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: sam-paech/Delirium-v1
- model: DreadPoor/Emu_Eggs-9B-Model_Stock
merge_method: slerp
base_model: sam-paech/Delirium-v1
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. | 33.50 |
| IFEval (0-Shot) | 72.81 |
| BBH (3-Shot) | 42.54 |
| MATH Lvl 5 (4-Shot) | 16.54 |
| GPQA (0-shot) | 13.65 |
| MuSR (0-shot) | 19.49 |
| MMLU-PRO (5-shot) | 35.99 |
- Downloads last month
- 64
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 allknowingroger/Gemmaslerp2-9B
Base model
unsloth/gemma-2-9b-it
Finetuned
sam-paech/Delirium-v1
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard72.810
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard42.540
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard16.540
- acc_norm on GPQA (0-shot)Open LLM Leaderboard13.650
- acc_norm on MuSR (0-shot)Open LLM Leaderboard19.490
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard35.990