---
base_model:
- prithivMLmods/Phi-4-QwQ
- prithivMLmods/Phi-4-Math-IO
- Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ
- prithivMLmods/Phi-4-o1
- bunnycore/Phi-4-RP-V0.2
- prithivMLmods/Phi-4-Empathetic
- LightningRodLabs/Flashlight-v1.0
- mudler/LocalAI-functioncall-phi-4-v0.3
- unsloth/phi-4
library_name: transformers
tags:
- mergekit
- merge
---
# **Phi4-Super**

[Phi-4-Super finetuned] from Microsoft's Phi-4 is a state-of-the-art open model developed with a focus on responsible problem solving and advanced reasoning capabilities. Built upon a diverse blend of synthetic datasets, carefully filtered public domain websites, and high-quality academic books and Q&A datasets, Phi-4-Super ensures that small, capable models are trained with datasets of exceptional depth and precision.

Phi-4-Super adopts a robust safety post-training approach using open-source and in-house synthetic datasets. This involves a combination of SFT (Supervised Fine-Tuning) and iterative DPO (Direct Preference Optimization) techniques, ensuring helpful and harmless outputs across various safety categories.

# Merge

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

### 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:
* [prithivMLmods/Phi-4-QwQ](https://huggingface.co./prithivMLmods/Phi-4-QwQ)
* [prithivMLmods/Phi-4-Math-IO](https://huggingface.co./prithivMLmods/Phi-4-Math-IO)
* [Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ](https://huggingface.co./Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ)
* [prithivMLmods/Phi-4-o1](https://huggingface.co./prithivMLmods/Phi-4-o1)
* [bunnycore/Phi-4-RP-V0.2](https://huggingface.co./bunnycore/Phi-4-RP-V0.2)
* [prithivMLmods/Phi-4-Empathetic](https://huggingface.co./prithivMLmods/Phi-4-Empathetic)
* [LightningRodLabs/Flashlight-v1.0](https://huggingface.co./LightningRodLabs/Flashlight-v1.0)
* [mudler/LocalAI-functioncall-phi-4-v0.3](https://huggingface.co./mudler/LocalAI-functioncall-phi-4-v0.3)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: prithivMLmods/Phi-4-o1
  - model: prithivMLmods/Phi-4-Empathetic
  - model: prithivMLmods/Phi-4-Math-IO
  - model: prithivMLmods/Phi-4-QwQ
  - model: LightningRodLabs/Flashlight-v1.0
  - model: Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ
  - model: mudler/LocalAI-functioncall-phi-4-v0.3
  - model: bunnycore/Phi-4-RP-V0.2
  - model: unsloth/phi-4
merge_method: model_stock
base_model: unsloth/phi-4
parameters:
  normalize: false
  int8_mask: true
dtype: bfloat16
tokenizer_source: "unsloth/phi-4"
```