README.md

metadata

license: llama3
library_name: transformers
tags:
  - mergekit
  - merge
base_model:
  - ResplendentAI/Aura_Uncensored_l3_8B
  - meta-llama/Meta-Llama-3-8B-Instruct
  - ResplendentAI/Kei_Llama3_8B
  - Undi95/Llama-3-Unholy-8B
  - vicgalle/Roleplay-Llama-3-8B
model-index:
  - name: L3-RP_io
    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: 63.05
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Azazelle/L3-RP_io
          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: 79.86
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Azazelle/L3-RP_io
          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: 67.92
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Azazelle/L3-RP_io
          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: 52.9
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Azazelle/L3-RP_io
          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=Azazelle/L3-RP_io
          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: 67.85
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Azazelle/L3-RP_io
          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 TIES merge method using meta-llama/Meta-Llama-3-8B-Instruct as a base.

Models Merged

The following models were included in the merge:

• ResplendentAI/Aura_Uncensored_l3_8B
• ResplendentAI/Kei_Llama3_8B
• Undi95/Llama-3-Unholy-8B
• vicgalle/Roleplay-Llama-3-8B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: ResplendentAI/Aura_Uncensored_l3_8B
    parameters:
      density: 0.4
      weight: 0.4
  - model: ResplendentAI/Kei_Llama3_8B
    parameters:
      density: 0.4
      weight: 0.4
  - model: Undi95/Llama-3-Unholy-8B
    parameters:
      density: 0.3
      weight: 0.2
  - model: vicgalle/Roleplay-Llama-3-8B
    parameters:
      density: 0.3
      weight: 0.3
merge_method: ties
base_model: meta-llama/Meta-Llama-3-8B-Instruct
parameters:
  rescale: true
  normalize: false
  int8_mask: true
dtype: bfloat16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	67.88
AI2 Reasoning Challenge (25-Shot)	63.05
HellaSwag (10-Shot)	79.86
MMLU (5-Shot)	67.92
TruthfulQA (0-shot)	52.90
Winogrande (5-shot)	75.69
GSM8k (5-shot)	67.85