README.md

metadata

library_name: transformers
tags:
  - mergekit
  - merge
base_model:
  - Qwen/Qwen2.5-14B-Instruct
  - qingy2019/Qwen2.5-Math-14B-Instruct
  - Qwen/Qwen2.5-14B
model-index:
  - name: Qwen2.5-Ultimate-14B-Instruct
    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: 39.38
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=qingy2019/Qwen2.5-Ultimate-14B-Instruct
          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: 40.58
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=qingy2019/Qwen2.5-Ultimate-14B-Instruct
          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: 28.02
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=qingy2019/Qwen2.5-Ultimate-14B-Instruct
          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: 14.21
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=qingy2019/Qwen2.5-Ultimate-14B-Instruct
          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: 9.89
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=qingy2019/Qwen2.5-Ultimate-14B-Instruct
          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: 43.66
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=qingy2019/Qwen2.5-Ultimate-14B-Instruct
          name: Open LLM Leaderboard

Qwen2.5 Ultimate 14B Instruct

Merged using rombodawg's method and using the first iteration of my Qwen2.5 Math 14B Instruct.

Merge Details

Merge Method

This model was merged using the TIES merge method using Qwen/Qwen2.5-14B as a base.

Models Merged

The following models were included in the merge:

• Qwen/Qwen2.5-14B-Instruct
• qingy2019/Qwen2.5-Math-14B-Instruct

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: qingy2019/Qwen2.5-Math-14B-Instruct
    parameters:
      weight: 1
      density: 1
  - model: Qwen/Qwen2.5-14B-Instruct
    parameters:
      weight: 1
      density: 1
merge_method: ties
base_model: Qwen/Qwen2.5-14B
parameters:
  weight: 1
  density: 1
  normalize: true
  int8_mask: true
tokenizer_source: qingy2019/Qwen2.5-Math-14B-Instruct
dtype: bfloat16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	29.29
IFEval (0-Shot)	39.38
BBH (3-Shot)	40.58
MATH Lvl 5 (4-Shot)	28.02
GPQA (0-shot)	14.21
MuSR (0-shot)	9.89
MMLU-PRO (5-shot)	43.66