29 lines
821 B
Markdown
29 lines
821 B
Markdown
|
---
|
||
|
|
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.
|