README.md

metadata

license: apache-2.0
tags:
  - mergekit
  - merge
datasets:
  - Intel/orca_dpo_pairs
  - NeuralNovel/Neural-Story-v1
base_model:
  - NeuralNovel/Mistral-7B-Instruct-v0.2-Neural-Story
  - NeuralNovel/Gecko-7B-v0.1-DPO
model-index:
  - name: Tiger-7b-v0.1
    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: 59.98
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NeuralNovel/Tiger-7b-v0.1
          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: 83.21
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NeuralNovel/Tiger-7b-v0.1
          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: 61.42
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NeuralNovel/Tiger-7b-v0.1
          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: 61.03
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NeuralNovel/Tiger-7b-v0.1
          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: 77.66
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NeuralNovel/Tiger-7b-v0.1
          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: 46.78
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NeuralNovel/Tiger-7b-v0.1
          name: Open LLM Leaderboard

Tiger-7b-v0.1

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

Join our Discord!

Metrics

Merge Method

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

• NeuralNovel/Mistral-7B-Instruct-v0.2-Neural-Story
• NeuralNovel/Gecko-7B-v0.1-DPO

merge

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: NeuralNovel/Mistral-7B-Instruct-v0.2-Neural-Story
        layer_range: [0, 32]
      - model: NeuralNovel/Gecko-7B-v0.1-DPO
        layer_range: [0, 32]
merge_method: slerp
base_model: NeuralNovel/Mistral-7B-Instruct-v0.2-Neural-Story
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
dtype: bfloat16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	65.02
AI2 Reasoning Challenge (25-Shot)	59.98
HellaSwag (10-Shot)	83.21
MMLU (5-Shot)	61.42
TruthfulQA (0-shot)	61.03
Winogrande (5-shot)	77.66
GSM8k (5-shot)	46.78