Update README.md
Browse files
README.md
CHANGED
|
@@ -70,11 +70,34 @@ or
|
|
| 70 |
|
| 71 |
### Response:
|
| 72 |
<leave a newline blank for model to respond>
|
|
|
|
| 73 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 74 |
```
|
| 75 |
|
| 76 |
## Benchmark Results
|
| 77 |
-
|
|
|
|
|
|
|
| 78 |
|
| 79 |
## Resources for Applied Use Cases:
|
| 80 |
For an example of a back and forth chatbot using huggingface transformers and discord, check out: https://github.com/teknium1/alpaca-discord
|
|
|
|
| 70 |
|
| 71 |
### Response:
|
| 72 |
<leave a newline blank for model to respond>
|
| 73 |
+
```
|
| 74 |
|
| 75 |
+
AGIEval
|
| 76 |
+
```
|
| 77 |
+
| Task |Version| Metric |Value | |Stderr|
|
| 78 |
+
|------------------------------|------:|--------|-----:|---|-----:|
|
| 79 |
+
|agieval_aqua_rat | 0|acc |0.2520|± |0.0273|
|
| 80 |
+
| | |acc_norm|0.2402|± |0.0269|
|
| 81 |
+
|agieval_logiqa_en | 0|acc |0.2796|± |0.0176|
|
| 82 |
+
| | |acc_norm|0.3241|± |0.0184|
|
| 83 |
+
|agieval_lsat_ar | 0|acc |0.2478|± |0.0285|
|
| 84 |
+
| | |acc_norm|0.2348|± |0.0280|
|
| 85 |
+
|agieval_lsat_lr | 0|acc |0.2843|± |0.0200|
|
| 86 |
+
| | |acc_norm|0.2765|± |0.0198|
|
| 87 |
+
|agieval_lsat_rc | 0|acc |0.3271|± |0.0287|
|
| 88 |
+
| | |acc_norm|0.3011|± |0.0280|
|
| 89 |
+
|agieval_sat_en | 0|acc |0.4660|± |0.0348|
|
| 90 |
+
| | |acc_norm|0.4223|± |0.0345|
|
| 91 |
+
|agieval_sat_en_without_passage| 0|acc |0.3738|± |0.0338|
|
| 92 |
+
| | |acc_norm|0.3447|± |0.0332|
|
| 93 |
+
|agieval_sat_math | 0|acc |0.2500|± |0.0293|
|
| 94 |
+
| | |acc_norm|0.2364|± |0.0287|
|
| 95 |
```
|
| 96 |
|
| 97 |
## Benchmark Results
|
| 98 |
+
|
| 99 |
+
|
| 100 |
+
|
| 101 |
|
| 102 |
## Resources for Applied Use Cases:
|
| 103 |
For an example of a back and forth chatbot using huggingface transformers and discord, check out: https://github.com/teknium1/alpaca-discord
|