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
- 6
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
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