Update README.md
Browse files
README.md
CHANGED
@@ -118,7 +118,7 @@ Trained on a DGX cluster with 8 A100 80GB GPUs for ~12 hours. Using Deepspeed +
|
|
118 |
|
119 |
Results on common sense reasoning benchmarks
|
120 |
|
121 |
-
|
122 |
| Model | BoolQ | PIQA | HellaSwag | WinoGrande | ARC-e | ARC-c | OBQA | Avg. |
|
123 |
|:--------------------------|:--------:|:--------:|:---------:|:----------:|:--------:|:--------:|:--------:|:--------:|
|
124 |
| GPT4All-J 6B v1.0 | 73.4 | 74.8 | 63.4 | 64.7 | 54.9 | 36.0 | 40.2 | 58.2 |
|
@@ -155,5 +155,5 @@ Results on common sense reasoning benchmarks
|
|
155 |
| GPT4-x-Vicuna-13b | 81.3 | 75.0 | 75.2 | 65.0 | 58.7 | 43.9 | 43.6 | 62.2 |
|
156 |
| Falcon 7b | 73.6 | **80.7** | 76.3 | 67.3 | 71.0 | 43.3 | 44.4 | 65.2 |
|
157 |
| text-davinci-003 | 88.1 | 83.8 | 83.4 | 75.8 | 83.9 | 63.9 | 51.0 | 75.7 |
|
158 |
-
|
159 |
|
|
|
118 |
|
119 |
Results on common sense reasoning benchmarks
|
120 |
|
121 |
+
|
122 |
| Model | BoolQ | PIQA | HellaSwag | WinoGrande | ARC-e | ARC-c | OBQA | Avg. |
|
123 |
|:--------------------------|:--------:|:--------:|:---------:|:----------:|:--------:|:--------:|:--------:|:--------:|
|
124 |
| GPT4All-J 6B v1.0 | 73.4 | 74.8 | 63.4 | 64.7 | 54.9 | 36.0 | 40.2 | 58.2 |
|
|
|
155 |
| GPT4-x-Vicuna-13b | 81.3 | 75.0 | 75.2 | 65.0 | 58.7 | 43.9 | 43.6 | 62.2 |
|
156 |
| Falcon 7b | 73.6 | **80.7** | 76.3 | 67.3 | 71.0 | 43.3 | 44.4 | 65.2 |
|
157 |
| text-davinci-003 | 88.1 | 83.8 | 83.4 | 75.8 | 83.9 | 63.9 | 51.0 | 75.7 |
|
158 |
+
|
159 |
|