README.md

metadata

library_name: transformers
tags:
  - mergekit
  - merge
base_model:
  - hf-100/Llama-3-Spellbound-Instruct-8B-0.3
  - unsloth/Meta-Llama-3.1-8B
  - arcee-ai/Llama-3.1-SuperNova-Lite
  - grimjim/Llama-3-Instruct-abliteration-LoRA-8B
  - THUDM/LongWriter-llama3.1-8b
  - ResplendentAI/Smarts_Llama3
  - djuna/L3.1-Suze-Vume-2-calc
  - djuna/L3.1-ForStHS
  - Blackroot/Llama-3-8B-Abomination-LORA
model-index:
  - name: L3.1-Purosani-2-8B
    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: 49.88
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/L3.1-Purosani-2-8B
          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: 31.39
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/L3.1-Purosani-2-8B
          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: 10.12
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/L3.1-Purosani-2-8B
          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: 6.82
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/L3.1-Purosani-2-8B
          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: 8.3
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/L3.1-Purosani-2-8B
          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: 30.57
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=djuna/L3.1-Purosani-2-8B
          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 della_linear merge method using unsloth/Meta-Llama-3.1-8B as a base.

Models Merged

The following models were included in the merge:

• hf-100/Llama-3-Spellbound-Instruct-8B-0.3
• arcee-ai/Llama-3.1-SuperNova-Lite + grimjim/Llama-3-Instruct-abliteration-LoRA-8B
• THUDM/LongWriter-llama3.1-8b + ResplendentAI/Smarts_Llama3
• djuna/L3.1-Suze-Vume-2-calc
• djuna/L3.1-ForStHS + Blackroot/Llama-3-8B-Abomination-LORA

Configuration

The following YAML configuration was used to produce this model:

merge_method: della_linear
dtype: bfloat16
parameters:
  epsilon: 0.1
  lambda: 1.0
  int8_mask: true
  normalize: true
base_model: unsloth/Meta-Llama-3.1-8B
models:
  - model: arcee-ai/Llama-3.1-SuperNova-Lite+grimjim/Llama-3-Instruct-abliteration-LoRA-8B
    parameters:
      weight: 1
      density: 0.5
  - model: hf-100/Llama-3-Spellbound-Instruct-8B-0.3
    parameters:
      weight: 1
      density: 0.45
  - model: djuna/L3.1-Suze-Vume-2-calc
    parameters:
      weight: 1
      density: 0.45
  - model: THUDM/LongWriter-llama3.1-8b+ResplendentAI/Smarts_Llama3
    parameters:
      weight: 1
      density: 0.55
  - model: djuna/L3.1-ForStHS+Blackroot/Llama-3-8B-Abomination-LORA
    parameters:
      weight: 1
      density: 0.5

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	22.85
IFEval (0-Shot)	49.88
BBH (3-Shot)	31.39
MATH Lvl 5 (4-Shot)	10.12
GPQA (0-shot)	6.82
MuSR (0-shot)	8.30
MMLU-PRO (5-shot)	30.57