Source: Q-bert/MetaMath-Cybertron-Starling ✦ Quant: TheBloke/MetaMath-Cybertron-Starling-AWQ ✦ Merge Q-bert/MetaMath-Cybertron and berkeley-nest/Starling-LM-7B-alpha using slerp merge
This model costs approximately $0.0013 to run on Replicate, or 769 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.
This model runs on Nvidia A40 GPU hardware. Predictions typically complete within 3 seconds.
Merge Q-bert/MetaMath-Cybertron and berkeley-nest/Starling-LM-7B-alpha using slerp merge.
You can use ChatML format.
Detailed results can be found Here
| Metric | Value |
|---|---|
| Avg. | 71.35 |
| ARC (25-shot) | 67.75 |
| HellaSwag (10-shot) | 86.23 |
| MMLU (5-shot) | 65.24 |
| TruthfulQA (0-shot) | 55.94 |
| Winogrande (5-shot) | 81.45 |
| GSM8K (5-shot) | 71.49 |