bunnycore/Phi-3.5-mini-TitanFusion-0.1

This is a merged pre-trained language model created using the TIES merge method. It is based on the microsoft/Phi-3.5-mini-instruct model and incorporates the knowledge and capabilities of the nbeerbower/phi3.5-gutenberg-4B and ArliAI/Phi-3.5-mini-3.8B-ArliAI-RPMax-v1.1 models.

Capabilities:

• Roleplay: The model can engage in role-playing scenarios, taking on different personas and responding to prompts in a character-appropriate manner.
• Creative Writing: It can assist in creative writing tasks, such as brainstorming ideas, generating plotlines, or developing characters.
• Reasoning: The model can reason about information and draw conclusions based on the data it has been trained on.

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 microsoft/Phi-3.5-mini-instruct as a base.

Models Merged

The following models were included in the merge:

• nbeerbower/phi3.5-gutenberg-4B
• ArliAI/Phi-3.5-mini-3.8B-ArliAI-RPMax-v1.1

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: ArliAI/Phi-3.5-mini-3.8B-ArliAI-RPMax-v1.1
    parameters:
      weight: 1
  - model: nbeerbower/phi3.5-gutenberg-4B
    parameters:
      weight: 1

merge_method: ties
base_model: microsoft/Phi-3.5-mini-instruct
parameters:
  density: 1
  normalize: true
  int8_mask: true
dtype: bfloat16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	25.29
IFEval (0-Shot)	52.28
BBH (3-Shot)	35.45
MATH Lvl 5 (4-Shot)	6.19
GPQA (0-shot)	10.85
MuSR (0-shot)	15.80
MMLU-PRO (5-shot)	31.18