Instructions to use icelab/cosmicroberta with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use icelab/cosmicroberta with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="icelab/cosmicroberta")# Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("icelab/cosmicroberta") model = AutoModelForMaskedLM.from_pretrained("icelab/cosmicroberta") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -2,14 +2,14 @@
|
|
| 2 |
license: mpl-2.0
|
| 3 |
widget:
|
| 4 |
- text: "The closest planet to earth is <mask>."
|
| 5 |
-
- text: "Electrical power is
|
| 6 |
---
|
| 7 |
|
| 8 |
### CosmicRoBERTa
|
| 9 |
|
| 10 |
-
This model is a further pre-trained version of RoBERTa on a domain-specific corpus,
|
| 11 |
|
| 12 |
-
The
|
| 13 |
|
| 14 |
### BibTeX entry and citation info
|
| 15 |
|
|
|
|
| 2 |
license: mpl-2.0
|
| 3 |
widget:
|
| 4 |
- text: "The closest planet to earth is <mask>."
|
| 5 |
+
- text: "Electrical power is stored on a spacecraft with <mask>."
|
| 6 |
---
|
| 7 |
|
| 8 |
### CosmicRoBERTa
|
| 9 |
|
| 10 |
+
This model is a further pre-trained version of RoBERTa for space science on a domain-specific corpus, which includes abstracts from the NTRS library, abstracts from SCOPUS, ECSS requirements, and other sources from this domain.
|
| 11 |
|
| 12 |
+
The model performs slightly better on a subset of the CR task presented in our paper.
|
| 13 |
|
| 14 |
### BibTeX entry and citation info
|
| 15 |
|