Update README.md
Browse files
README.md
CHANGED
|
@@ -299,7 +299,6 @@ This model is suitable for long context NLI or as a backbone for reward models o
|
|
| 299 |
This checkpoint has strong zero-shot validation performance on many tasks (e.g. 70% on WNLI), and can be used for:
|
| 300 |
- Zero-shot entailment-based classification for arbitrary labels [ZS].
|
| 301 |
- Natural language inference [NLI]
|
| 302 |
-
- Hundreds of previous tasks with tasksource-adapters [TA].
|
| 303 |
- Further fine-tuning on a new task or tasksource task (classification, token classification or multiple-choice) [FT].
|
| 304 |
|
| 305 |
|
|
|
|
| 299 |
This checkpoint has strong zero-shot validation performance on many tasks (e.g. 70% on WNLI), and can be used for:
|
| 300 |
- Zero-shot entailment-based classification for arbitrary labels [ZS].
|
| 301 |
- Natural language inference [NLI]
|
|
|
|
| 302 |
- Further fine-tuning on a new task or tasksource task (classification, token classification or multiple-choice) [FT].
|
| 303 |
|
| 304 |
|