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: zelk12/MT3-IMA-gemma-2-9B
- model: zelk12/MT3-BMMGMU-gemma-2-9B
merge_method: slerp
base_model: zelk12/MT3-IMA-gemma-2-9B
dtype: bfloat16
parameters:
t: 0.5
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 32.18 |
| IFEval (0-Shot) | 77.86 |
| BBH (3-Shot) | 44.25 |
| MATH Lvl 5 (4-Shot) | 9.44 |
| GPQA (0-shot) | 12.64 |
| MuSR (0-shot) | 11.90 |
| MMLU-PRO (5-shot) | 36.96 |
- Downloads last month
- 11
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 zelk12/MT3-gemma-2-9B
Merge model
this model
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard77.860
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard44.250
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard9.440
- acc_norm on GPQA (0-shot)Open LLM Leaderboard12.640
- acc_norm on MuSR (0-shot)Open LLM Leaderboard11.900
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard36.960