Update README.md
Browse files
README.md
CHANGED
|
@@ -80,7 +80,22 @@ Minotaur was fine-tuned from the base model LLaMA 13B, please refer to its model
|
|
| 80 |
|
| 81 |
## Benchmarks
|
| 82 |
|
| 83 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 84 |
|
| 85 |
|
| 86 |
## Examples - results may vary based on temperature and other settings
|
|
|
|
| 80 |
|
| 81 |
## Benchmarks
|
| 82 |
|
| 83 |
+
hf-causal-experimental (pretrained=openaccess-ai-collective/minotaur-7b), limit: None, provide_description: False, num_fewshot: 0, batch_size: None
|
| 84 |
+
|
| 85 |
+
| Task |Version| Metric |Value | |Stderr|
|
| 86 |
+
|-------------|------:|--------|-----:|---|-----:|
|
| 87 |
+
|arc_challenge| 0|acc |0.4078|_ |0.0144|
|
| 88 |
+
| | |acc_norm|0.4292|_ |0.0145|
|
| 89 |
+
|arc_easy | 0|acc |0.7424|_ |0.0090|
|
| 90 |
+
| | |acc_norm|0.6877|_ |0.0095|
|
| 91 |
+
|boolq | 1|acc |0.7679|_ |0.0074|
|
| 92 |
+
|hellaswag | 0|acc |0.5636|_ |0.0049|
|
| 93 |
+
| | |acc_norm|0.7377|_ |0.0044|
|
| 94 |
+
|openbookqa | 0|acc |0.3540|_ |0.0214|
|
| 95 |
+
| | |acc_norm|0.4420|_ |0.0222|
|
| 96 |
+
|piqa | 0|acc |0.7878|_ |0.0095|
|
| 97 |
+
| | |acc_norm|0.7851|_ |0.0096|
|
| 98 |
+
|winogrande | 0|acc |0.7072|_ |0.0128|
|
| 99 |
|
| 100 |
|
| 101 |
## Examples - results may vary based on temperature and other settings
|