merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the Model Stock merge method using anthracite-org/magnum-v2-4b as a base.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
merge_method: model_stock
models:
- model: Magpie-Align/MagpieLM-4B-Chat-v0.1
parameters:
weight: 1.0
- model: FourOhFour/Deedlit_4B
parameters:
weight: 1.0
base_model: anthracite-org/magnum-v2-4b
dtype: bfloat16
normalize: true
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 16.19 |
| IFEval (0-Shot) | 42.30 |
| BBH (3-Shot) | 19.29 |
| MATH Lvl 5 (4-Shot) | 4.00 |
| GPQA (0-shot) | 4.47 |
| MuSR (0-shot) | 9.93 |
| MMLU-PRO (5-shot) | 17.17 |
- Downloads last month
- 3
Model tree for Nexesenex/Nemotron_W_4b_MagLight_0.1
Merge model
this model
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard42.300
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard19.290
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard4.000
- acc_norm on GPQA (0-shot)Open LLM Leaderboard4.470
- acc_norm on MuSR (0-shot)Open LLM Leaderboard9.930
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard17.170