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 unsloth/phi-4 as a base.
Models Merged
The following models were included in the merge:
- bunnycore/Phi-4-Stock-RP
- Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ
- bunnycore/Phi-4-Stock-RP + bunnycore/Phi-4-RP-lora_model
- bunnycore/Phi-4-Stock-Ex
Configuration
The following YAML configuration was used to produce this model:
models:
- model: bunnycore/Phi-4-Stock-RP+bunnycore/Phi-4-RP-lora_model
- model: bunnycore/Phi-4-Stock-Ex
- model: Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ
- model: bunnycore/Phi-4-Stock-RP
base_model: unsloth/phi-4
merge_method: model_stock
parameters:
normalize: true
dtype: bfloat16
tokenizer_source: unsloth/phi-4
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 38.87 |
| IFEval (0-Shot) | 63.75 |
| BBH (3-Shot) | 54.69 |
| MATH Lvl 5 (4-Shot) | 35.88 |
| GPQA (0-shot) | 13.20 |
| MuSR (0-shot) | 17.57 |
| MMLU-PRO (5-shot) | 48.12 |
- Downloads last month
- 9
Model tree for bunnycore/Phi-4-Model-Stock-v2
Merge model
this model
Spaces using bunnycore/Phi-4-Model-Stock-v2 9
Paper for bunnycore/Phi-4-Model-Stock-v2
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard63.750
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard54.690
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard35.880
- acc_norm on GPQA (0-shot)Open LLM Leaderboard13.200
- acc_norm on MuSR (0-shot)Open LLM Leaderboard17.570
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard48.120