metadata

license: apache-2.0
library_name: transformers
tags:
  - mergekit
  - merge
base_model:
  - fblgit/cybertron-v4-qw7B-MGS
  - Tsunami-th/Tsunami-0.5x-7B-Instruct
model-index:
  - name: 3Bgeneralv2-ECE-PRYMMAL-Martial
    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: 56.77
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=brgx53/3Bgeneralv2-ECE-PRYMMAL-Martial
          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: 37.25
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=brgx53/3Bgeneralv2-ECE-PRYMMAL-Martial
          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: 30.74
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=brgx53/3Bgeneralv2-ECE-PRYMMAL-Martial
          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: 8.17
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=brgx53/3Bgeneralv2-ECE-PRYMMAL-Martial
          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: 12.79
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=brgx53/3Bgeneralv2-ECE-PRYMMAL-Martial
          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: 38.95
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=brgx53/3Bgeneralv2-ECE-PRYMMAL-Martial
          name: Open LLM Leaderboard

my-output

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

Merge Details

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:


slices:
  - sources:
      - model: fblgit/cybertron-v4-qw7B-MGS
        layer_range: [0, 28]
      - model: Tsunami-th/Tsunami-0.5x-7B-Instruct
        layer_range: [0, 28]
merge_method: slerp
base_model: Tsunami-th/Tsunami-0.5x-7B-Instruct
parameters:
  t:
    - filter: self_attn
      value: [1, 0.75, 0.5, 0.25, 0]
    - filter: mlp
      value: [0, 0.25, 0.5, 0.75, 1]
    - value: 0.5
dtype: bfloat16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	30.78
IFEval (0-Shot)	56.77
BBH (3-Shot)	37.25
MATH Lvl 5 (4-Shot)	30.74
GPQA (0-shot)	8.17
MuSR (0-shot)	12.79
MMLU-PRO (5-shot)	38.95