brgx53/3Blareneg-ECE-PRYMMAL-Martial

my-output

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

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

• jpacifico/Chocolatine-3B-Instruct-DPO-Revised
• microsoft/Phi-3.5-mini-instruct

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: jpacifico/Chocolatine-3B-Instruct-DPO-Revised
        layer_range: [0, 32]
      - model: microsoft/Phi-3.5-mini-instruct
        layer_range: [0, 32]
merge_method: slerp
base_model: microsoft/Phi-3.5-mini-instruct
parameters:
  t:
    - filter: self_attn
      value: [1, 0.75, 0.5, 0.25, 0]
    - filter: mlp
      value: [0, 0.25, 0.5, 0.75, 1]
    - value: 0.5
dtype: bfloat16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	21.23
IFEval (0-Shot)	28.76
BBH (3-Shot)	35.45
MATH Lvl 5 (4-Shot)	2.95
GPQA (0-shot)	11.30
MuSR (0-shot)	15.43
MMLU-PRO (5-shot)	33.51