README.md

metadata

library_name: transformers
tags:
  - mergekit
  - merge
base_model:
  - bunnycore/FuseQwQen-7B
  - prithivMLmods/QwQ-LCoT-7B-Instruct
  - qingy2024/UwU-7B-Instruct
  - fblgit/cybertron-v4-qw7B-UNAMGS
model-index:
  - name: FwF-Qwen-7B-0.2
    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: 44.79
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co./spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/FwF-Qwen-7B-0.2
          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: 37.67
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co./spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/FwF-Qwen-7B-0.2
          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: 22.36
            name: exact match
        source:
          url: >-
            https://huggingface.co./spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/FwF-Qwen-7B-0.2
          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: 5.37
            name: acc_norm
        source:
          url: >-
            https://huggingface.co./spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/FwF-Qwen-7B-0.2
          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: 12.29
            name: acc_norm
        source:
          url: >-
            https://huggingface.co./spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/FwF-Qwen-7B-0.2
          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: 37.58
            name: accuracy
        source:
          url: >-
            https://huggingface.co./spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/FwF-Qwen-7B-0.2
          name: Open LLM Leaderboard

FwF-Qwen-7B-0.2 is a large language model that is created by merging three other models. These models are specialized for reasoning, long thinking, roleplay, and general tasks, respectively.

Merge Details

Merge Method

This model was merged using the linear merge method.

Models Merged

The following models were included in the merge:

• bunnycore/FuseQwQen-7B
• prithivMLmods/QwQ-LCoT-7B-Instruct
• qingy2024/UwU-7B-Instruct
• fblgit/cybertron-v4-qw7B-UNAMGS

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: bunnycore/FuseQwQen-7B
    parameters:
      weight: 0.9
  - model: qingy2024/UwU-7B-Instruct
    parameters:
      weight: 0.9
  - model: prithivMLmods/QwQ-LCoT-7B-Instruct
    parameters:
      weight: 0.5
  - model: fblgit/cybertron-v4-qw7B-UNAMGS
    parameters:
      weight: 0.5
merge_method: linear
normalize: false
int8_mask: true
dtype: bfloat16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	26.68
IFEval (0-Shot)	44.79
BBH (3-Shot)	37.67
MATH Lvl 5 (4-Shot)	22.36
GPQA (0-shot)	5.37
MuSR (0-shot)	12.29
MMLU-PRO (5-shot)	37.58