README.md

metadata

language:
  - en
license: cc-by-nc-4.0
library_name: transformers
tags:
  - mergekit
  - merge
base_model:
  - SanjiWatsuki/Kunoichi-DPO-v2-7B
  - macadeliccc/WestLake-7B-v2-laser-truthy-dpo
model-index:
  - name: finch
    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: 71.59
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=antiven0m/finch
          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: 87.87
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=antiven0m/finch
          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: 64.81
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=antiven0m/finch
          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: 67.96
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=antiven0m/finch
          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: 84.14
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=antiven0m/finch
          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: 66.34
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=antiven0m/finch
          name: Open LLM Leaderboard

Finch 7b Merge

A SLERP merge of my two current fav 7B models

macadeliccc/WestLake-7B-v2-laser-truthy-dpo & SanjiWatsuki/Kunoichi-DPO-v2-7B

• 6bpw EXL2 Quant
• GGUF Quants

Settings

I reccomend using the ChatML format. As for samplers, I reccomend the following:

Temperature: 1.2
Min P: 0.2
Smoothing Factor: 0.2

Mergekit Config

base_model: macadeliccc/WestLake-7B-v2-laser-truthy-dpo
dtype: float16
merge_method: slerp
parameters:
  t:
  - filter: self_attn
    value: [0.0, 0.5, 0.3, 0.7, 1.0]
  - filter: mlp
    value: [1.0, 0.5, 0.7, 0.3, 0.0]
  - value: 0.5
slices:
- sources:
  - layer_range: [0, 32]
    model: macadeliccc/WestLake-7B-v2-laser-truthy-dpo
  - layer_range: [0, 32]
    model: SanjiWatsuki/Kunoichi-DPO-v2-7B

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	73.78
AI2 Reasoning Challenge (25-Shot)	71.59
HellaSwag (10-Shot)	87.87
MMLU (5-Shot)	64.81
TruthfulQA (0-shot)	67.96
Winogrande (5-shot)	84.14
GSM8k (5-shot)	66.34