README.md

metadata

license: llama3.2
library_name: transformers
tags:
  - mergekit
  - merge
base_model:
  - NousResearch/Hermes-3-Llama-3.2-3B
  - lunahr/Hermes-3-Llama-3.2-3B-abliterated
  - lunahr/thea-rp-3b-25r
model-index:
  - name: Llama_3.2_3b_Kermes_v1
    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: 48.52
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nexesenex/Llama_3.2_3b_Kermes_v1
          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: 21.17
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nexesenex/Llama_3.2_3b_Kermes_v1
          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: 3.1
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nexesenex/Llama_3.2_3b_Kermes_v1
          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: 3.13
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nexesenex/Llama_3.2_3b_Kermes_v1
          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: 9.31
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nexesenex/Llama_3.2_3b_Kermes_v1
          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: 17.19
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Nexesenex/Llama_3.2_3b_Kermes_v1
          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 NousResearch/Hermes-3-Llama-3.2-3B as a base.

Models Merged

The following models were included in the merge:

• lunahr/Hermes-3-Llama-3.2-3B-abliterated
• lunahr/thea-rp-3b-25r

Configuration

The following YAML configuration was used to produce this model:

merge_method: model_stock
models:
  - model: lunahr/Hermes-3-Llama-3.2-3B-abliterated
    parameters:
      weight: 1.0
  - model: lunahr/thea-rp-3b-25r
    parameters:
      weight: 1.0
base_model: NousResearch/Hermes-3-Llama-3.2-3B
dtype: float16
normalize: true

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	17.07
IFEval (0-Shot)	48.52
BBH (3-Shot)	21.17
MATH Lvl 5 (4-Shot)	3.10
GPQA (0-shot)	3.13
MuSR (0-shot)	9.31
MMLU-PRO (5-shot)	17.19