README.md

metadata

library_name: transformers
tags:
  - mergekit
  - merge
base_model:
  - suayptalha/Luminis-phi-4
  - bunnycore/Phi-4-RR-Shoup
model-index:
  - name: Phi-4-Sce-exp-v0.1
    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: 65.95
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Phi-4-Sce-exp-v0.1
          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: 56.07
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Phi-4-Sce-exp-v0.1
          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: 48.11
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Phi-4-Sce-exp-v0.1
          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: 11.41
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Phi-4-Sce-exp-v0.1
          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: 15.11
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Phi-4-Sce-exp-v0.1
          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: 49.14
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Phi-4-Sce-exp-v0.1
          name: Open LLM Leaderboard

merge

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

Merge Details

Merge Method

This model was merged using the SCE merge method using suayptalha/Luminis-phi-4 as a base.

Models Merged

The following models were included in the merge:

• bunnycore/Phi-4-RR-Shoup

Configuration

The following YAML configuration was used to produce this model:

models:
  # Pivot model
  - model: suayptalha/Luminis-phi-4
  # Target models
  - model: bunnycore/Phi-4-RR-Shoup
merge_method: sce
base_model: suayptalha/Luminis-phi-4
parameters:
  select_topk: 1.5
dtype: bfloat16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	40.97
IFEval (0-Shot)	65.95
BBH (3-Shot)	56.07
MATH Lvl 5 (4-Shot)	48.11
GPQA (0-shot)	11.41
MuSR (0-shot)	15.11
MMLU-PRO (5-shot)	49.14