README.md

metadata

license: cc-by-nc-4.0
library_name: transformers
tags:
  - mergekit
  - merge
base_model:
  - jsfs11/TurdusTrixBeagle-DARETIES-7B
  - senseable/garten2-7b
model-index:
  - name: Westgate
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: AI2 Reasoning Challenge (25-Shot)
          type: ai2_arc
          config: ARC-Challenge
          split: test
          args:
            num_few_shot: 25
        metrics:
          - type: acc_norm
            value: 71.42
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nlpguy/Westgate
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: HellaSwag (10-Shot)
          type: hellaswag
          split: validation
          args:
            num_few_shot: 10
        metrics:
          - type: acc_norm
            value: 88.14
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nlpguy/Westgate
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MMLU (5-Shot)
          type: cais/mmlu
          config: all
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 65.11
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nlpguy/Westgate
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: TruthfulQA (0-shot)
          type: truthful_qa
          config: multiple_choice
          split: validation
          args:
            num_few_shot: 0
        metrics:
          - type: mc2
            value: 62.59
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nlpguy/Westgate
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: Winogrande (5-shot)
          type: winogrande
          config: winogrande_xl
          split: validation
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 85.71
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nlpguy/Westgate
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: GSM8k (5-shot)
          type: gsm8k
          config: main
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 70.05
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=nlpguy/Westgate
          name: Open LLM Leaderboard

merged

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:

• jsfs11/TurdusTrixBeagle-DARETIES-7B
• senseable/garten2-7b

Configuration

The following YAML configuration was used to produce this model:

base_model:
  model:
    path: senseable/garten2-7b
dtype: float16
merge_method: slerp
parameters:
  t:
  - value: [0.0, 0.3, 0.5, 0.7, 1.0]
slices:
- sources:
  - layer_range: [0, 32]
    model:
      model:
        path: jsfs11/TurdusTrixBeagle-DARETIES-7B
  - layer_range: [0, 32]
    model:
      model:
        path: senseable/garten2-7b

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	73.84
AI2 Reasoning Challenge (25-Shot)	71.42
HellaSwag (10-Shot)	88.14
MMLU (5-Shot)	65.11
TruthfulQA (0-shot)	62.59
Winogrande (5-shot)	85.71
GSM8k (5-shot)	70.05