README.md

metadata

language:
  - en
license: mit
library_name: transformers
tags:
  - mergekit
  - merge
base_model:
  - gz987/qwen2.5-7b-cabs-v0.3
  - gz987/qwen2.5-7b-cabs-v0.4
  - gz987/qwen2.5-7b-cabs-v0.1
  - gz987/qwen2.5-7b-cabs-v0.2
pipeline_tag: text-generation
model-index:
  - name: Clarus-7B-v0.2
    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: 76.79
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=suayptalha/Clarus-7B-v0.2
          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: 36.02
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=suayptalha/Clarus-7B-v0.2
          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: 48.56
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=suayptalha/Clarus-7B-v0.2
          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: 6.94
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=suayptalha/Clarus-7B-v0.2
          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: 15.07
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=suayptalha/Clarus-7B-v0.2
          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: 37.78
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=suayptalha/Clarus-7B-v0.2
          name: Open LLM Leaderboard

Merged Model

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

Merge Details

Merge Method

This model was merged using the Model Stock merge method using gz987/qwen2.5-7b-cabs-v0.3 as a base.

Models Merged

The following models were included in the merge:

• gz987/qwen2.5-7b-cabs-v0.4
• gz987/qwen2.5-7b-cabs-v0.1
• gz987/qwen2.5-7b-cabs-v0.2

Configuration

The following YAML configuration was used to produce this model:

name:                Clarus-7B-v0.2
merge_method:        model_stock
base_model:          gz987/qwen2.5-7b-cabs-v0.3
tokenizer_source:    base
dtype:               bfloat16
out_dtype:           bfloat16
parameters:
  int8_mask:         true
  normalize:         true
  rescale:           false
models:
  - model:           gz987/qwen2.5-7b-cabs-v0.4
  - model:           gz987/qwen2.5-7b-cabs-v0.2
  - model:           gz987/qwen2.5-7b-cabs-v0.1

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	36.86
IFEval (0-Shot)	76.79
BBH (3-Shot)	36.02
MATH Lvl 5 (4-Shot)	48.56
GPQA (0-shot)	6.94
MuSR (0-shot)	15.07
MMLU-PRO (5-shot)	37.78