Model Stock: All we need is just a few fine-tuned models
Paper
•
2403.19522
•
Published
•
13
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 bunnycore/Phi-4-Model-Stock-v4 as a base.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
models:
- model: Quazim0t0/Phi4.Turn.R1Distill_v1.5.1-Tensors
- model: bunnycore/Phi-4-Model-Stock-v4
- model: bunnycore/Phi-4-ReasoningRP
merge_method: model_stock
base_model: bunnycore/Phi-4-Model-Stock-v4
parameters:
normalize: true
dtype: bfloat16
tokenizer_source: bunnycore/Phi-4-Model-Stock-v4
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 40.84 |
| IFEval (0-Shot) | 70.03 |
| BBH (3-Shot) | 55.98 |
| MATH Lvl 5 (4-Shot) | 38.07 |
| GPQA (0-shot) | 15.32 |
| MuSR (0-shot) | 16.73 |
| MMLU-PRO (5-shot) | 48.90 |
- Downloads last month
- 6
Model tree for bunnycore/Phi-4-RStock-v0.1
Merge model
this model
Paper for bunnycore/Phi-4-RStock-v0.1
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard70.030
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard55.980
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard38.070
- acc_norm on GPQA (0-shot)Open LLM Leaderboard15.320
- acc_norm on MuSR (0-shot)Open LLM Leaderboard16.730
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard48.900