Update README.md
Browse files
README.md
CHANGED
|
@@ -57,13 +57,6 @@ Besides, be aware of the following hyper-parameters:
|
|
| 57 |
- `num_beams == 1`. In our experiments, we set beam size to 1. But we recommend you try with a larger beam size to get better responses from models.
|
| 58 |
|
| 59 |
|
| 60 |
-
## Zero-Shot Evaluation Performances
|
| 61 |
-
|
| 62 |
-
We use the [metric calculation scripts](https://github.com/yizhongw/Tk-Instruct/blob/main/src/compute_metrics.py) of [Tk-Instruct](https://github.com/yizhongw/Tk-Instruct/tree/main) (i.e., `ROUGE-L` and `Exact-Match`).
|
| 63 |
-
|
| 64 |
-
<div style="text-align:center"><img src="https://cdn-uploads.huggingface.co/production/uploads/6434a6e8ea46c009904c617e/IjeMYWLMRO_qGOOiXxemP.png" alt="performances.png" width="600"/></div>
|
| 65 |
-
|
| 66 |
-
|
| 67 |
|
| 68 |
## 🥳 Citation
|
| 69 |
|
|
|
|
| 57 |
- `num_beams == 1`. In our experiments, we set beam size to 1. But we recommend you try with a larger beam size to get better responses from models.
|
| 58 |
|
| 59 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 60 |
|
| 61 |
## 🥳 Citation
|
| 62 |
|