Downloads · 30 days
667
1% of all-time downloads
BERTtime-Stories-100m-nucleus-1
nikitastheo/BERTtime-Stories-100m-nucleus-1
BERTtime-Stories-100m-nucleus-1 is a fill-mask model from nikitastheo. Use it when you need the model to fill a missing word. It is set up for transformers. The card lists the license as gpl-3.0.
This model uses the LTG-BERT architecture. The model was trained on a combination of the BabyLM Dataset, the TinyStories Dataset, and generated data, in accordance with the rules of the Stric track, and the 100M word…
All-time downloads
48.6K
Public
Repo size
836 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin418 MB · 100%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- License
- gpl-3.0
- Model type
- ltgbert
- Access
- Public
- Created
- Sep 17, 2024
- Updated
- Sep 17, 2024
- SHA
- aff0e4df
Try a prompt
Model card
From the Hugging Face model README
This model uses the LTG-BERT architecture. The model was trained on a combination of the BabyLM Dataset, the TinyStories Dataset, and generated data, in accordance with the rules of the Stric track, and the 100M word budget.
The model was trained with 128 token sequence length
Hyperparameters used and evaluation scores will follow in a subsequent update.
- Task
- Fill-Mask
- Library
- transformers
- Type
- ltgbert
- License
- gpl-3.0
- Languages
- en
- Created
- Sep 17, 2024
- Updated
- Sep 17, 2024