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: CultriX/SeQwence-14Bv1
- model: CultriX/Qwestion-14B
merge_method: slerp
base_model: CultriX/SeQwence-14Bv1
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. | 38.94 |
| IFEval (0-Shot) | 71.19 |
| BBH (3-Shot) | 47.39 |
| MATH Lvl 5 (4-Shot) | 33.16 |
| GPQA (0-shot) | 15.32 |
| MuSR (0-shot) | 17.81 |
| MMLU-PRO (5-shot) | 48.78 |
- Downloads last month
- 28
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for allknowingroger/QwenSlerp5-14B
Merge model
this model
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard71.190
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard47.390
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard33.160
- acc_norm on GPQA (0-shot)Open LLM Leaderboard15.320
- acc_norm on MuSR (0-shot)Open LLM Leaderboard17.810
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard48.780