Instructions to use NbAiLabArchive/test_w7 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use NbAiLabArchive/test_w7 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="NbAiLabArchive/test_w7")# Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("NbAiLabArchive/test_w7") model = AutoModelForMaskedLM.from_pretrained("NbAiLabArchive/test_w7") - Notebooks
- Google Colab
- Kaggle
first push
Browse files
run_w7.sh
CHANGED
|
@@ -3,7 +3,8 @@
|
|
| 3 |
--model_type="roberta" \
|
| 4 |
--config_name="./" \
|
| 5 |
--tokenizer_name="./" \
|
| 6 |
-
--
|
|
|
|
| 7 |
--max_seq_length="128" \
|
| 8 |
--weight_decay="0.01" \
|
| 9 |
--per_device_train_batch_size="128" \
|
|
|
|
| 3 |
--model_type="roberta" \
|
| 4 |
--config_name="./" \
|
| 5 |
--tokenizer_name="./" \
|
| 6 |
+
--train_file="/mnt/disks/flaxdisk/corpus/train-shard-0001-of-0001.json" \
|
| 7 |
+
--validation_file="/mnt/disks/flaxdisk/corpus/validation-shard-0001-of-0001.json" \
|
| 8 |
--max_seq_length="128" \
|
| 9 |
--weight_decay="0.01" \
|
| 10 |
--per_device_train_batch_size="128" \
|