README.md

metadata

library_name: transformers
tags:
  - mergekit
  - merge
base_model:
  - Qwen/Qwen2.5-14B-Instruct
  - Qwen/Qwen2.5-Coder-14B
  - deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
  - huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated-v2
  - tanliboy/lambda-qwen2.5-14b-dpo-test
  - SicariusSicariiStuff/Impish_QWEN_14B-1M
  - Qwen/Qwen2.5-14B
model-index:
  - name: li-14b-v0.4
    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: 81.33
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=wanlige/li-14b-v0.4
          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: 50.38
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=wanlige/li-14b-v0.4
          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: 55.74
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=wanlige/li-14b-v0.4
          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: 11.86
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=wanlige/li-14b-v0.4
          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: 16.35
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=wanlige/li-14b-v0.4
          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: 46.3
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=wanlige/li-14b-v0.4
          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 Qwen/Qwen2.5-14B-Instruct as a base.

Models Merged

The following models were included in the merge:

• Qwen/Qwen2.5-Coder-14B
• deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
• huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated-v2
• tanliboy/lambda-qwen2.5-14b-dpo-test
• SicariusSicariiStuff/Impish_QWEN_14B-1M
• Qwen/Qwen2.5-14B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-14B #logic
  - model: huihui-ai/DeepSeek-R1-Distill-Qwen-14B-abliterated-v2 #uncensored
  - model: Qwen/Qwen2.5-14B #text generation
  - model: Qwen/Qwen2.5-14B-Instruct #chat assistant
  - model: Qwen/Qwen2.5-Coder-14B #coding
  - model: SicariusSicariiStuff/Impish_QWEN_14B-1M #math
  - model: tanliboy/lambda-qwen2.5-14b-dpo-test #dpo
merge_method: model_stock
base_model: Qwen/Qwen2.5-14B-Instruct
normalize: true
int8_mask: true
dtype: bfloat16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	43.66
IFEval (0-Shot)	81.33
BBH (3-Shot)	50.38
MATH Lvl 5 (4-Shot)	55.74
GPQA (0-shot)	11.86
MuSR (0-shot)	16.35
MMLU-PRO (5-shot)	46.30