metadata

library_name: transformers
tags:
  - mergekit
  - merge
base_model:
  - DreadPoor/Heart_Stolen-8B-Model_Stock
  - bunnycore/Llama-3.1-8B-TitanFusion
  - arcee-ai/Llama-3.1-SuperNova-Lite
  - DreadPoor/Aspire-8B-model_stock
  - vicgalle/Configurable-Llama-3.1-8B-Instruct
  - mlabonne/Hermes-3-Llama-3.1-8B-lorablated
model-index:
  - name: Llama-3.1-8B-TitanFusion-v3
    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: 48.1
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Llama-3.1-8B-TitanFusion-v3
          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: 32.07
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Llama-3.1-8B-TitanFusion-v3
          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: 12.99
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Llama-3.1-8B-TitanFusion-v3
          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: 7.83
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Llama-3.1-8B-TitanFusion-v3
          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: 11.94
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Llama-3.1-8B-TitanFusion-v3
          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: 31.17
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Llama-3.1-8B-TitanFusion-v3
          name: Open LLM Leaderboard

merge

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 bunnycore/Llama-3.1-8B-TitanFusion 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: DreadPoor/Aspire-8B-model_stock
  - model: arcee-ai/Llama-3.1-SuperNova-Lite
  - model: mlabonne/Hermes-3-Llama-3.1-8B-lorablated
  - model: bunnycore/Llama-3.1-8B-TitanFusion
  - model: vicgalle/Configurable-Llama-3.1-8B-Instruct
  - model: DreadPoor/Heart_Stolen-8B-Model_Stock
merge_method: model_stock
base_model: bunnycore/Llama-3.1-8B-TitanFusion
normalize: false
int8_mask: true
dtype: bfloat16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	24.02
IFEval (0-Shot)	48.10
BBH (3-Shot)	32.07
MATH Lvl 5 (4-Shot)	12.99
GPQA (0-shot)	7.83
MuSR (0-shot)	11.94
MMLU-PRO (5-shot)	31.17