merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the SLERP merge method.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
models:
- model: Saxo/Linkbricks-Horizon-AI-Korean-Superb-27B
- model: jwang2373/UW-SBEL-ChronoGemma-27b-it
merge_method: slerp
base_model: Saxo/Linkbricks-Horizon-AI-Korean-Superb-27B
dtype: bfloat16
parameters:
t: [0, 0.5, 1, 0.5, 0] # V shaped curve: Hermes for input & output, WizardMath in the middle layers
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 36.20 |
| IFEval (0-Shot) | 70.86 |
| BBH (3-Shot) | 50.10 |
| MATH Lvl 5 (4-Shot) | 23.72 |
| GPQA (0-shot) | 16.11 |
| MuSR (0-shot) | 16.05 |
| MMLU-PRO (5-shot) | 40.36 |
- Downloads last month
- 5
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for hotmailuser/Gemma2Crono-27B
Merge model
this model
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard70.860
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard50.100
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard23.720
- acc_norm on GPQA (0-shot)Open LLM Leaderboard16.110
- acc_norm on MuSR (0-shot)Open LLM Leaderboard16.050
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard40.360