers_available() else None)),
         ("instructblip", ("GPT2Tokenizer", "GPT2TokenizerFast" if is_tokenizers_available() else None)),
         ("instructblipvideo", ("GPT2Tokenizer", "GPT2TokenizerFast" if is_tokenizers_available() else None)),
-        ("internvl", ("Qwen2Tokenizer", "Qwen2TokenizerFast" if is_tokenizers_available() else None)),
         ("interns1", ("InternS1Tokenizer", None)),
+        ("internvl", ("Qwen2Tokenizer", "Qwen2TokenizerFast" if is_tokenizers_available() else None)),
         (
             "jamba",
             (
diff --git a/src/transformers/models/auto/video_processing_auto.py b/src/transformers/models/auto/video_processing_auto.py
@@ -49,8 +49,8 @@
             ("glm4v", "Glm4vVideoProcessor"),
             ("instructblip", "InstructBlipVideoVideoProcessor"),
             ("instructblipvideo", "InstructBlipVideoVideoProcessor"),
-            ("internvl", "InternVLVideoProcessor"),
             ("interns1", "InternS1VideoProcessor"),
+            ("internvl", "InternVLVideoProcessor"),
             ("llava_next_video", "LlavaNextVideoVideoProcessor"),
             ("llava_onevision", "LlavaOnevisionVideoProcessor"),
             ("qwen2_5_omni", "Qwen2VLVideoProcessor"),
diff --git a/src/transformers/models/interns1/__init__.py b/src/transformers/models/interns1/__init__.py
@@ -21,8 +21,8 @@
     from .configuration_interns1 import *
     from .modeling_interns1 import *
     from .processing_interns1 import *
-    from .video_processing_interns1 import *
     from .tokenization_interns1 import *
+    from .video_processing_interns1 import *
 else:
     import sys
 
diff --git a/src/transformers/models/interns1/configuration_interns1.py b/src/transformers/models/interns1/configuration_interns1.py
@@ -21,7 +21,9 @@
 class InternS1VisionConfig(PretrainedConfig):
     r"""
     This is the configuration class to store the configuration of a [`InternS1VisionModel`]. It is used to instantiate
-    an InternS1VisionModel model according to the specified arguments, defining the model architecture.
+    an InternS1VisionModel 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 Intern-S1.
+    e.g. [internlm/Intern-S1](https://huggingface.co/internlm/Intern-S1)
 
     Args:
         hidden_size (`int`, *optional*, defaults to 1024):
@@ -141,6 +143,8 @@ class InternS1Config(PretrainedConfig):
     r"""
     This is the configuration class to store the configuration of a [`InternS1ForConditionalGeneration`].
     It is used to instantiate a InternS1 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 Intern-S1.
+    e.g. [internlm/Intern-S1](https://huggingface.co/internlm/Intern-S1)
 
     Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
     documentation from [`PretrainedConfig`] for more information.
diff --git a/src/transformers/models/interns1/modeling_interns1.py b/src/transformers/models/interns1/modeling_interns1.py
@@ -565,37 +565,32 @@ def forward(self, image_features):
     """
 )
 class InternS1ModelOutputWithPast(ModelOutput):
-    """
-    Base class for model's outputs, with potential hidden states and attentions.
-
-    Args:
-        last_hidden_state (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`):
-            Sequence of hidden-states at the output of the last layer of the model.
-        past_key_values (`Cache`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`):
-            It is a [`~cache_utils.Cache`] instance. For more details, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache).
-
-            Contains pre-computed hidden-states (key and values in the self-attention blocks and optionally if
-            `config.is_encoder_decoder=True` in the cross-attention blocks) that can be used (see `past_key_values`
-            input) to speed up sequential decoding.
-        hidden_states (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
-            Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, +
-            one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.
-
-            Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.
-        attentions (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
-            Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
-            sequence_length)`.
-
-            Attentions weights after the attention softmax, used to compute the weighted average in the self-attention
-            heads.
-        router_logits (`tuple(torch.FloatTensor)`, *optional*, returned when `output_router_probs=True` and `config.add_router_probs=True` is passed or when `config.output_router_probs=True`):
-            Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, sequence_length, num_experts)`.
-
-            Raw router logtis (post-softmax) that are computed by MoE routers, these terms are used to compute the auxiliary
-            loss for Mixture of Experts models.
-        image_hidden_states (`torch.FloatTensor`, *optional*):
-            A `torch.FloatTensor` of size `(batch_size, num_images, sequence_length, hidden_size)`.
-            image_hidden_states of the model produced by the vision encoder and after projecting the last hidden state.
+    r"""
+    past_key_values (`Cache`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`):
+        It is a [`~cache_utils.Cache`] instance. For more details, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache).
+
+        Contains pre-computed hidden-states (key and values in the self-attention blocks and optionally if
+        `config.is_encoder_decoder=True` in the cross-attention blocks) that can be used (see `past_key_values`
+        input) to speed up sequential decoding.
+    hidden_states (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
+        Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, +
+        one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.
+
+        Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.
+    attentions (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
+        Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
+        sequence_length)`.
+
+        Attentions weights after the attention softmax, used to compute the weighted average in the self-attention
+        heads.
+    router_logits (`tuple(torch.FloatTensor)`, *optional*, returned when `output_router_probs=True` and `config.add_router_probs=True` is passed or when `config.output_router_probs=True`):
+        Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, sequence_length, num_experts)`.
+
+        Raw router logtis (post-softmax) that are computed by MoE routers, these terms are used to compute the auxiliary
+        loss for Mixture of Experts models.
+    image_hidden_states (`torch.FloatTensor`, *optional*):
+        A `torch.FloatTensor` of size `(batch_size, num_images, sequence_length, hidden_size)`.
+        image_hidden_states of the model produced by the vision encoder and after projecting the last hidden state.
     """
 
     last_hidden_state: Optional[torch.FloatTensor] = None
@@ -820,44 +815,37 @@ def pixel_shuffle(self, vision_features: torch.Tensor, scale_factor: float = 0.5
     """
 )
 class InternS1CausalLMOutputWithPast(ModelOutput):
-    """
-    Base class for causal language model (or autoregressive) with mixture of experts outputs.
-
-    Args:
-        loss (`torch.FloatTensor` of shape `(1,)`, *optional*, returned when `labels` is provided):
-            Language modeling loss (for next-token prediction).
-
-        logits (`torch.FloatTensor` of shape `(batch_size, sequence_length, config.vocab_size)`):
-            Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).
-
-        aux_loss (`torch.FloatTensor`, *optional*, returned when `labels` is provided):
-            aux_loss for the sparse modules.
-
-        router_logits (`tuple(torch.FloatTensor)`, *optional*, returned when `output_router_probs=True` and `config.add_router_probs=True` is passed or when `config.output_router_probs=True`):
-            Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, sequence_length, num_experts)`.
-
-            Raw router logtis (post-softmax) that are computed by MoE routers, these terms are used to compute the auxiliary
-            loss for Mixture of Experts models.
-
-        past_key_values (`Cache`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`):
-            It is a [`~cache_utils.Cache`] instance. For more details, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache).
-
-            Contains pre-computed hidden-states (key and values in the self-attention blocks) that can be used (see
-            `past_key_values` input) to speed up sequential decoding.
-        hidden_states (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
-            Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, +
-            one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.
-
-            Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.
-        attentions (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
-            Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
-            sequence_length)`.
-
-            Attentions weights after the attention softmax, used to compute the weighted average in the self-attention
-            heads.
-        image_hidden_states (`torch.FloatTensor`, *optional*):
-            A `torch.FloatTensor` of size `(batch_size, num_images, sequence_length, hidden_size)`.
-            image_hidden_states of the model produced by the vision encoder and after projecting the last hidden state.
+    r"""
+    loss (`torch.FloatTensor` of shape `(1,)`, *optional*, returned when `labels` is provided):
+        Language modeling loss (for next-token prediction).
+    aux_loss (`torch.FloatTensor`, *optional*, returned when `labels` is provided):
+        aux_loss for the sparse modules.
+    logits (`torch.FloatTensor` of shape `(batch_size, sequence_length, config.vocab_size)`):
+        Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).
+    past_key_values (`Cache`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`):
+        It is a [`~cache_utils.Cache`] instance. For more details, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache).
+
+        Contains pre-computed hidden-states (key and values in the self-attention blocks) that can be used (see
+        `past_key_values` input) to speed up sequential decoding.
+    hidden_states (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
+        Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, +
+        one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.
+
+        Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.
+    attentions (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
+        Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
+        sequence_length)`.
+
+        Attentions weights after the attention softmax, used to compute the weighted average in the self-attention
+        heads.
+    router_logits (`tuple(torch.FloatTensor)`, *optional*, returned when `output_router_probs=True` and `config.add_router_probs=True` is passed or when `config.output_router_probs=True`):
+        Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, sequence_length, num_experts)`.
+
+        Raw router logtis (post-softmax) that are computed by MoE routers, these terms are used to compute the auxiliary
+        loss for Mixture of Experts models.
+    image_hidden_states (`torch.FloatTensor`, *optional*):
+        A `torch.FloatTensor` of size `(batch_size, num_images, sequence_length, hidden_size)`.
+        image_hidden_states of the model produced by the vision encoder and after projecting the last hidden state.
     """
 
     loss: Optional[torch.FloatTensor] = None
diff --git a/src/transformers/models/interns1/modular_interns1.py b/src/transformers/models/interns1/modular_interns1.py
@@ -30,13 +30,13 @@
 from ...modeling_utils import ALL_ATTENTION_FUNCTIONS, PreTrainedModel
 from ...processing_utils import Unpack
 from ...utils import (
+    ModelOutput,
+    TransformersKwargs,
     auto_docstring,
     can_return_tuple,
     is_torchdynamo_compiling,
     logging,
     torch_int,
-    ModelOutput,
-    TransformersKwargs,
 )
 from ..clip.modeling_clip import CLIPMLP
 from ..janus.modeling_janus import JanusVisionAttention
diff --git a/src/transformers/models/interns1/tokenization_interns1.py b/src/transformers/models/interns1/tokenization_interns1.py
diff --git a/utils/check_repo.py b/utils/check_repo.py

Original file line number	Diff line number	Diff line change
`@@ -317,8 +317,8 @@`
`317`	`317`	`("idefics3", ("LlamaTokenizer", "LlamaTokenizerFast" if is_tokenizers_available() else None)),`
`318`	`318`	`("instructblip", ("GPT2Tokenizer", "GPT2TokenizerFast" if is_tokenizers_available() else None)),`
`319`	`319`	`("instructblipvideo", ("GPT2Tokenizer", "GPT2TokenizerFast" if is_tokenizers_available() else None)),`
`320`		`- ("internvl", ("Qwen2Tokenizer", "Qwen2TokenizerFast" if is_tokenizers_available() else None)),`
`321`	`320`	`("interns1", ("InternS1Tokenizer", None)),`
	`321`	`+ ("internvl", ("Qwen2Tokenizer", "Qwen2TokenizerFast" if is_tokenizers_available() else None)),`
`322`	`322`	`(`
`323`	`323`	`"jamba",`
`324`	`324`	`(`