README.md

metadata

language:
  - en
license: apache-2.0
library_name: transformers
tags:
  - mergekit
  - merge
base_model:
  - sthenno-com/miscii-14b-0218
  - wanlige/li-14b-v0.4-slerp0.1
  - wanlige/li-14b-v0.4
pipeline_tag: text-generation
model-index:
  - name: Lix-14B-v0.1
    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: 78.13
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=suayptalha/Lix-14B-v0.1
          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: 51.47
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=suayptalha/Lix-14B-v0.1
          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: 52.95
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=suayptalha/Lix-14B-v0.1
          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: 16
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=suayptalha/Lix-14B-v0.1
          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: 13.42
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=suayptalha/Lix-14B-v0.1
          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: 47.94
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=suayptalha/Lix-14B-v0.1
          name: Open LLM Leaderboard

Merged Model

This model is currently ranked #3 among the models up to 15B parameters and #59 among all models on the Open LLM Leaderboard.

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 wanlige/li-14b-v0.4 as a base.

Models Merged

The following models were included in the merge:

• sthenno-com/miscii-14b-0218
• wanlige/li-14b-v0.4-slerp0.1

Configuration

The following YAML configuration was used to produce this model:

name:                Lix-14B-v0.1
merge_method:        model_stock
base_model:          wanlige/li-14b-v0.4
tokenizer_source:    base
dtype:               bfloat16
out_dtype:           bfloat16
parameters:
  int8_mask:         true
  normalize:         true
  rescale:           false
models:
  - model:           wanlige/li-14b-v0.4-slerp0.1
  - model:           sthenno-com/miscii-14b-0218

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	43.32
IFEval (0-Shot)	78.13
BBH (3-Shot)	51.47
MATH Lvl 5 (4-Shot)	52.95
GPQA (0-shot)	16.00
MuSR (0-shot)	13.42
MMLU-PRO (5-shot)	47.94