README.md

---
license: mit
library_name: transformers
tags:
- mergekit
- merge
- phi4
base_model:
- unsloth/phi-4
- bunnycore/Phi-4-Avg
- prithivMLmods/Phi-4-Empathetic
- prithivMLmods/Phi-4-Math-IO
- prithivMLmods/Phi-4-QwQ
model-index:
- name: Phi-4-Model-Stock
  results:
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: IFEval (0-Shot)
      type: HuggingFaceH4/ifeval
      args:
        num_few_shot: 0
    metrics:
    - type: inst_level_strict_acc and prompt_level_strict_acc
      value: 68.79
      name: strict accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Phi-4-Model-Stock
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: BBH (3-Shot)
      type: BBH
      args:
        num_few_shot: 3
    metrics:
    - type: acc_norm
      value: 55.32
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Phi-4-Model-Stock
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MATH Lvl 5 (4-Shot)
      type: hendrycks/competition_math
      args:
        num_few_shot: 4
    metrics:
    - type: exact_match
      value: 38.6
      name: exact match
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Phi-4-Model-Stock
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: GPQA (0-shot)
      type: Idavidrein/gpqa
      args:
        num_few_shot: 0
    metrics:
    - type: acc_norm
      value: 13.98
      name: acc_norm
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Phi-4-Model-Stock
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MuSR (0-shot)
      type: TAUR-Lab/MuSR
      args:
        num_few_shot: 0
    metrics:
    - type: acc_norm
      value: 15.12
      name: acc_norm
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Phi-4-Model-Stock
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MMLU-PRO (5-shot)
      type: TIGER-Lab/MMLU-Pro
      config: main
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 48.54
      name: accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Phi-4-Model-Stock
      name: Open LLM Leaderboard
---
# merge

This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).

## Merge Details
### Merge Method

This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [unsloth/phi-4](https://huggingface.co/unsloth/phi-4) as a base.

### Models Merged

The following models were included in the merge:
* [bunnycore/Phi-4-Avg](https://huggingface.co/bunnycore/Phi-4-Avg)
* [prithivMLmods/Phi-4-Empathetic](https://huggingface.co/prithivMLmods/Phi-4-Empathetic)
* [prithivMLmods/Phi-4-Math-IO](https://huggingface.co/prithivMLmods/Phi-4-Math-IO)
* [prithivMLmods/Phi-4-QwQ](https://huggingface.co/prithivMLmods/Phi-4-QwQ)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: prithivMLmods/Phi-4-QwQ
  - model: bunnycore/Phi-4-Avg
  - model: prithivMLmods/Phi-4-Empathetic
  - model: prithivMLmods/Phi-4-Math-IO
base_model: unsloth/phi-4
merge_method: model_stock
parameters:
  normalize: true
dtype: bfloat16
tokenizer_source: unsloth/phi-4

```
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/bunnycore__Phi-4-Model-Stock-details)

|      Metric       |Value|
|-------------------|----:|
|Avg.               |40.06|
|IFEval (0-Shot)    |68.79|
|BBH (3-Shot)       |55.32|
|MATH Lvl 5 (4-Shot)|38.60|
|GPQA (0-shot)      |13.98|
|MuSR (0-shot)      |15.12|
|MMLU-PRO (5-shot)  |48.54|