README.md

metadata

library_name: transformers
tags:
  - mergekit
  - merge
base_model:
  - Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ
  - Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ
  - bunnycore/Phi-4-rp-v1-lora
  - bunnycore/Phi-4-Model-Stock-v2
model-index:
  - name: Phi-4-Model-Stock-v3
    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: 59.12
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Phi-4-Model-Stock-v3
          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: 52.78
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Phi-4-Model-Stock-v3
          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: 46.9
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Phi-4-Model-Stock-v3
          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: 5.26
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Phi-4-Model-Stock-v3
          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: 11.18
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Phi-4-Model-Stock-v3
          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: 48.68
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=bunnycore/Phi-4-Model-Stock-v3
          name: Open LLM Leaderboard

merge

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

Merge Details

<|im_start|>system<|im_sep|> {system_message}<|im_end|> <|im_start|>user<|im_sep|> {prompt}<|im_end|> <|im_start|>assistant<|im_sep|>

Merge Method

This model was merged using the Model Stock merge method using Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ as a base.

Models Merged

The following models were included in the merge:

• Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ + bunnycore/Phi-4-rp-v1-lora
• bunnycore/Phi-4-Model-Stock-v2

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: bunnycore/Phi-4-Model-Stock-v2
  - model: Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ
  - model: Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ+bunnycore/Phi-4-rp-v1-lora
base_model: Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ
merge_method: model_stock
parameters:
  normalize: true
dtype: bfloat16
tokenizer_source: unsloth/phi-4

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	37.32
IFEval (0-Shot)	59.12
BBH (3-Shot)	52.78
MATH Lvl 5 (4-Shot)	46.90
GPQA (0-shot)	5.26
MuSR (0-shot)	11.18
MMLU-PRO (5-shot)	48.68