---
license: mit
language:
- en
pipeline_tag: text-generation
---

## Atomight V2.5 1.7B
Most **powerful and capable model** in the current and *newest* Atomight family variant. 

Other details for this model soon. Wait for further information and details. 

## Self-reported benchmark results

These results are self-reported for `NovatasticRoScript/Atomight-V2.5-1.7B`.

| Benchmark | Metric | Score |
|---|---:|---:|
| ARC-Challenge | Accuracy (normalized) | 43.00 |
| HellaSwag | Accuracy (normalized) | 60.43 |
| WinoGrande | Accuracy | 61.09 |
| TruthfulQA MC2 | Accuracy | 45.89 |
| HumanEval | Pass@1 | 40.24 |
| MBPP | Pass@1 | 42.80 |
| MMLU | Accuracy | 55.68 |

### Notes
- GSM8K is tracked separately in Hugging Face evaluation results.
- The other scores are listed here as self-reported model card results.