Instructions to use acul3/roberta-base-indo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use acul3/roberta-base-indo with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="acul3/roberta-base-indo")# Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("acul3/roberta-base-indo") model = AutoModelForMaskedLM.from_pretrained("acul3/roberta-base-indo", device_map="auto") - Notebooks
- Google Colab
- Kaggle
change warmup steps
Browse files
run.sh
CHANGED
|
@@ -21,7 +21,7 @@ tmux new-session -d -s my_session python3 run_mlm_flax.py \
|
|
| 21 |
--save_strategy="steps" \
|
| 22 |
--save_steps="10000" \
|
| 23 |
--save_total_limit='5' \
|
| 24 |
-
--warmup_steps="
|
| 25 |
--overwrite_output_dir \
|
| 26 |
--eval_steps="10000" \
|
| 27 |
--logging_steps="500" \
|
|
|
|
| 21 |
--save_strategy="steps" \
|
| 22 |
--save_steps="10000" \
|
| 23 |
--save_total_limit='5' \
|
| 24 |
+
--warmup_steps="30000" \
|
| 25 |
--overwrite_output_dir \
|
| 26 |
--eval_steps="10000" \
|
| 27 |
--logging_steps="500" \
|