nbeerbower's picture
Adding Evaluation Results (#1)
11246cd verified
metadata
library_name: transformers
tags:
  - mergekit
  - merge
base_model:
  - nbeerbower/mistral-nemo-gutenberg-12B-v3
  - nbeerbower/Lyra-Gutenberg-mistral-nemo-12B
  - nbeerbower/mistral-nemo-gutenberg-12B-v4
  - nbeerbower/mistral-nemo-bophades-12B
model-index:
  - name: Stella-mistral-nemo-12B-v2
    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: 32.74
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Stella-mistral-nemo-12B-v2
          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: 35.36
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Stella-mistral-nemo-12B-v2
          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: 10.42
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Stella-mistral-nemo-12B-v2
          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: 10.96
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Stella-mistral-nemo-12B-v2
          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: 14.43
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Stella-mistral-nemo-12B-v2
          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: 29.83
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Stella-mistral-nemo-12B-v2
          name: Open LLM Leaderboard

Stella-mistral-nemo-12B-v2

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 nbeerbower/mistral-nemo-bophades-12B as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
    - model: nbeerbower/Lyra-Gutenberg-mistral-nemo-12B
    - model: nbeerbower/mistral-nemo-gutenberg-12B-v4
    - model: nbeerbower/mistral-nemo-gutenberg-12B-v3
merge_method: model_stock
base_model: nbeerbower/mistral-nemo-bophades-12B
dtype: bfloat16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric Value
Avg. 22.29
IFEval (0-Shot) 32.74
BBH (3-Shot) 35.36
MATH Lvl 5 (4-Shot) 10.42
GPQA (0-shot) 10.96
MuSR (0-shot) 14.43
MMLU-PRO (5-shot) 29.83