README.md

metadata

library_name: transformers
tags:
  - mergekit
  - merge
base_model:
  - Weyaxi/Einstein-v6.1-Llama3-8B
  - flammenai/Mahou-1.3-llama3-8B
  - Danielbrdz/Barcenas-Llama3-8b-ORPO
model-index:
  - name: llama3-8B-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: 41.23
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Naveenpoliasetty/llama3-8B-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: 30.87
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Naveenpoliasetty/llama3-8B-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: 7.1
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Naveenpoliasetty/llama3-8B-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: 5.37
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Naveenpoliasetty/llama3-8B-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: 9.18
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Naveenpoliasetty/llama3-8B-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: 30.42
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Naveenpoliasetty/llama3-8B-V2
          name: Open LLM Leaderboard

merged_model

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

Merge Details

Merge Method

This model was merged using the linear merge method.

Models Merged

The following models were included in the merge:

• Weyaxi/Einstein-v6.1-Llama3-8B
• flammenai/Mahou-1.3-llama3-8B
• Danielbrdz/Barcenas-Llama3-8b-ORPO

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: flammenai/Mahou-1.3-llama3-8B
    parameters:
      weight: 1.0
  - model: Danielbrdz/Barcenas-Llama3-8b-ORPO
    parameters:
      weight: 1.0
  - model: Weyaxi/Einstein-v6.1-Llama3-8B
    parameters:
      weight: 1.0
merge_method: linear
tokenizer_source: union
dtype: float16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	20.69
IFEval (0-Shot)	41.23
BBH (3-Shot)	30.87
MATH Lvl 5 (4-Shot)	7.10
GPQA (0-shot)	5.37
MuSR (0-shot)	9.18
MMLU-PRO (5-shot)	30.42