README.md

metadata

language:
  - en
license: llama3.2
library_name: transformers
tags:
  - mergekit
  - merge
base_model:
  - Rombo-Org/Rombo-LLM-V2.7-llama-3.2-3b
  - unsloth/Llama-3.2-3B
  - Triangle104/Hermes3-R1-Llama3.2-3b
model-index:
  - name: RomboHermes3-R1-Llama3.2-3b
    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: 30.07
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/RomboHermes3-R1-Llama3.2-3b
          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: 19.09
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/RomboHermes3-R1-Llama3.2-3b
          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: 8.16
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/RomboHermes3-R1-Llama3.2-3b
          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: 4.47
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/RomboHermes3-R1-Llama3.2-3b
          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: 4.41
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/RomboHermes3-R1-Llama3.2-3b
          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: 21.75
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Triangle104/RomboHermes3-R1-Llama3.2-3b
          name: Open LLM Leaderboard

Merge

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

Quant: https://huggingface.co/Triangle104/RomboHermes3-R1-Llama3.2-3b-Q4_K_M-GGUF

Merge Method

This model was merged using the TIES merge method using unsloth/Llama-3.2-3B as a base.

Models Merged

The following models were included in the merge:

• Rombo-Org/Rombo-LLM-V2.7-llama-3.2-3b
• Triangle104/Hermes3-R1-Llama3.2-3b

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Rombo-Org/Rombo-LLM-V2.7-llama-3.2-3b
    parameters:
      density: 1
      weight: 1
  - model: Triangle104/Hermes3-R1-Llama3.2-3b
    parameters:
      density: 1
      weight: 1
merge_method: ties
base_model: unsloth/Llama-3.2-3B
parameters:
  normalize: true
  int8_mask: true
dtype: float16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	14.66
IFEval (0-Shot)	30.07
BBH (3-Shot)	19.09
MATH Lvl 5 (4-Shot)	8.16
GPQA (0-shot)	4.47
MuSR (0-shot)	4.41
MMLU-PRO (5-shot)	21.75