[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>

scripts/fsmt/fsmt-make-super-tiny-model.py

@@ -24,18 +24,19 @@
 #
 # It will be used then as "stas/tiny-wmt19-en-ru"
 
-from pathlib import Path
 import json
 import tempfile
+from pathlib import Path
 
-from transformers import FSMTTokenizer, FSMTConfig, FSMTForConditionalGeneration
+from transformers import FSMTConfig, FSMTForConditionalGeneration, FSMTTokenizer
 from transformers.models.fsmt.tokenization_fsmt import VOCAB_FILES_NAMES
 
+
 mname_tiny = "tiny-wmt19-en-ru"
 
 # Build
 
-# borrowed from a test 
+# borrowed from a test
 vocab = [ "l", "o", "w", "e", "r", "s", "t", "i", "d", "n", "w</w>", "r</w>", "t</w>", "lo", "low", "er</w>", "low</w>", "lowest</w>", "newer</w>", "wider</w>", "<unk>", ]
 vocab_tokens = dict(zip(vocab, range(len(vocab))))
 merges = ["l o 123", "lo w 1456", "e r</w> 1789", ""]
@@ -57,7 +58,7 @@ with tempfile.TemporaryDirectory() as tmpdirname:
         tgt_vocab_file=tgt_vocab_file,
         merges_file=merges_file,
     )
-    
+
 config = FSMTConfig(
     langs=['ru', 'en'],
     src_vocab_size=1000, tgt_vocab_size=1000,

scripts/fsmt/fsmt-make-tiny-model.py

@@ -27,16 +27,18 @@
 # It will be used then as "stas/tiny-wmt19-en-de"
 
 # Build
-from transformers import FSMTTokenizer, FSMTConfig, FSMTForConditionalGeneration
+from transformers import FSMTConfig, FSMTForConditionalGeneration, FSMTTokenizer
+
+
 mname = "facebook/wmt19-en-de"
 tokenizer = FSMTTokenizer.from_pretrained(mname)
 # get the correct vocab sizes, etc. from the master model
 config = FSMTConfig.from_pretrained(mname)
-config.update(dict(
-    d_model=4,
-    encoder_layers=1, decoder_layers=1,
-    encoder_ffn_dim=4, decoder_ffn_dim=4,
-    encoder_attention_heads=1, decoder_attention_heads=1))
+config.update({
+    "d_model": 4,
+    "encoder_layers": 1, "decoder_layers": 1,
+    "encoder_ffn_dim": 4, "decoder_ffn_dim": 4,
+    "encoder_attention_heads": 1, "decoder_attention_heads": 1})
 
 tiny_model = FSMTForConditionalGeneration(config)
 print(f"num of params {tiny_model.num_parameters()}")

scripts/fsmt/gen-card-allenai-wmt16.py

@@ -19,6 +19,7 @@
 import os
 from pathlib import Path
 
+
 def write_model_card(model_card_dir, src_lang, tgt_lang, model_name):
 
     texts = {

scripts/fsmt/gen-card-allenai-wmt19.py

@@ -19,6 +19,7 @@
 import os
 from pathlib import Path
 
+
 def write_model_card(model_card_dir, src_lang, tgt_lang, model_name):
 
     texts = {

scripts/fsmt/gen-card-facebook-wmt19.py

@@ -19,6 +19,7 @@
 import os
 from pathlib import Path
 
+
 def write_model_card(model_card_dir, src_lang, tgt_lang):
 
     texts = {
@@ -39,7 +40,7 @@ def write_model_card(model_card_dir, src_lang, tgt_lang):
 
     readme = f"""
 ---
-language: 
+language:
 - {src_lang}
 - {tgt_lang}
 thumbnail: