README.md

metadata

language:
  - en
license: mit
library_name: transformers
tags:
  - mergekit
  - merge
base_model:
  - FelixChao/Sectumsempra-7B-DPO
  - FelixChao/WestSeverus-7B-DPO-v2
pipeline_tag: text-generation
model-index:
  - name: Severusectum-7B-DPO
    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: 71.5
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=s3nh/Severusectum-7B-DPO
          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: 88.55
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=s3nh/Severusectum-7B-DPO
          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: 64.79
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=s3nh/Severusectum-7B-DPO
          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: 72.45
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=s3nh/Severusectum-7B-DPO
          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: 83.27
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=s3nh/Severusectum-7B-DPO
          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: 70.51
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=s3nh/Severusectum-7B-DPO
          name: Open LLM Leaderboard

Severusectum-7B-DPO

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:

• FelixChao/Sectumsempra-7B-DPO
• FelixChao/WestSeverus-7B-DPO-v2

Configuration

The following YAML configuration was used to produce this model:

base_model: FelixChao/Sectumsempra-7B-DPO
dtype: bfloat16
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: FelixChao/Sectumsempra-7B-DPO
  - layer_range: [0, 32]
    model: FelixChao/WestSeverus-7B-DPO-v2

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	75.18
AI2 Reasoning Challenge (25-Shot)	71.50
HellaSwag (10-Shot)	88.55
MMLU (5-Shot)	64.79
TruthfulQA (0-shot)	72.45
Winogrande (5-shot)	83.27
GSM8k (5-shot)	70.51