merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the TIES merge method using prithivMLmods/Phi-4-Empathetic + ngxson/LoRA-phi-4-abliterated 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: prithivMLmods/Phi-4-Empathetic+ngxson/LoRA-phi-4-abliterated
  - model: prithivMLmods/Phi-4-o1+ngxson/LoRA-phi-4-abliterated
    parameters:
      density: 0.75
      weight: 0.75
  - model: prithivMLmods/Phi-4-QwQ+ngxson/LoRA-phi-4-abliterated
    parameters:
      density: 0.50
      weight: 0.50
  - model: prithivMLmods/Phi-4-Math-IO+ngxson/LoRA-phi-4-abliterated
    parameters:
      density: 0.30
      weight: 0.30
merge_method: ties
base_model: prithivMLmods/Phi-4-Empathetic+ngxson/LoRA-phi-4-abliterated
parameters:
  normalize: true
dytpe: float32
Downloads last month
72
Safetensors
Model size
14.7B params
Tensor type
FP16
·
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

Model tree for Sorawiz/Phi-4-Base

Collection including Sorawiz/Phi-4-Base