Update README.md
Browse files
README.md
CHANGED
@@ -304,6 +304,21 @@ This checkpoint has strong zero-shot validation performance on many tasks (e.g.
|
|
304 |
- Hundreds of previous tasks with tasksource-adapters [TA].
|
305 |
- Further fine-tuning on a new task or tasksource task (classification, token classification or multiple-choice) [FT].
|
306 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
307 |
# [ZS] Zero-shot classification pipeline
|
308 |
```python
|
309 |
from transformers import pipeline
|
|
|
304 |
- Hundreds of previous tasks with tasksource-adapters [TA].
|
305 |
- Further fine-tuning on a new task or tasksource task (classification, token classification or multiple-choice) [FT].
|
306 |
|
307 |
+
| dataset | accuracy |
|
308 |
+
|:----------------------------|----------------:|
|
309 |
+
| anli/a1 | 63.3 |
|
310 |
+
| anli/a2 | 47.2 |
|
311 |
+
| anli/a3 | 49.4 |
|
312 |
+
| nli_fever | 79.4 |
|
313 |
+
| fever-evidence-related | 99.4 |
|
314 |
+
| folio | 61.8 |
|
315 |
+
| ConTRoL-nli | 63.3 |
|
316 |
+
| cladder | 71.1 |
|
317 |
+
| zero-shot-label-nli | 74.4 |
|
318 |
+
| chatbot_arena_conversations | 72.2 |
|
319 |
+
| oasst2_pairwise_rlhf_reward | 73.9 |
|
320 |
+
| doc-nli | 90.0 |
|
321 |
+
|
322 |
# [ZS] Zero-shot classification pipeline
|
323 |
```python
|
324 |
from transformers import pipeline
|