README.md

metadata

tags:
  - mergekit
  - merge
base_model:
  - uukuguy/speechless-instruct-mistral-7b-v0.2
  - SanjiWatsuki/Kunoichi-DPO-v2-7B
model-index:
  - name: Proto-Harpy-Spark-v0.1-7B
    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: 43.33
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Jacoby746/Proto-Harpy-Spark-v0.1-7B
          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: 26.91
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Jacoby746/Proto-Harpy-Spark-v0.1-7B
          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: 5.82
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Jacoby746/Proto-Harpy-Spark-v0.1-7B
          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: 7.38
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Jacoby746/Proto-Harpy-Spark-v0.1-7B
          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=Jacoby746/Proto-Harpy-Spark-v0.1-7B
          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: 22.99
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Jacoby746/Proto-Harpy-Spark-v0.1-7B
          name: Open LLM Leaderboard
license: apache-2.0

merge

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:

• ../models/uukuguy_speechless-instruct-mistral-7b-v0.2
• ../models/SanjiWatsuki_Kunoichi-DPO-v2-7B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: ../models/SanjiWatsuki_Kunoichi-DPO-v2-7B
  - model: ../models/uukuguy_speechless-instruct-mistral-7b-v0.2
merge_method: slerp
base_model: ../models/uukuguy_speechless-instruct-mistral-7b-v0.2
parameters:
  t:
    - value: [0.5, 0.1, 0.4, 0.3, 0.5, 0.7, 0.5, 0.7, 0.2, 0.1, 0.4] 
  embed_slerp: true 
dtype: float16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	19.79
IFEval (0-Shot)	43.33
BBH (3-Shot)	26.91
MATH Lvl 5 (4-Shot)	5.82
GPQA (0-shot)	7.38
MuSR (0-shot)	12.29
MMLU-PRO (5-shot)	22.99