Update README.md
Browse files
README.md
CHANGED
@@ -292,7 +292,7 @@ pipeline_tag: zero-shot-classification
|
|
292 |
|
293 |
# Model Card for DeBERTa-v3-small-tasksource-nli
|
294 |
|
295 |
-
This is [DeBERTa-v3-
|
296 |
This checkpoint has strong zero-shot validation performance on many tasks, and can be used for:
|
297 |
- Zero-shot entailment-based classification for arbitrary labels [ZS].
|
298 |
- Natural language inference [NLI]
|
@@ -344,7 +344,7 @@ trainer.train()
|
|
344 |
```
|
345 |
|
346 |
## Evaluation
|
347 |
-
This model ranked 1st among all models with the microsoft/deberta-v3-base architecture according to the IBM model recycling evaluation.
|
348 |
https://ibm.github.io/model-recycling/
|
349 |
|
350 |
### Software and training details
|
|
|
292 |
|
293 |
# Model Card for DeBERTa-v3-small-tasksource-nli
|
294 |
|
295 |
+
This is [DeBERTa-v3-small](https://hf.co/microsoft/deberta-v3-small) fine-tuned with multi-task learning on 600+ tasks of the [tasksource collection](https://github.com/sileod/tasksource/).
|
296 |
This checkpoint has strong zero-shot validation performance on many tasks, and can be used for:
|
297 |
- Zero-shot entailment-based classification for arbitrary labels [ZS].
|
298 |
- Natural language inference [NLI]
|
|
|
344 |
```
|
345 |
|
346 |
## Evaluation
|
347 |
+
This the base equivalent of this model was ranked 1st among all models with the microsoft/deberta-v3-base architecture according to the IBM model recycling evaluation.
|
348 |
https://ibm.github.io/model-recycling/
|
349 |
|
350 |
### Software and training details
|