README.md

metadata

license: mit
library_name: transformers
tags:
  - mergekit
  - merge
base_model:
  - prithivMLmods/Phi-4-o1
  - bunnycore/Phi-4-14B-1M-RRP-v1-lora
  - microsoft/phi-4
model-index:
  - name: Phi4-RP-o1
    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: 2.2
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Phi4-RP-o1
          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: 51.59
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Phi4-RP-o1
          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: 36.03
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Phi4-RP-o1
          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: 16.44
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Phi4-RP-o1
          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: 19.18
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Phi4-RP-o1
          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: 45.67
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/Phi4-RP-o1
          name: Open LLM Leaderboard

merge

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

Merge Method

This model was merged using the Passthrough merge method using prithivMLmods/Phi-4-o1 + bunnycore/Phi-4-14B-1M-RRP-v1-lora as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

base_model: prithivMLmods/Phi-4-o1+bunnycore/Phi-4-14B-1M-RRP-v1-lora
dtype: bfloat16
merge_method: passthrough
models:
  - model: prithivMLmods/Phi-4-o1+bunnycore/Phi-4-14B-1M-RRP-v1-lora

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	28.52
IFEval (0-Shot)	2.20
BBH (3-Shot)	51.59
MATH Lvl 5 (4-Shot)	36.03
GPQA (0-shot)	16.44
MuSR (0-shot)	19.18
MMLU-PRO (5-shot)	45.67