40.3 MB

Ctrl+K

1 contributor

History: 23 commits

ModerRAS

Document training lineage

f2ec095 3 days ago

colab
Add Codex Colab training workflow 6 days ago
data
Clean special code parsing 5 days ago
datasets
Train thin anime filename parser 3 days ago
docs
Train thin anime filename parser 3 days ago
exports
Train thin anime filename parser 3 days ago
.gitattributes

1.57 kB
重新训练模型，补充训练结果 7 days ago
.gitignore

247 Bytes
Polish Hugging Face repository docs 4 days ago
.gitmodules

118 Bytes
Add AniFileBERT model and training project 11 days ago
AGENTS.md

7.55 kB
Remove stale diagnostics reports 4 days ago
ANDROID.md

3.44 kB
Polish Hugging Face repository docs 4 days ago
MAINTENANCE.md

5.9 kB
Train thin anime filename parser 3 days ago
README.md

11.1 kB
Document training lineage 3 days ago
benchmark_inference.py

7.69 kB
Train thin anime filename parser 3 days ago
benchmark_results.json

981 Bytes
Train thin anime filename parser 3 days ago
build_repair_focus_dataset.py

11.5 kB
Train thin anime filename parser 3 days ago
case_metrics.json

52.7 kB
Train thin anime filename parser 3 days ago
check_f1.py

1.42 kB
Add AniFileBERT model and training project 11 days ago
colab_client.py

6.75 kB
Add Codex Colab training workflow 6 days ago
colab_train.py

19.2 kB
Add Codex Colab training workflow 6 days ago
colab_worker.py

16.9 kB
Add Codex Colab training workflow 6 days ago
config.json

1.39 kB
Improve anime filename parser model 5 days ago
config.py

2.04 kB
重建词表：从632K dmhy_weak.jsonl统计频率取top8000，覆盖96.2% 7 days ago
convert_to_char_dataset.py

7.59 kB
Add character-token DMHY training path 7 days ago
data_generator.py

29.4 kB
Add AniFileBERT model and training project 11 days ago
dataset.py

12.2 kB
Improve anime filename parser model 5 days ago
diagnose_pipeline.py

35.9 kB
Improve anime filename parser model 5 days ago
dmhy_dataset.py

47.4 kB
Train thin anime filename parser 3 days ago
evaluate_parser_cases.py

7.47 kB
Train thin anime filename parser 3 days ago
export_onnx.py

4.99 kB
Polish Hugging Face repository docs 4 days ago
inference.py

44.4 kB
Train thin anime filename parser 3 days ago
label_repairs.py

17.6 kB
Clean special code parsing 5 days ago
llm_labeler.py

10.3 kB
完成整个数据集的整理 7 days ago
mix_datasets.py

2.32 kB
Add AniFileBERT model and training project 11 days ago
model.py

2.04 kB
Add AniFileBERT model and training project 11 days ago
model.safetensors

19.1 MB
xet

Train thin anime filename parser 3 days ago
onnx_inference.py

4.45 kB
Train thin anime filename parser 3 days ago
parse_eval_metrics.json

34 kB
Train thin anime filename parser 3 days ago
pyproject.toml

851 Bytes
Improve anime filename parser model 5 days ago
relabel_dataset_from_filenames.py

6.19 kB
Improve anime filename parser model 5 days ago
repair_dataset_labels.py

4 kB
Improve anime filename parser model 5 days ago
requirements.txt

232 Bytes
Improve anime filename parser model 5 days ago
run_metadata.json

592 Bytes
Train thin anime filename parser 3 days ago
semantic_labeler.py

12 kB
完成整个数据集的整理 7 days ago
smoke_test.py

1.62 kB
Add AniFileBERT model and training project 11 days ago
test_train_small.py

3.79 kB
Add AniFileBERT model and training project 11 days ago
tokenizer.py

14.2 kB
Improve anime filename parser model 5 days ago
tokenizer_config.json

951 Bytes
Improve anime filename parser model 5 days ago
train.py

29.1 kB
Train thin anime filename parser 3 days ago
trainer_eval_metrics.json

301 Bytes
Train thin anime filename parser 3 days ago
training_args.bin
Detected Pickle imports (10)
- "transformers.trainer_utils.IntervalStrategy",
- "accelerate.utils.dataclasses.DistributedType",
- "transformers.trainer_utils.SaveStrategy",
- "transformers.trainer_utils.SchedulerType",
- "transformers.trainer_utils.HubStrategy",
- "transformers.training_args.OptimizerNames",
- "accelerate.state.PartialState",
- "torch.device",
- "transformers.trainer_pt_utils.AcceleratorConfig",
- "transformers.training_args.TrainingArguments"
How to fix it?
5.27 kB
xet

Train thin anime filename parser 3 days ago

Detected Pickle imports (10)