[`Styling`] stylify using ruff (#27144)

* try to stylify using ruff

* might need to remove these changes?

* use ruf format andruff check

* use isinstance instead of type comparision

* use # fmt: skip

* use # fmt: skip

* nits

* soem styling changes

* update ci job

* nits isinstance

* more files update

* nits

* more nits

* small nits

* check and format

* revert wrong changes

* actually use formatter instead of checker

* nits

* well docbuilder is overwriting this commit

* revert notebook changes

* try to nuke docbuilder

* style

* fix feature exrtaction test

* remve `indent-width = 4`

* fixup

* more nits

* update the ruff version that we use

* style

* nuke docbuilder styling

* leve the print for detected changes

* nits

* Remove file I/O
Co-authored-by: charliermarsh <charlie.r.marsh@gmail.com>

* style

* nits

* revert notebook changes

* Add # fmt skip when possible

* Add # fmt skip when possible

* Fix

* More `  # fmt: skip` usage

* More `  # fmt: skip` usage

* More `  # fmt: skip` usage

* NIts

* more fixes

* fix tapas

* Another way to skip

* Recommended way

* Fix two more fiels

* Remove asynch
Remove asynch

---------
Co-authored-by: charliermarsh <charlie.r.marsh@gmail.com>

src/transformers/models/mobilenet_v2/configuration_mobilenet_v2.py

@@ -96,6 +96,7 @@ class MobileNetV2Config(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "mobilenet_v2"
 
     def __init__(

src/transformers/models/mobilenet_v2/image_processing_mobilenet_v2.py

@@ -312,8 +312,7 @@ class MobileNetV2ImageProcessor(BaseImageProcessor):
     # Copied from transformers.models.beit.image_processing_beit.BeitImageProcessor.post_process_semantic_segmentation with Beit->MobileNetV2
     def post_process_semantic_segmentation(self, outputs, target_sizes: List[Tuple] = None):
         """
-        Converts the output of [`MobileNetV2ForSemanticSegmentation`] into semantic segmentation maps. Only supports
-        PyTorch.
+        Converts the output of [`MobileNetV2ForSemanticSegmentation`] into semantic segmentation maps. Only supports PyTorch.
 
         Args:
             outputs ([`MobileNetV2ForSemanticSegmentation`]):

src/transformers/models/mobilevit/configuration_mobilevit.py

@@ -111,6 +111,7 @@ class MobileViTConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "mobilevit"
 
     def __init__(

src/transformers/models/mobilevit/image_processing_mobilevit.py

@@ -311,8 +311,7 @@ class MobileViTImageProcessor(BaseImageProcessor):
     # Copied from transformers.models.beit.image_processing_beit.BeitImageProcessor.post_process_semantic_segmentation with Beit->MobileViT
     def post_process_semantic_segmentation(self, outputs, target_sizes: List[Tuple] = None):
         """
-        Converts the output of [`MobileViTForSemanticSegmentation`] into semantic segmentation maps. Only supports
-        PyTorch.
+        Converts the output of [`MobileViTForSemanticSegmentation`] into semantic segmentation maps. Only supports PyTorch.
 
         Args:
             outputs ([`MobileViTForSemanticSegmentation`]):

src/transformers/models/mobilevitv2/configuration_mobilevitv2.py

@@ -97,6 +97,7 @@ class MobileViTV2Config(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "mobilevitv2"
 
     def __init__(

src/transformers/models/mpnet/configuration_mpnet.py

@@ -79,6 +79,7 @@ class MPNetConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "mpnet"
 
     def __init__(

src/transformers/models/mpt/modeling_mpt.py

@@ -51,7 +51,7 @@ MPT_PRETRAINED_MODEL_ARCHIVE_LIST = [
     "mosaicml/mpt-7b-8k-chat",
     "mosaicml/mpt-30b",
     "mosaicml/mpt-30b-instruct",
-    "mosaicml/mpt-30b-chat"
+    "mosaicml/mpt-30b-chat",
     # See all MPT models at https://huggingface.co/models?filter=mpt
 ]
 

src/transformers/models/mra/configuration_mra.py

@@ -90,6 +90,7 @@ class MraConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "mra"
 
     def __init__(

src/transformers/models/mt5/configuration_mt5.py

@@ -68,6 +68,7 @@ class MT5Config(PretrainedConfig):
         use_cache (`bool`, *optional*, defaults to `True`):
             Whether or not the model should return the last key/values attentions (not used by all models).
     """
+
     model_type = "mt5"
     keys_to_ignore_at_inference = ["past_key_values"]
 

src/transformers/models/mt5/modeling_flax_mt5.py

@@ -61,6 +61,7 @@ class FlaxMT5Model(FlaxT5Model):
     >>> outputs = model(input_ids=inputs["input_ids"], decoder_input_ids=decoder_input_ids)
     >>> hidden_states = outputs.last_hidden_state
     ```"""
+
     model_type = "mt5"
     config_class = MT5Config
 
@@ -87,6 +88,7 @@ class FlaxMT5EncoderModel(FlaxT5EncoderModel):
     >>> outputs = model(input_ids=inputs["input_ids"])
     >>> hidden_states = outputs.last_hidden_state
     ```"""
+
     model_type = "mt5"
     config_class = MT5Config
 

src/transformers/models/mt5/modeling_mt5.py

@@ -1331,6 +1331,7 @@ class MT5Model(MT5PreTrainedModel):
     >>> outputs = model(input_ids=inputs["input_ids"], decoder_input_ids=labels["input_ids"])
     >>> hidden_states = outputs.last_hidden_state
     ```"""
+
     model_type = "mt5"
     config_class = MT5Config
     _keys_to_ignore_on_load_missing = ["decoder.block.0.layer.1.EncDecAttention.relative_attention_bias.weight"]

src/transformers/models/mt5/modeling_tf_mt5.py

@@ -44,6 +44,7 @@ class TFMT5Model(TFT5Model):
     >>> outputs = model(input_ids=inputs["input_ids"], decoder_input_ids=labels["input_ids"])
     >>> hidden_states = outputs.last_hidden_state
     ```"""
+
     model_type = "mt5"
     config_class = MT5Config
 

src/transformers/models/musicgen/configuration_musicgen.py

@@ -79,6 +79,7 @@ class MusicgenDecoderConfig(PretrainedConfig):
             Number of channels in the audio data. Either 1 for mono or 2 for stereo. Stereo models generate a separate
             audio stream for the left/right output channels. Mono models generate a single audio stream output.
     """
+
     model_type = "musicgen_decoder"
     keys_to_ignore_at_inference = ["past_key_values"]
 

src/transformers/models/musicgen/processing_musicgen.py

@@ -37,6 +37,7 @@ class MusicgenProcessor(ProcessorMixin):
         tokenizer (`T5Tokenizer`):
             An instance of [`T5Tokenizer`]. The tokenizer is a required input.
     """
+
     feature_extractor_class = "EncodecFeatureExtractor"
     tokenizer_class = ("T5Tokenizer", "T5TokenizerFast")
 

src/transformers/models/mvp/configuration_mvp.py

@@ -104,6 +104,7 @@ class MvpConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "mvp"
     keys_to_ignore_at_inference = ["past_key_values"]
     attribute_map = {"num_attention_heads": "encoder_attention_heads", "hidden_size": "d_model"}

src/transformers/models/mvp/tokenization_mvp_fast.py

@@ -130,6 +130,7 @@ class MvpTokenizerFast(PreTrainedTokenizerFast):
         trim_offsets (`bool`, *optional*, defaults to `True`):
             Whether the post processing step should trim offsets to avoid including whitespaces.
     """
+
     vocab_files_names = VOCAB_FILES_NAMES
     pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
     max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES

src/transformers/models/nat/configuration_nat.py

@@ -92,6 +92,7 @@ class NatConfig(BackboneConfigMixin, PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     model_type = "nat"
 
     attribute_map = {

src/transformers/models/nezha/configuration_nezha.py

@@ -63,6 +63,7 @@ class NezhaConfig(PretrainedConfig):
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
+
     pretrained_config_archive_map = NEZHA_PRETRAINED_CONFIG_ARCHIVE_MAP
     model_type = "nezha"
 

src/transformers/models/nllb/tokenization_nllb.py

@@ -41,9 +41,7 @@ PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {
     "facebook/nllb-200-distilled-600M": 1024,
 }
 
-# fmt: off
-FAIRSEQ_LANGUAGE_CODES = ['ace_Arab', 'ace_Latn', 'acm_Arab', 'acq_Arab', 'aeb_Arab', 'afr_Latn', 'ajp_Arab', 'aka_Latn', 'amh_Ethi', 'apc_Arab', 'arb_Arab', 'ars_Arab', 'ary_Arab', 'arz_Arab', 'asm_Beng', 'ast_Latn', 'awa_Deva', 'ayr_Latn', 'azb_Arab', 'azj_Latn', 'bak_Cyrl', 'bam_Latn', 'ban_Latn', 'bel_Cyrl', 'bem_Latn', 'ben_Beng', 'bho_Deva', 'bjn_Arab', 'bjn_Latn', 'bod_Tibt', 'bos_Latn', 'bug_Latn', 'bul_Cyrl', 'cat_Latn', 'ceb_Latn', 'ces_Latn', 'cjk_Latn', 'ckb_Arab', 'crh_Latn', 'cym_Latn', 'dan_Latn', 'deu_Latn', 'dik_Latn', 'dyu_Latn', 'dzo_Tibt', 'ell_Grek', 'eng_Latn', 'epo_Latn', 'est_Latn', 'eus_Latn', 'ewe_Latn', 'fao_Latn', 'pes_Arab', 'fij_Latn', 'fin_Latn', 'fon_Latn', 'fra_Latn', 'fur_Latn', 'fuv_Latn', 'gla_Latn', 'gle_Latn', 'glg_Latn', 'grn_Latn', 'guj_Gujr', 'hat_Latn', 'hau_Latn', 'heb_Hebr', 'hin_Deva', 'hne_Deva', 'hrv_Latn', 'hun_Latn', 'hye_Armn', 'ibo_Latn', 'ilo_Latn', 'ind_Latn', 'isl_Latn', 'ita_Latn', 'jav_Latn', 'jpn_Jpan', 'kab_Latn', 'kac_Latn', 'kam_Latn', 'kan_Knda', 'kas_Arab', 'kas_Deva', 'kat_Geor', 'knc_Arab', 'knc_Latn', 'kaz_Cyrl', 'kbp_Latn', 'kea_Latn', 'khm_Khmr', 'kik_Latn', 'kin_Latn', 'kir_Cyrl', 'kmb_Latn', 'kon_Latn', 'kor_Hang', 'kmr_Latn', 'lao_Laoo', 'lvs_Latn', 'lij_Latn', 'lim_Latn', 'lin_Latn', 'lit_Latn', 'lmo_Latn', 'ltg_Latn', 'ltz_Latn', 'lua_Latn', 'lug_Latn', 'luo_Latn', 'lus_Latn', 'mag_Deva', 'mai_Deva', 'mal_Mlym', 'mar_Deva', 'min_Latn', 'mkd_Cyrl', 'plt_Latn', 'mlt_Latn', 'mni_Beng', 'khk_Cyrl', 'mos_Latn', 'mri_Latn', 'zsm_Latn', 'mya_Mymr', 'nld_Latn', 'nno_Latn', 'nob_Latn', 'npi_Deva', 'nso_Latn', 'nus_Latn', 'nya_Latn', 'oci_Latn', 'gaz_Latn', 'ory_Orya', 'pag_Latn', 'pan_Guru', 'pap_Latn', 'pol_Latn', 'por_Latn', 'prs_Arab', 'pbt_Arab', 'quy_Latn', 'ron_Latn', 'run_Latn', 'rus_Cyrl', 'sag_Latn', 'san_Deva', 'sat_Beng', 'scn_Latn', 'shn_Mymr', 'sin_Sinh', 'slk_Latn', 'slv_Latn', 'smo_Latn', 'sna_Latn', 'snd_Arab', 'som_Latn', 'sot_Latn', 'spa_Latn', 'als_Latn', 'srd_Latn', 'srp_Cyrl', 'ssw_Latn', 'sun_Latn', 'swe_Latn', 'swh_Latn', 'szl_Latn', 'tam_Taml', 'tat_Cyrl', 'tel_Telu', 'tgk_Cyrl', 'tgl_Latn', 'tha_Thai', 'tir_Ethi', 'taq_Latn', 'taq_Tfng', 'tpi_Latn', 'tsn_Latn', 'tso_Latn', 'tuk_Latn', 'tum_Latn', 'tur_Latn', 'twi_Latn', 'tzm_Tfng', 'uig_Arab', 'ukr_Cyrl', 'umb_Latn', 'urd_Arab', 'uzn_Latn', 'vec_Latn', 'vie_Latn', 'war_Latn', 'wol_Latn', 'xho_Latn', 'ydd_Hebr', 'yor_Latn', 'yue_Hant', 'zho_Hans', 'zho_Hant', 'zul_Latn']
-# fmt: on
+FAIRSEQ_LANGUAGE_CODES = ['ace_Arab', 'ace_Latn', 'acm_Arab', 'acq_Arab', 'aeb_Arab', 'afr_Latn', 'ajp_Arab', 'aka_Latn', 'amh_Ethi', 'apc_Arab', 'arb_Arab', 'ars_Arab', 'ary_Arab', 'arz_Arab', 'asm_Beng', 'ast_Latn', 'awa_Deva', 'ayr_Latn', 'azb_Arab', 'azj_Latn', 'bak_Cyrl', 'bam_Latn', 'ban_Latn', 'bel_Cyrl', 'bem_Latn', 'ben_Beng', 'bho_Deva', 'bjn_Arab', 'bjn_Latn', 'bod_Tibt', 'bos_Latn', 'bug_Latn', 'bul_Cyrl', 'cat_Latn', 'ceb_Latn', 'ces_Latn', 'cjk_Latn', 'ckb_Arab', 'crh_Latn', 'cym_Latn', 'dan_Latn', 'deu_Latn', 'dik_Latn', 'dyu_Latn', 'dzo_Tibt', 'ell_Grek', 'eng_Latn', 'epo_Latn', 'est_Latn', 'eus_Latn', 'ewe_Latn', 'fao_Latn', 'pes_Arab', 'fij_Latn', 'fin_Latn', 'fon_Latn', 'fra_Latn', 'fur_Latn', 'fuv_Latn', 'gla_Latn', 'gle_Latn', 'glg_Latn', 'grn_Latn', 'guj_Gujr', 'hat_Latn', 'hau_Latn', 'heb_Hebr', 'hin_Deva', 'hne_Deva', 'hrv_Latn', 'hun_Latn', 'hye_Armn', 'ibo_Latn', 'ilo_Latn', 'ind_Latn', 'isl_Latn', 'ita_Latn', 'jav_Latn', 'jpn_Jpan', 'kab_Latn', 'kac_Latn', 'kam_Latn', 'kan_Knda', 'kas_Arab', 'kas_Deva', 'kat_Geor', 'knc_Arab', 'knc_Latn', 'kaz_Cyrl', 'kbp_Latn', 'kea_Latn', 'khm_Khmr', 'kik_Latn', 'kin_Latn', 'kir_Cyrl', 'kmb_Latn', 'kon_Latn', 'kor_Hang', 'kmr_Latn', 'lao_Laoo', 'lvs_Latn', 'lij_Latn', 'lim_Latn', 'lin_Latn', 'lit_Latn', 'lmo_Latn', 'ltg_Latn', 'ltz_Latn', 'lua_Latn', 'lug_Latn', 'luo_Latn', 'lus_Latn', 'mag_Deva', 'mai_Deva', 'mal_Mlym', 'mar_Deva', 'min_Latn', 'mkd_Cyrl', 'plt_Latn', 'mlt_Latn', 'mni_Beng', 'khk_Cyrl', 'mos_Latn', 'mri_Latn', 'zsm_Latn', 'mya_Mymr', 'nld_Latn', 'nno_Latn', 'nob_Latn', 'npi_Deva', 'nso_Latn', 'nus_Latn', 'nya_Latn', 'oci_Latn', 'gaz_Latn', 'ory_Orya', 'pag_Latn', 'pan_Guru', 'pap_Latn', 'pol_Latn', 'por_Latn', 'prs_Arab', 'pbt_Arab', 'quy_Latn', 'ron_Latn', 'run_Latn', 'rus_Cyrl', 'sag_Latn', 'san_Deva', 'sat_Beng', 'scn_Latn', 'shn_Mymr', 'sin_Sinh', 'slk_Latn', 'slv_Latn', 'smo_Latn', 'sna_Latn', 'snd_Arab', 'som_Latn', 'sot_Latn', 'spa_Latn', 'als_Latn', 'srd_Latn', 'srp_Cyrl', 'ssw_Latn', 'sun_Latn', 'swe_Latn', 'swh_Latn', 'szl_Latn', 'tam_Taml', 'tat_Cyrl', 'tel_Telu', 'tgk_Cyrl', 'tgl_Latn', 'tha_Thai', 'tir_Ethi', 'taq_Latn', 'taq_Tfng', 'tpi_Latn', 'tsn_Latn', 'tso_Latn', 'tuk_Latn', 'tum_Latn', 'tur_Latn', 'twi_Latn', 'tzm_Tfng', 'uig_Arab', 'ukr_Cyrl', 'umb_Latn', 'urd_Arab', 'uzn_Latn', 'vec_Latn', 'vie_Latn', 'war_Latn', 'wol_Latn', 'xho_Latn', 'ydd_Hebr', 'yor_Latn', 'yue_Hant', 'zho_Hans', 'zho_Hant', 'zul_Latn']  # fmt: skip
 
 
 class NllbTokenizer(PreTrainedTokenizer):

src/transformers/models/nllb/tokenization_nllb_fast.py

@@ -53,9 +53,7 @@ PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {
     "facebook/nllb-200-distilled-600M": 1024,
 }
 
-# fmt: off
-FAIRSEQ_LANGUAGE_CODES = ['ace_Arab', 'ace_Latn', 'acm_Arab', 'acq_Arab', 'aeb_Arab', 'afr_Latn', 'ajp_Arab', 'aka_Latn', 'amh_Ethi', 'apc_Arab', 'arb_Arab', 'ars_Arab', 'ary_Arab', 'arz_Arab', 'asm_Beng', 'ast_Latn', 'awa_Deva', 'ayr_Latn', 'azb_Arab', 'azj_Latn', 'bak_Cyrl', 'bam_Latn', 'ban_Latn', 'bel_Cyrl', 'bem_Latn', 'ben_Beng', 'bho_Deva', 'bjn_Arab', 'bjn_Latn', 'bod_Tibt', 'bos_Latn', 'bug_Latn', 'bul_Cyrl', 'cat_Latn', 'ceb_Latn', 'ces_Latn', 'cjk_Latn', 'ckb_Arab', 'crh_Latn', 'cym_Latn', 'dan_Latn', 'deu_Latn', 'dik_Latn', 'dyu_Latn', 'dzo_Tibt', 'ell_Grek', 'eng_Latn', 'epo_Latn', 'est_Latn', 'eus_Latn', 'ewe_Latn', 'fao_Latn', 'pes_Arab', 'fij_Latn', 'fin_Latn', 'fon_Latn', 'fra_Latn', 'fur_Latn', 'fuv_Latn', 'gla_Latn', 'gle_Latn', 'glg_Latn', 'grn_Latn', 'guj_Gujr', 'hat_Latn', 'hau_Latn', 'heb_Hebr', 'hin_Deva', 'hne_Deva', 'hrv_Latn', 'hun_Latn', 'hye_Armn', 'ibo_Latn', 'ilo_Latn', 'ind_Latn', 'isl_Latn', 'ita_Latn', 'jav_Latn', 'jpn_Jpan', 'kab_Latn', 'kac_Latn', 'kam_Latn', 'kan_Knda', 'kas_Arab', 'kas_Deva', 'kat_Geor', 'knc_Arab', 'knc_Latn', 'kaz_Cyrl', 'kbp_Latn', 'kea_Latn', 'khm_Khmr', 'kik_Latn', 'kin_Latn', 'kir_Cyrl', 'kmb_Latn', 'kon_Latn', 'kor_Hang', 'kmr_Latn', 'lao_Laoo', 'lvs_Latn', 'lij_Latn', 'lim_Latn', 'lin_Latn', 'lit_Latn', 'lmo_Latn', 'ltg_Latn', 'ltz_Latn', 'lua_Latn', 'lug_Latn', 'luo_Latn', 'lus_Latn', 'mag_Deva', 'mai_Deva', 'mal_Mlym', 'mar_Deva', 'min_Latn', 'mkd_Cyrl', 'plt_Latn', 'mlt_Latn', 'mni_Beng', 'khk_Cyrl', 'mos_Latn', 'mri_Latn', 'zsm_Latn', 'mya_Mymr', 'nld_Latn', 'nno_Latn', 'nob_Latn', 'npi_Deva', 'nso_Latn', 'nus_Latn', 'nya_Latn', 'oci_Latn', 'gaz_Latn', 'ory_Orya', 'pag_Latn', 'pan_Guru', 'pap_Latn', 'pol_Latn', 'por_Latn', 'prs_Arab', 'pbt_Arab', 'quy_Latn', 'ron_Latn', 'run_Latn', 'rus_Cyrl', 'sag_Latn', 'san_Deva', 'sat_Beng', 'scn_Latn', 'shn_Mymr', 'sin_Sinh', 'slk_Latn', 'slv_Latn', 'smo_Latn', 'sna_Latn', 'snd_Arab', 'som_Latn', 'sot_Latn', 'spa_Latn', 'als_Latn', 'srd_Latn', 'srp_Cyrl', 'ssw_Latn', 'sun_Latn', 'swe_Latn', 'swh_Latn', 'szl_Latn', 'tam_Taml', 'tat_Cyrl', 'tel_Telu', 'tgk_Cyrl', 'tgl_Latn', 'tha_Thai', 'tir_Ethi', 'taq_Latn', 'taq_Tfng', 'tpi_Latn', 'tsn_Latn', 'tso_Latn', 'tuk_Latn', 'tum_Latn', 'tur_Latn', 'twi_Latn', 'tzm_Tfng', 'uig_Arab', 'ukr_Cyrl', 'umb_Latn', 'urd_Arab', 'uzn_Latn', 'vec_Latn', 'vie_Latn', 'war_Latn', 'wol_Latn', 'xho_Latn', 'ydd_Hebr', 'yor_Latn', 'yue_Hant', 'zho_Hans', 'zho_Hant', 'zul_Latn']
-# fmt: on
+FAIRSEQ_LANGUAGE_CODES = ['ace_Arab', 'ace_Latn', 'acm_Arab', 'acq_Arab', 'aeb_Arab', 'afr_Latn', 'ajp_Arab', 'aka_Latn', 'amh_Ethi', 'apc_Arab', 'arb_Arab', 'ars_Arab', 'ary_Arab', 'arz_Arab', 'asm_Beng', 'ast_Latn', 'awa_Deva', 'ayr_Latn', 'azb_Arab', 'azj_Latn', 'bak_Cyrl', 'bam_Latn', 'ban_Latn', 'bel_Cyrl', 'bem_Latn', 'ben_Beng', 'bho_Deva', 'bjn_Arab', 'bjn_Latn', 'bod_Tibt', 'bos_Latn', 'bug_Latn', 'bul_Cyrl', 'cat_Latn', 'ceb_Latn', 'ces_Latn', 'cjk_Latn', 'ckb_Arab', 'crh_Latn', 'cym_Latn', 'dan_Latn', 'deu_Latn', 'dik_Latn', 'dyu_Latn', 'dzo_Tibt', 'ell_Grek', 'eng_Latn', 'epo_Latn', 'est_Latn', 'eus_Latn', 'ewe_Latn', 'fao_Latn', 'pes_Arab', 'fij_Latn', 'fin_Latn', 'fon_Latn', 'fra_Latn', 'fur_Latn', 'fuv_Latn', 'gla_Latn', 'gle_Latn', 'glg_Latn', 'grn_Latn', 'guj_Gujr', 'hat_Latn', 'hau_Latn', 'heb_Hebr', 'hin_Deva', 'hne_Deva', 'hrv_Latn', 'hun_Latn', 'hye_Armn', 'ibo_Latn', 'ilo_Latn', 'ind_Latn', 'isl_Latn', 'ita_Latn', 'jav_Latn', 'jpn_Jpan', 'kab_Latn', 'kac_Latn', 'kam_Latn', 'kan_Knda', 'kas_Arab', 'kas_Deva', 'kat_Geor', 'knc_Arab', 'knc_Latn', 'kaz_Cyrl', 'kbp_Latn', 'kea_Latn', 'khm_Khmr', 'kik_Latn', 'kin_Latn', 'kir_Cyrl', 'kmb_Latn', 'kon_Latn', 'kor_Hang', 'kmr_Latn', 'lao_Laoo', 'lvs_Latn', 'lij_Latn', 'lim_Latn', 'lin_Latn', 'lit_Latn', 'lmo_Latn', 'ltg_Latn', 'ltz_Latn', 'lua_Latn', 'lug_Latn', 'luo_Latn', 'lus_Latn', 'mag_Deva', 'mai_Deva', 'mal_Mlym', 'mar_Deva', 'min_Latn', 'mkd_Cyrl', 'plt_Latn', 'mlt_Latn', 'mni_Beng', 'khk_Cyrl', 'mos_Latn', 'mri_Latn', 'zsm_Latn', 'mya_Mymr', 'nld_Latn', 'nno_Latn', 'nob_Latn', 'npi_Deva', 'nso_Latn', 'nus_Latn', 'nya_Latn', 'oci_Latn', 'gaz_Latn', 'ory_Orya', 'pag_Latn', 'pan_Guru', 'pap_Latn', 'pol_Latn', 'por_Latn', 'prs_Arab', 'pbt_Arab', 'quy_Latn', 'ron_Latn', 'run_Latn', 'rus_Cyrl', 'sag_Latn', 'san_Deva', 'sat_Beng', 'scn_Latn', 'shn_Mymr', 'sin_Sinh', 'slk_Latn', 'slv_Latn', 'smo_Latn', 'sna_Latn', 'snd_Arab', 'som_Latn', 'sot_Latn', 'spa_Latn', 'als_Latn', 'srd_Latn', 'srp_Cyrl', 'ssw_Latn', 'sun_Latn', 'swe_Latn', 'swh_Latn', 'szl_Latn', 'tam_Taml', 'tat_Cyrl', 'tel_Telu', 'tgk_Cyrl', 'tgl_Latn', 'tha_Thai', 'tir_Ethi', 'taq_Latn', 'taq_Tfng', 'tpi_Latn', 'tsn_Latn', 'tso_Latn', 'tuk_Latn', 'tum_Latn', 'tur_Latn', 'twi_Latn', 'tzm_Tfng', 'uig_Arab', 'ukr_Cyrl', 'umb_Latn', 'urd_Arab', 'uzn_Latn', 'vec_Latn', 'vie_Latn', 'war_Latn', 'wol_Latn', 'xho_Latn', 'ydd_Hebr', 'yor_Latn', 'yue_Hant', 'zho_Hans', 'zho_Hant', 'zul_Latn']  # fmt: skip
 
 
 class NllbTokenizerFast(PreTrainedTokenizerFast):