This commit is contained in:
pre-commit-ci[bot] 2025-04-29 11:26:40 +00:00 committed by GitHub
commit fdfc28e21a
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
11 changed files with 18 additions and 18 deletions

View File

@ -8,21 +8,21 @@ repos:
args: ['--in-place', '--remove-unused-variables', '--remove-all-unused-imports', '--ignore-init-module-imports'] args: ['--in-place', '--remove-unused-variables', '--remove-all-unused-imports', '--ignore-init-module-imports']
- repo: https://github.com/pycqa/isort - repo: https://github.com/pycqa/isort
rev: 5.13.2 rev: 6.0.1
hooks: hooks:
- id: isort - id: isort
name: sort all imports (python) name: sort all imports (python)
args: ["--profile", "black"] # avoid conflict with black args: ["--profile", "black"] # avoid conflict with black
- repo: https://github.com/psf/black-pre-commit-mirror - repo: https://github.com/psf/black-pre-commit-mirror
rev: 24.10.0 rev: 25.1.0
hooks: hooks:
- id: black - id: black
name: black formatter name: black formatter
args: ['--line-length=120', '--target-version=py37', '--target-version=py38', '--target-version=py39','--target-version=py310'] args: ['--line-length=120', '--target-version=py37', '--target-version=py38', '--target-version=py39','--target-version=py310']
- repo: https://github.com/pre-commit/mirrors-clang-format - repo: https://github.com/pre-commit/mirrors-clang-format
rev: v19.1.5 rev: v20.1.0
hooks: hooks:
- id: clang-format - id: clang-format
name: clang formatter name: clang formatter

View File

@ -81,11 +81,11 @@ with gr.Blocks(css=CSS) as demo:
) )
with gr.Row(): with gr.Row():
btn = gr.UploadButton("📁", file_types=["file"], file_count="multiple", size="sm") btn = gr.UploadButton("📁", file_types=["file"], file_count="multiple", size="sm")
restart_btn = gr.Button(str("\u21BB"), elem_id="restart-btn", scale=1) restart_btn = gr.Button(str("\u21bb"), elem_id="restart-btn", scale=1)
txt = gr.Textbox( txt = gr.Textbox(
scale=8, scale=8,
show_label=False, show_label=False,
placeholder="Enter text and press enter, or use 📁 to upload files, click \u21BB to clear loaded files and restart chat", placeholder="Enter text and press enter, or use 📁 to upload files, click \u21bb to clear loaded files and restart chat",
container=True, container=True,
autofocus=True, autofocus=True,
) )

View File

@ -34,8 +34,8 @@ class PreTrainingDataset:
self.do_whole_word_mask = do_whole_word_mask self.do_whole_word_mask = do_whole_word_mask
self.max_predictions_per_seq = max_predictions_per_seq self.max_predictions_per_seq = max_predictions_per_seq
self.vocab_words = list(tokenizer.vocab.keys()) self.vocab_words = list(tokenizer.vocab.keys())
self.rec = re.compile("[\u4E00-\u9FA5]") self.rec = re.compile("[\u4e00-\u9fa5]")
self.whole_rec = re.compile("##[\u4E00-\u9FA5]") self.whole_rec = re.compile("##[\u4e00-\u9fa5]")
self.mlm_p = 0.15 self.mlm_p = 0.15
self.mlm_mask_p = 0.8 self.mlm_mask_p = 0.8