Instructions to use marksverdhei/t5-base-define with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use marksverdhei/t5-base-define with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("marksverdhei/t5-base-define") model = AutoModelForSeq2SeqLM.from_pretrained("marksverdhei/t5-base-define", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit ·
459a723
1
Parent(s): 56bb84c
Update README.md
Browse files
README.md
CHANGED
|
@@ -14,9 +14,6 @@ This model is trained to generate word definitions based on the word and a conte
|
|
| 14 |
using a subset of wordnet for all words that have an example and definition.
|
| 15 |
The model uses task prompts on the format 'define "[word]": [example sentence]'
|
| 16 |
|
| 17 |
-
To my knowledge, this is the first public model trained on a word definition task.
|
| 18 |
-
Similar work: [Zero-shot Word Sense Disambiguation using Sense Definition Embeddings](https://aclanthology.org/P19-1568.pdf)
|
| 19 |
-
|
| 20 |
This model in particular is a on-shot learner for unseen words, as it has to infer the definition by only one example
|
| 21 |
|
| 22 |
How to run:
|
|
|
|
| 14 |
using a subset of wordnet for all words that have an example and definition.
|
| 15 |
The model uses task prompts on the format 'define "[word]": [example sentence]'
|
| 16 |
|
|
|
|
|
|
|
|
|
|
| 17 |
This model in particular is a on-shot learner for unseen words, as it has to infer the definition by only one example
|
| 18 |
|
| 19 |
How to run:
|