Token Classification
Transformers
ONNX
Safetensors
English
Japanese
Chinese
bert
anime
filename-parsing
Eval Results (legacy)
Instructions to use ModerRAS/AniFileBERT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ModerRAS/AniFileBERT with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="ModerRAS/AniFileBERT")# Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("ModerRAS/AniFileBERT") model = AutoModelForTokenClassification.from_pretrained("ModerRAS/AniFileBERT") - Notebooks
- Google Colab
- Kaggle
提高训练速度并使用GPU进行训练
Browse files
config.py
CHANGED
|
@@ -34,7 +34,7 @@ class Config:
|
|
| 34 |
|
| 35 |
# System
|
| 36 |
device: str = "cpu"
|
| 37 |
-
num_workers: int =
|
| 38 |
save_dir: str = "./checkpoints"
|
| 39 |
log_interval: int = 100
|
| 40 |
|
|
|
|
| 34 |
|
| 35 |
# System
|
| 36 |
device: str = "cpu"
|
| 37 |
+
num_workers: int = 4
|
| 38 |
save_dir: str = "./checkpoints"
|
| 39 |
log_interval: int = 100
|
| 40 |
|
train.py
CHANGED
|
@@ -217,13 +217,14 @@ def main():
|
|
| 217 |
learning_rate=config.learning_rate,
|
| 218 |
weight_decay=config.weight_decay,
|
| 219 |
warmup_steps=config.warmup_steps,
|
| 220 |
-
use_cpu=
|
| 221 |
report_to="none",
|
| 222 |
save_total_limit=2,
|
| 223 |
load_best_model_at_end=True,
|
| 224 |
metric_for_best_model="f1",
|
| 225 |
greater_is_better=True,
|
| 226 |
dataloader_num_workers=config.num_workers,
|
|
|
|
| 227 |
)
|
| 228 |
|
| 229 |
# Data collator
|
|
|
|
| 217 |
learning_rate=config.learning_rate,
|
| 218 |
weight_decay=config.weight_decay,
|
| 219 |
warmup_steps=config.warmup_steps,
|
| 220 |
+
use_cpu=False,
|
| 221 |
report_to="none",
|
| 222 |
save_total_limit=2,
|
| 223 |
load_best_model_at_end=True,
|
| 224 |
metric_for_best_model="f1",
|
| 225 |
greater_is_better=True,
|
| 226 |
dataloader_num_workers=config.num_workers,
|
| 227 |
+
fp16=True
|
| 228 |
)
|
| 229 |
|
| 230 |
# Data collator
|