README.md

metadata

library_name: transformers
tags:
  - mergekit
  - merge
base_model:
  - sometimesanotion/Lamarck-14B-v0.7
  - sometimesanotion/Qwenvergence-14B-v12-Prose-DS
model-index:
  - name: Lamarckvergence-14B
    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: 76.56
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=suayptalha/Lamarckvergence-14B
          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: 50.33
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=suayptalha/Lamarckvergence-14B
          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: 54
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=suayptalha/Lamarckvergence-14B
          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: 15.1
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=suayptalha/Lamarckvergence-14B
          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: 16.34
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=suayptalha/Lamarckvergence-14B
          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: 47.59
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=suayptalha/Lamarckvergence-14B
          name: Open LLM Leaderboard
license: apache-2.0
language:
  - en
pipeline_tag: text-generation

Merged Model

This model is currently ranked #1 among the models up to 15B parameters and #56 among all models on the Open LLM Leaderboard.

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:

• sometimesanotion/Lamarck-14B-v0.7
• sometimesanotion/Qwenvergence-14B-v12-Prose-DS

Configuration

The following YAML configuration was used to produce this model:

base_model: sometimesanotion/Lamarck-14B-v0.7
dtype: bfloat16
merge_method: slerp
parameters:
  t:
  - filter: self_attn
    value: [0.0, 0.5, 0.3, 0.7, 1.0]
  - filter: mlp
    value: [1.0, 0.5, 0.7, 0.3, 0.0]
  - value: 0.5
slices:
- sources:
  - layer_range: [0, 48]
    model: sometimesanotion/Lamarck-14B-v0.7
  - layer_range: [0, 48]
    model: sometimesanotion/Qwenvergence-14B-v12-Prose-DS

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	43.32
IFEval (0-Shot)	76.56
BBH (3-Shot)	50.33
MATH Lvl 5 (4-Shot)	54.00
GPQA (0-shot)	15.10
MuSR (0-shot)	16.34
MMLU-PRO (5-shot)	47.59