Instructions to use microsoft/deberta-v3-small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/deberta-v3-small with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="microsoft/deberta-v3-small")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("microsoft/deberta-v3-small", dtype="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -54,10 +54,10 @@ python -m torch.distributed.launch --nproc_per_node=${num_gpus} \
|
|
| 54 |
--do_eval \
|
| 55 |
--evaluation_strategy steps \
|
| 56 |
--max_seq_length 256 \
|
| 57 |
-
--warmup_steps
|
| 58 |
--per_device_train_batch_size ${batch_size} \
|
| 59 |
--learning_rate 3e-5 \
|
| 60 |
-
--num_train_epochs
|
| 61 |
--output_dir $output_dir \
|
| 62 |
--overwrite_output_dir \
|
| 63 |
--logging_steps 1000 \
|
|
|
|
| 54 |
--do_eval \
|
| 55 |
--evaluation_strategy steps \
|
| 56 |
--max_seq_length 256 \
|
| 57 |
+
--warmup_steps 1000 \
|
| 58 |
--per_device_train_batch_size ${batch_size} \
|
| 59 |
--learning_rate 3e-5 \
|
| 60 |
+
--num_train_epochs 3 \
|
| 61 |
--output_dir $output_dir \
|
| 62 |
--overwrite_output_dir \
|
| 63 |
--logging_steps 1000 \
|