Instructions to use hsuvaskakoty/bart_temp_dm_10k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use hsuvaskakoty/bart_temp_dm_10k with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("hsuvaskakoty/bart_temp_dm_10k") model = AutoModelForSeq2SeqLM.from_pretrained("hsuvaskakoty/bart_temp_dm_10k") - Notebooks
- Google Colab
- Kaggle
Commit ·
2d07a23
1
Parent(s): 4ddf440
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,6 +1,7 @@
|
|
| 1 |
A BART-base model fine-tuned for temporal definition modelling task. The dataset comprises 10000 definition-context pairs and is organised in the following way.
|
| 2 |
|
| 3 |
Definition: \<t\> Coronavirus \<t\> is a type of virus.
|
|
|
|
| 4 |
Context :\<y\> 2022 \</y\> This year \<t\> Coronavirus \<t\> were very prudent in many countries.
|
| 5 |
|
| 6 |
The validation loss for the model is: 0.88
|
|
|
|
| 1 |
A BART-base model fine-tuned for temporal definition modelling task. The dataset comprises 10000 definition-context pairs and is organised in the following way.
|
| 2 |
|
| 3 |
Definition: \<t\> Coronavirus \<t\> is a type of virus.
|
| 4 |
+
|
| 5 |
Context :\<y\> 2022 \</y\> This year \<t\> Coronavirus \<t\> were very prudent in many countries.
|
| 6 |
|
| 7 |
The validation loss for the model is: 0.88
|