Model | ARC | HellaSwag | MMLU | TruthfulQA | Winogrande | GSM8K |
---|---|---|---|---|---|---|
mera-mix-4x7B | 65.7 | 84.73 | Error: File does not exist | 51.03 | 79.48 | 66.34 |
Task | Version | Metric | Value | Stderr | |
---|---|---|---|---|---|
arc_challenge | 1 | acc,none | 0.62 | ||
acc_stderr,none | 0.01 | ||||
acc_norm,none | 0.66 |