Instructions to use mismayil/comet-bart-ai2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mismayil/comet-bart-ai2 with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("mismayil/comet-bart-ai2") model = AutoModelForSeq2SeqLM.from_pretrained("mismayil/comet-bart-ai2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Mete Ismayil commited on
Commit ·
c920ae5
1
Parent(s): 24a4361
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,5 @@
|
|
| 1 |
---
|
| 2 |
license: afl-3.0
|
| 3 |
---
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: afl-3.0
|
| 3 |
---
|
| 4 |
+
|
| 5 |
+
This model has been trained by the original authors of the paper [(Comet-) Atomic 2020: On Symbolic and Neural Commonsense Knowledge Graphs.](https://www.semanticscholar.org/paper/COMET-ATOMIC-2020%3A-On-Symbolic-and-Neural-Knowledge-Hwang-Bhagavatula/e39503e01ebb108c6773948a24ca798cd444eb62) and has been released [here](https://storage.googleapis.com/ai2-mosaic-public/projects/mosaic-kgs/comet-atomic_2020_BART.zip). Original codebase for training is [here](https://github.com/allenai/comet-atomic-2020)
|