README.md

metadata

license: cc-by-nc-4.0
library_name: transformers
tags:
  - mergekit
  - merge
  - alpaca
  - mistral
  - not-for-all-audiences
  - nsfw
model-index:
  - name: IceSakeV6RP-7b
    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: 50.33
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=icefog72/IceSakeV6RP-7b
          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: 30.39
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=icefog72/IceSakeV6RP-7b
          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: 5.66
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=icefog72/IceSakeV6RP-7b
          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: 5.48
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=icefog72/IceSakeV6RP-7b
          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: 11.63
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=icefog72/IceSakeV6RP-7b
          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: 23.26
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=icefog72/IceSakeV6RP-7b
          name: Open LLM Leaderboard

IceSakeV6RP-7b

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

Merge Details

This is model only for merges!

Merge Method

This model was merged using the TIES merge method using G:\FModels\Mistroll-7B-v2.2 as a base.

Models Merged

The following models were included in the merge:

• IceCoffeeRP-7b
• kuno-royale-v3-7b
• IceSakeV4RP-7b
  • IceSakeV2RP-7b
  • IceSakeV3RP-7b
    • coven_7b_128k_orpo_alpha
    • IceSakeV2RP-7b
      • OmniBeagle-7B_StrangeMerges_44
      • IceSakeV0RP-7b

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: H:\FModels\kuno-royale-v3-7b
    parameters:
      density: 0.8
      weight: 0.5
  - model: G:\FModels\IceSakeV4RP-7b
    parameters:
      density: 0.5
      weight: 0.5
  - model: F:\FModels\IceCoffeeRP-7b
    parameters:
      density: 0.5
      weight: 0.7
merge_method: ties
base_model: G:\FModels\Mistroll-7B-v2.2
parameters:
  normalize: true
  int8_mask: true
dtype: float16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	21.13
IFEval (0-Shot)	50.33
BBH (3-Shot)	30.39
MATH Lvl 5 (4-Shot)	5.66
GPQA (0-shot)	5.48
MuSR (0-shot)	11.63
MMLU-PRO (5-shot)	23.26