metadata

language:
  - en
  - zh
license: apache-2.0
library_name: transformers
tags:
  - mergekit
  - merge
base_model:
  - sthenno/tempesthenno-0126-ckpt150
  - ToastyPigeon/Qwen2.5-14B-Instruct-1M-Unalign
  - huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated
  - SicariusSicariiStuff/Impish_QWEN_14B-1M
  - sthenno-com/miscii-14b-1225
  - sthenno/tempesthenno-nuslerp-0124
  - huihui-ai/Qwen2.5-14B-Instruct-1M-abliterated
model-index:
  - name: miscii-14b-1M-0128
    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: 41.81
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=win10/miscii-14b-1M-0128
          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: 37.27
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=win10/miscii-14b-1M-0128
          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: 40.18
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=win10/miscii-14b-1M-0128
          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: 17.67
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=win10/miscii-14b-1M-0128
          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: 28.75
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=win10/miscii-14b-1M-0128
          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: 38.79
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=win10/miscii-14b-1M-0128
          name: Open LLM Leaderboard

merge

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

Your support = more models

My Ko-fi page (Click here)

Merge Details

Merge Method

This model was merged using the SCE merge method using sthenno-com/miscii-14b-1225 as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

merge_method: sce
models:
  - model: sthenno/tempesthenno-nuslerp-0124
  - model: huihui-ai/Qwen2.5-14B-Instruct-1M-abliterated
  - model: sthenno/tempesthenno-0126-ckpt150
  - model: huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated
  - model: SicariusSicariiStuff/Impish_QWEN_14B-1M
  - model: ToastyPigeon/Qwen2.5-14B-Instruct-1M-Unalign
base_model: sthenno-com/miscii-14b-1225
parameters:
  select_topk: 1.0
dtype: bfloat16
normalize: true

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	34.08
IFEval (0-Shot)	41.81
BBH (3-Shot)	37.27
MATH Lvl 5 (4-Shot)	40.18
GPQA (0-shot)	17.67
MuSR (0-shot)	28.75
MMLU-PRO (5-shot)	38.79