README.md

metadata

library_name: transformers
tags:
  - mergekit
  - merge
base_model:
  - wanlige/li-14b-v0.4
  - sthenno-com/miscii-14b-0218
model-index:
  - name: li-14b-v0.4-slerp0.1
    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: 79.23
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=wanlige/li-14b-v0.4-slerp0.1
          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: 50.88
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=wanlige/li-14b-v0.4-slerp0.1
          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: 53.32
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=wanlige/li-14b-v0.4-slerp0.1
          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: 14.54
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=wanlige/li-14b-v0.4-slerp0.1
          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: 11.75
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=wanlige/li-14b-v0.4-slerp0.1
          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: 47.71
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=wanlige/li-14b-v0.4-slerp0.1
          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 SLERP merge method.

Models Merged

The following models were included in the merge:

• wanlige/li-14b-v0.4
• sthenno-com/miscii-14b-0218

Configuration

The following YAML configuration was used to produce this model:

# merge_method:        arcee_fusion
# base_model:          wanlige/li-14b-v0.4
# tokenizer_source:    base
# parameters:
#   int8_mask:         true
#   normalize:         true
#   rescale:           false
# dtype:               bfloat16
# out_dtype:           bfloat16
# models:
#   - model:           sthenno-com/miscii-14b-0218

base_model:          wanlige/li-14b-v0.4
merge_method:        slerp
tokenizer_source:    base
dtype:               float32
out_dtype:           bfloat16
parameters:
  t:
    - filter:        self_attn
      value:         [ 0.00, 0.50, 0.30, 0.70, 1.00 ]
    - filter:        mlp
      value:         [ 1.00, 0.50, 0.70, 0.30, 0.00 ]
    - value:         [ 0.00, 0.00, 0.00, 0.00, 0.04, 0.08, 0.12, 0.16, 0.24, 0.32, 0.40, 0.48, 0.56, 0.64, 0.72, 0.72, 0.72, 0.72, 0.72, 0.72, 0.72, 0.72, 0.64, 0.56, 0.48 ]
slices:
  - sources:
      - model:       wanlige/li-14b-v0.4
        layer_range: [ 0, 48 ]
      - model:       sthenno-com/miscii-14b-0218
        layer_range: [ 0, 48 ]

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	42.91
IFEval (0-Shot)	79.23
BBH (3-Shot)	50.88
MATH Lvl 5 (4-Shot)	53.32
GPQA (0-shot)	14.54
MuSR (0-shot)	11.75
MMLU-PRO (5-shot)	47.71