Update README.md
Browse files
README.md
CHANGED
|
@@ -104,7 +104,18 @@ How may I assist you today?
|
|
| 104 |
*Prompt Example on Temp 0.5
|
| 105 |
|
| 106 |
## Evaluation
|
| 107 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 108 |
|
| 109 |
## Disclaimer
|
| 110 |
We must inform users that despite our best efforts in data cleansing, the possibility of uncensored content slipping through cannot be entirely ruled out.
|
|
|
|
| 104 |
*Prompt Example on Temp 0.5
|
| 105 |
|
| 106 |
## Evaluation
|
| 107 |
+
|
| 108 |
+
|
| 109 |
+
|
| 110 |
+
| Metric | Value |
|
| 111 |
+
|-----------------------|---------------------------|
|
| 112 |
+
| Avg. | 74.21 |
|
| 113 |
+
| ARC (25-shot) | 70.82 |
|
| 114 |
+
| HellaSwag (10-shot) | 88.63 |
|
| 115 |
+
| MMLU (5-shot) | 66.2|
|
| 116 |
+
| TruthfulQA (0-shot) | 71.95 |
|
| 117 |
+
| Winogrande (5-shot) | 83.5 |
|
| 118 |
+
| GSM8K (5-shot) | 64.14 |
|
| 119 |
|
| 120 |
## Disclaimer
|
| 121 |
We must inform users that despite our best efforts in data cleansing, the possibility of uncensored content slipping through cannot be entirely ruled out.
|