Instructions to use NbAiLab/roberta_des_128 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use NbAiLab/roberta_des_128 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="NbAiLab/roberta_des_128")# Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("NbAiLab/roberta_des_128") model = AutoModelForMaskedLM.from_pretrained("NbAiLab/roberta_des_128") - Notebooks
- Google Colab
- Kaggle
minor
Browse files- run_step1.sh +2 -1
run_step1.sh
CHANGED
|
@@ -9,7 +9,7 @@
|
|
| 9 |
--weight_decay="0.01" \
|
| 10 |
--per_device_train_batch_size="256" \
|
| 11 |
--per_device_eval_batch_size="256" \
|
| 12 |
-
--learning_rate=4e-4" \
|
| 13 |
--warmup_steps="10000" \
|
| 14 |
--overwrite_output_dir \
|
| 15 |
--num_train_epochs="1000" \
|
|
@@ -24,3 +24,4 @@
|
|
| 24 |
--static_learning_rate="True" \
|
| 25 |
--dtype="bfloat16" \
|
| 26 |
--push_to_hub
|
|
|
|
|
|
| 9 |
--weight_decay="0.01" \
|
| 10 |
--per_device_train_batch_size="256" \
|
| 11 |
--per_device_eval_batch_size="256" \
|
| 12 |
+
--learning_rate=i"4e-4" \
|
| 13 |
--warmup_steps="10000" \
|
| 14 |
--overwrite_output_dir \
|
| 15 |
--num_train_epochs="1000" \
|
|
|
|
| 24 |
--static_learning_rate="True" \
|
| 25 |
--dtype="bfloat16" \
|
| 26 |
--push_to_hub
|
| 27 |
+
|