Instructions to use NbAiLab/roberta_jan_128_ncc with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use NbAiLab/roberta_jan_128_ncc with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="NbAiLab/roberta_jan_128_ncc")# Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("NbAiLab/roberta_jan_128_ncc") model = AutoModelForMaskedLM.from_pretrained("NbAiLab/roberta_jan_128_ncc") - Notebooks
- Google Colab
- Kaggle
before training starts
Browse files- run_128.sh +1 -0
run_128.sh
CHANGED
|
@@ -4,6 +4,7 @@ python run_mlm_flax.py \
|
|
| 4 |
--config_name="roberta-base" \
|
| 5 |
--tokenizer_name="NbAiLab/nb-roberta-base" \
|
| 6 |
--dataset_name="NbAiLab/NCC" \
|
|
|
|
| 7 |
--max_seq_length="128" \
|
| 8 |
--weight_decay="0.01" \
|
| 9 |
--per_device_train_batch_size="232" \
|
|
|
|
| 4 |
--config_name="roberta-base" \
|
| 5 |
--tokenizer_name="NbAiLab/nb-roberta-base" \
|
| 6 |
--dataset_name="NbAiLab/NCC" \
|
| 7 |
+
--cache_dir="/mnt/disks/flaxdisk/cache/" \
|
| 8 |
--max_seq_length="128" \
|
| 9 |
--weight_decay="0.01" \
|
| 10 |
--per_device_train_batch_size="232" \
|