LogoS-7Bx2-MoE-13B-v0.1
Model built by @RubielLabarta using SLERP merge method. The model is release for research purposes only, commercial use is not allowed.
The LogoS is a model to experiment with the MoE method, which could significantly increase the performance of the original model. The model has 12.9B parameters.
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 77.14 |
| AI2 Reasoning Challenge (25-Shot) | 74.49 |
| HellaSwag (10-Shot) | 89.07 |
| MMLU (5-Shot) | 64.74 |
| TruthfulQA (0-shot) | 74.57 |
| Winogrande (5-shot) | 88.32 |
| GSM8k (5-shot) | 71.65 |
- Downloads last month
- 1,197
Merge of
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard74.490
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard89.070
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard64.740
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard74.570
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard88.320
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard71.650