README.md

metadata

license: apache-2.0
library_name: transformers
tags:
  - mergekit
  - merge
base_model:
  - NeuralNovel/Senzu-7B-v0.1-DPO
  - senseable/WestLake-7B-v2
model-index:
  - name: WestSenzu-Swap-7B
    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: 68.34
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Aryanne/WestSenzu-Swap-7B
          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: 85.7
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Aryanne/WestSenzu-Swap-7B
          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: 64.14
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Aryanne/WestSenzu-Swap-7B
          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: 50.43
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Aryanne/WestSenzu-Swap-7B
          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: 82.48
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Aryanne/WestSenzu-Swap-7B
          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: 52.62
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Aryanne/WestSenzu-Swap-7B
          name: Open LLM Leaderboard

It's experimental, but seems fine for me, I didn't run it deeply yet but should be good for Role-play 😈 considering the two merged models, feel free to leave a suggestion or feedback.

This is a merge of pre-trained language models created using mergekit(my experimental branch swapping here )

Merge Details

Merge Method

This model was merged using the task_swapping merge method using NeuralNovel/Senzu-7B-v0.1-DPO as a base.

Models Merged

The following models were included in the merge:

• senseable/WestLake-7B-v2

Configuration

The following YAML configuration was used to produce this model:

merge_method: task_swapping
base_model: NeuralNovel/Senzu-7B-v0.1-DPO
models:
  - model: senseable/WestLake-7B-v2
    parameters:
      weight: 0.75
      diagonal_offset: 2    #it doesn't do anything when you use random_mask
      random_mask: 0.3333
      random_mask_seed: 98557
dtype: bfloat16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	67.28
AI2 Reasoning Challenge (25-Shot)	68.34
HellaSwag (10-Shot)	85.70
MMLU (5-Shot)	64.14
TruthfulQA (0-shot)	50.43
Winogrande (5-shot)	82.48
GSM8k (5-shot)	52.62