saishf's picture
Adding Evaluation Results (#3)
b1ef652 verified
metadata
license: cc-by-nc-4.0
library_name: transformers
tags:
  - mergekit
  - merge
base_model:
  - saishf/Ortho-SOVL-8B-L3
  - saishf/SOVLish-Maid-L3-8B
  - saishf/Merge-Mayhem-L3-V2.1
  - saishf/Merge-Mayhem-L3-V2
model-index:
  - name: Llama4Some-SOVL-4x8B-L3-V1
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: AI2 Reasoning Challenge (25-Shot)
          type: ai2_arc
          config: ARC-Challenge
          split: test
          args:
            num_few_shot: 25
        metrics:
          - type: acc_norm
            value: 61.95
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Llama4Some-SOVL-4x8B-L3-V1
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: HellaSwag (10-Shot)
          type: hellaswag
          split: validation
          args:
            num_few_shot: 10
        metrics:
          - type: acc_norm
            value: 79.38
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Llama4Some-SOVL-4x8B-L3-V1
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MMLU (5-Shot)
          type: cais/mmlu
          config: all
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 65.49
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Llama4Some-SOVL-4x8B-L3-V1
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: TruthfulQA (0-shot)
          type: truthful_qa
          config: multiple_choice
          split: validation
          args:
            num_few_shot: 0
        metrics:
          - type: mc2
            value: 51.48
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Llama4Some-SOVL-4x8B-L3-V1
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: Winogrande (5-shot)
          type: winogrande
          config: winogrande_xl
          split: validation
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 75.69
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Llama4Some-SOVL-4x8B-L3-V1
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: GSM8k (5-shot)
          type: gsm8k
          config: main
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 66.57
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=saishf/Llama4Some-SOVL-4x8B-L3-V1
          name: Open LLM Leaderboard

merge

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

Merge Details

This model is a merge of all of my SOVL models, in the hopes to create the most unhinged and wild model possible. But in Mixtral fashion!

It may be insane, it may be incoherent. I can't load it :3

Merge Method

This model was merged using the Mixture Of Experts method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

base_model: saishf/Ortho-SOVL-8B-L3
gate_mode: random
dtype: bfloat16
experts:
  - source_model: saishf/Ortho-SOVL-8B-L3
  - source_model: saishf/SOVLish-Maid-L3-8B
  - source_model: saishf/Merge-Mayhem-L3-V2.1
  - source_model: saishf/Merge-Mayhem-L3-V2

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric Value
Avg. 66.76
AI2 Reasoning Challenge (25-Shot) 61.95
HellaSwag (10-Shot) 79.38
MMLU (5-Shot) 65.49
TruthfulQA (0-shot) 51.48
Winogrande (5-shot) 75.69
GSM8k (5-shot) 66.57