README.md

metadata

language:
  - en
license: apache-2.0
tags:
  - mergekit
  - merge
base_model:
  - flemmingmiguel/MBX-7B-v3
  - paulml/NeuralOmniWestBeaglake-7B
  - FelixChao/Faraday-7B
  - paulml/NeuralOmniBeagleMBX-v3-7B
model-index:
  - name: Samlagast-7B-bf16
    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: 73.98
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kquant03/Samlagast-7B-bf16
          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: 89.34
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kquant03/Samlagast-7B-bf16
          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: 64.58
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kquant03/Samlagast-7B-bf16
          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: 73.9
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kquant03/Samlagast-7B-bf16
          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: 85.48
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kquant03/Samlagast-7B-bf16
          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: 67.55
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kquant03/Samlagast-7B-bf16
          name: Open LLM Leaderboard

To see what will happen.

Join our Discord!

GGUF FILES HERE

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

Merge Method

This model was merged using the task arithmetic merge method using paulml/NeuralOmniBeagleMBX-v3-7B as a base.

Models Merged

The following models were included in the merge:

• flemmingmiguel/MBX-7B-v3
• paulml/NeuralOmniWestBeaglake-7B
• FelixChao/Faraday-7B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: paulml/NeuralOmniWestBeaglake-7B
    parameters:
      weight: 1
  - model: FelixChao/Faraday-7B
    parameters:
      weight: 1
  - model: flemmingmiguel/MBX-7B-v3
    parameters:
      weight: 1
  - model: paulml/NeuralOmniBeagleMBX-v3-7B
    parameters:
      weight: 1
merge_method: task_arithmetic
base_model: paulml/NeuralOmniBeagleMBX-v3-7B
parameters:
  normalize: true
  int8_mask: true
dtype: float16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	75.81
AI2 Reasoning Challenge (25-Shot)	73.98
HellaSwag (10-Shot)	89.34
MMLU (5-Shot)	64.58
TruthfulQA (0-shot)	73.90
Winogrande (5-shot)	85.48
GSM8k (5-shot)	67.55