Grafted-Wind-Elementals-2x70B
A MoE merge of:
Why use one 70B when you could use two?
I really liked this model's writing ability. Just need a few more 3090s, right?
License: Non-commercial research use only.
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 76.21 |
| AI2 Reasoning Challenge (25-Shot) | 73.38 |
| HellaSwag (10-Shot) | 89.08 |
| MMLU (5-Shot) | 75.79 |
| TruthfulQA (0-shot) | 65.57 |
| Winogrande (5-shot) | 84.85 |
| GSM8k (5-shot) | 68.61 |
- Downloads last month
- 4
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for lodrick-the-lafted/Grafted-Wind-Elementals-2x70B
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard73.380
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard89.080
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard75.790
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard65.570
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard84.850
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard68.610