Add `Kosmos-2` model (#24709)

* Add KOSMOS-2 model

* update

* update

* update

* address review comment - 001

* address review comment - 002

* address review comment - 003

* style

* Apply suggestions from code review
Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

* fix

* address review comment - 004

* address review comment - 005

* address review comment - 006

* address review comment - 007

* address review comment - 008

* address review comment - 009

* address review comment - 010

* address review comment - 011

* update readme

* fix

* fix

* fix

* [skip ci] fix

* revert the change in _decode

* fix docstring

* fix docstring

* Update docs/source/en/model_doc/kosmos-2.md
Co-authored-by: NielsRogge <48327001+NielsRogge@users.noreply.github.com>

* no more Kosmos2Tokenizer

* style

* remove "returned when being computed by the model"

* Apply suggestions from code review
Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>

* UTM5 Atten

* fix attn mask

* use present_key_value_states instead of next_decoder_cache

* style

* conversion scripts

* conversion scripts

* conversion scripts

* Add _reorder_cache

* fix doctest and copies

* rename 1

* rename 2

* rename 3

* make fixup

* fix table

* fix docstring

* rename 4

* change repo_id

* remove tip

* update md file

* make style

* update md file

* put docs/source/en/model_doc/kosmos-2.md to slow

* update conversion script

* Use CLIPImageProcessor in Kosmos2Processor

* Remove Kosmos2ImageProcessor

* Remove to_dict in Kosmos2Config

* Remove files

* fix import

* Update conversion

* normalized=False

* Not using hardcoded values like <image>

* elt --> element

* Apply suggestion

* Not using hardcoded values like </image>

* No assert

* No nested functions

* Fix md file

* copy

* update doc

* fix docstring

* fix name

* Remove _add_remove_spaces_around_tag_tokens

* Remove dummy docstring of _preprocess_single_example

* Use `BatchEncoding`

* temp

* temp

* temp

* Update

* Update

* Make Kosmos2ProcessorTest a bit pretty

* Update gradient checkpointing

* Fix gradient checkpointing test

* Remove one liner remove_special_fields

* Simplify conversion script

* fix add_eos_token

* update readme

* update tests

* Change to microsoft/kosmos-2-patch14-224

* style

* Fix doc

---------
Co-authored-by: ydshieh <ydshieh@users.noreply.github.com>
Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>
Co-authored-by: NielsRogge <48327001+NielsRogge@users.noreply.github.com>
Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>

src/transformers/utils/dummy_pt_objects.py

@@ -4261,6 +4261,30 @@ class JukeboxVQVAE(metaclass=DummyObject):
         requires_backends(self, ["torch"])
 
 
+KOSMOS2_PRETRAINED_MODEL_ARCHIVE_LIST = None
+
+
+class Kosmos2ForConditionalGeneration(metaclass=DummyObject):
+    _backends = ["torch"]
+
+    def __init__(self, *args, **kwargs):
+        requires_backends(self, ["torch"])
+
+
+class Kosmos2Model(metaclass=DummyObject):
+    _backends = ["torch"]
+
+    def __init__(self, *args, **kwargs):
+        requires_backends(self, ["torch"])
+
+
+class Kosmos2PreTrainedModel(metaclass=DummyObject):
+    _backends = ["torch"]
+
+    def __init__(self, *args, **kwargs):
+        requires_backends(self, ["torch"])
+
+
 LAYOUTLM_PRETRAINED_MODEL_ARCHIVE_LIST = None
 
 

utils/check_repo.py

@@ -73,6 +73,9 @@ PRIVATE_MODELS = [
     "MaskFormerSwinPreTrainedModel",
     "BridgeTowerTextModel",
     "BridgeTowerVisionModel",
+    "Kosmos2TextModel",
+    "Kosmos2TextForCausalLM",
+    "Kosmos2VisionModel",
 ]
 
 # Update this list for models that are not tested with a comment explaining the reason it should not be.

utils/not_doctested.txt

@@ -618,6 +618,7 @@ src/transformers/models/instructblip/processing_instructblip.py
 src/transformers/models/jukebox/configuration_jukebox.py
 src/transformers/models/jukebox/convert_jukebox.py
 src/transformers/models/jukebox/modeling_jukebox.py
+src/transformers/models/kosmos2/convert_kosmos2_original_pytorch_checkpoint_to_pytorch.py
 src/transformers/models/led/configuration_led.py
 src/transformers/models/led/modeling_led.py
 src/transformers/models/led/modeling_tf_led.py

utils/slow_documentation_tests.txt

 docs/source/en/generation_strategies.md
 docs/source/en/model_doc/ctrl.md
+docs/source/en/model_doc/kosmos-2.md
 docs/source/en/model_doc/seamless_m4t.md
 docs/source/en/task_summary.md
 docs/source/en/tasks/prompting.md
 src/transformers/models/blip_2/modeling_blip_2.py
 src/transformers/models/ctrl/modeling_ctrl.py
+src/transformers/models/kosmos2/modeling_kosmos2.py