Commit
•
ac685a1
1
Parent(s):
1636c24
Update README.md
Browse files
README.md
CHANGED
|
@@ -67,86 +67,7 @@ print(generate_response(prompt), "\n")
|
|
| 67 |
| | |none | 0|acc_norm|0.8058|± |0.0092|
|
| 68 |
|winogrande |Yaml |none | 0|acc |0.7372|± |0.0124|
|
| 69 |
|
| 70 |
-
|
| 71 |
-
|---------------------------------------------------------------------------|------:|------:|---------:|-------:|------:|
|
| 72 |
-
|[SOLAR-math-2x10.7b](https://huggingface.co/macadeliccc/SOLAR-math-2x10.7b)| 47.2| 75.18| 64.73| 45.15| 58.07|
|
| 73 |
-
|
| 74 |
-
### AGIEval
|
| 75 |
-
| Task |Version| Metric |Value| |Stderr|
|
| 76 |
-
|------------------------------|------:|--------|----:|---|-----:|
|
| 77 |
-
|agieval_aqua_rat | 0|acc |30.31|± | 2.89|
|
| 78 |
-
| | |acc_norm|30.31|± | 2.89|
|
| 79 |
-
|agieval_logiqa_en | 0|acc |43.78|± | 1.95|
|
| 80 |
-
| | |acc_norm|43.93|± | 1.95|
|
| 81 |
-
|agieval_lsat_ar | 0|acc |21.74|± | 2.73|
|
| 82 |
-
| | |acc_norm|19.13|± | 2.60|
|
| 83 |
-
|agieval_lsat_lr | 0|acc |57.25|± | 2.19|
|
| 84 |
-
| | |acc_norm|56.47|± | 2.20|
|
| 85 |
-
|agieval_lsat_rc | 0|acc |68.77|± | 2.83|
|
| 86 |
-
| | |acc_norm|68.03|± | 2.85|
|
| 87 |
-
|agieval_sat_en | 0|acc |78.16|± | 2.89|
|
| 88 |
-
| | |acc_norm|79.13|± | 2.84|
|
| 89 |
-
|agieval_sat_en_without_passage| 0|acc |47.57|± | 3.49|
|
| 90 |
-
| | |acc_norm|44.66|± | 3.47|
|
| 91 |
-
|agieval_sat_math | 0|acc |41.36|± | 3.33|
|
| 92 |
-
| | |acc_norm|35.91|± | 3.24|
|
| 93 |
-
|
| 94 |
-
Average: 47.2%
|
| 95 |
-
|
| 96 |
-
### GPT4All
|
| 97 |
-
| Task |Version| Metric |Value| |Stderr|
|
| 98 |
-
|-------------|------:|--------|----:|---|-----:|
|
| 99 |
-
|arc_challenge| 0|acc |59.22|± | 1.44|
|
| 100 |
-
| | |acc_norm|61.43|± | 1.42|
|
| 101 |
-
|arc_easy | 0|acc |84.26|± | 0.75|
|
| 102 |
-
| | |acc_norm|83.63|± | 0.76|
|
| 103 |
-
|boolq | 1|acc |88.69|± | 0.55|
|
| 104 |
-
|hellaswag | 0|acc |65.98|± | 0.47|
|
| 105 |
-
| | |acc_norm|84.29|± | 0.36|
|
| 106 |
-
|openbookqa | 0|acc |34.20|± | 2.12|
|
| 107 |
-
| | |acc_norm|47.20|± | 2.23|
|
| 108 |
-
|piqa | 0|acc |81.83|± | 0.90|
|
| 109 |
-
| | |acc_norm|82.59|± | 0.88|
|
| 110 |
-
|winogrande | 0|acc |78.45|± | 1.16|
|
| 111 |
-
|
| 112 |
-
Average: 75.18%
|
| 113 |
-
|
| 114 |
-
### TruthfulQA
|
| 115 |
-
| Task |Version|Metric|Value| |Stderr|
|
| 116 |
-
|-------------|------:|------|----:|---|-----:|
|
| 117 |
-
|truthfulqa_mc| 1|mc1 |48.47|± | 1.75|
|
| 118 |
-
| | |mc2 |64.73|± | 1.53|
|
| 119 |
-
|
| 120 |
-
Average: 64.73%
|
| 121 |
-
|
| 122 |
-
### Bigbench
|
| 123 |
-
| Task |Version| Metric |Value| |Stderr|
|
| 124 |
-
|------------------------------------------------|------:|---------------------|----:|---|-----:|
|
| 125 |
-
|bigbench_causal_judgement | 0|multiple_choice_grade|61.05|± | 3.55|
|
| 126 |
-
|bigbench_date_understanding | 0|multiple_choice_grade|68.56|± | 2.42|
|
| 127 |
-
|bigbench_disambiguation_qa | 0|multiple_choice_grade|35.27|± | 2.98|
|
| 128 |
-
|bigbench_geometric_shapes | 0|multiple_choice_grade|31.20|± | 2.45|
|
| 129 |
-
| | |exact_str_match | 0.00|± | 0.00|
|
| 130 |
-
|bigbench_logical_deduction_five_objects | 0|multiple_choice_grade|30.00|± | 2.05|
|
| 131 |
-
|bigbench_logical_deduction_seven_objects | 0|multiple_choice_grade|23.43|± | 1.60|
|
| 132 |
-
|bigbench_logical_deduction_three_objects | 0|multiple_choice_grade|46.00|± | 2.88|
|
| 133 |
-
|bigbench_movie_recommendation | 0|multiple_choice_grade|35.60|± | 2.14|
|
| 134 |
-
|bigbench_navigate | 0|multiple_choice_grade|57.50|± | 1.56|
|
| 135 |
-
|bigbench_reasoning_about_colored_objects | 0|multiple_choice_grade|55.80|± | 1.11|
|
| 136 |
-
|bigbench_ruin_names | 0|multiple_choice_grade|45.98|± | 2.36|
|
| 137 |
-
|bigbench_salient_translation_error_detection | 0|multiple_choice_grade|40.58|± | 1.56|
|
| 138 |
-
|bigbench_snarks | 0|multiple_choice_grade|66.85|± | 3.51|
|
| 139 |
-
|bigbench_sports_understanding | 0|multiple_choice_grade|71.40|± | 1.44|
|
| 140 |
-
|bigbench_temporal_sequences | 0|multiple_choice_grade|56.40|± | 1.57|
|
| 141 |
-
|bigbench_tracking_shuffled_objects_five_objects | 0|multiple_choice_grade|24.00|± | 1.21|
|
| 142 |
-
|bigbench_tracking_shuffled_objects_seven_objects| 0|multiple_choice_grade|17.09|± | 0.90|
|
| 143 |
-
|bigbench_tracking_shuffled_objects_three_objects| 0|multiple_choice_grade|46.00|± | 2.88|
|
| 144 |
-
|
| 145 |
-
Average: 45.15%
|
| 146 |
-
|
| 147 |
-
Average score: 58.07%
|
| 148 |
-
|
| 149 |
-
Elapsed time: 04:05:27
|
| 150 |
|
| 151 |
### 📚 Citations
|
| 152 |
|
|
|
|
| 67 |
| | |none | 0|acc_norm|0.8058|± |0.0092|
|
| 68 |
|winogrande |Yaml |none | 0|acc |0.7372|± |0.0124|
|
| 69 |
|
| 70 |
+
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 71 |
|
| 72 |
### 📚 Citations
|
| 73 |
|