README.md

metadata

license: apache-2.0
tags:
  - merge
  - mergekit
  - lazymergekit
model-index:
  - name: SmolLM2-1.7-Persona
    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: 54.65
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/SmolLM2-1.7-Persona
          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: 11.2
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/SmolLM2-1.7-Persona
          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: 4
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/SmolLM2-1.7-Persona
          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: 1.79
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/SmolLM2-1.7-Persona
          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: 3.03
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/SmolLM2-1.7-Persona
          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: 10.82
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/SmolLM2-1.7-Persona
          name: Open LLM Leaderboard

SmolLM2-1.7-Persona

SmolLM2-1.7-Persona is a merge of the following models using mergekit:

🧩 Configuration

base_model: HuggingFaceTB/SmolLM2-1.7B-Instruct+bunnycore/SmolLM2-1.7B-persona-lora
dtype: bfloat16
merge_method: passthrough
models:
  - model: HuggingFaceTB/SmolLM2-1.7B-Instruct+bunnycore/SmolLM2-1.7B-persona-lora

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	14.25
IFEval (0-Shot)	54.65
BBH (3-Shot)	11.20
MATH Lvl 5 (4-Shot)	4.00
GPQA (0-shot)	1.79
MuSR (0-shot)	3.03
MMLU-PRO (5-shot)	10.82