DonutLM-v1 / README.md
leaderboard-pr-bot's picture
Adding Evaluation Results
8fbbe1a verified
metadata
license: apache-2.0
tags:
  - merge
model-index:
  - name: DonutLM-v1
    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: 69.11
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cookinai/DonutLM-v1
          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: 85.91
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cookinai/DonutLM-v1
          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: 65.45
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cookinai/DonutLM-v1
          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: 63.36
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cookinai/DonutLM-v1
          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: 81.69
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cookinai/DonutLM-v1
          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: 66.79
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cookinai/DonutLM-v1
          name: Open LLM Leaderboard

Fixed

Heard alot in the commuity about jondurbin/bagel-dpo-7b-v0.1 and it sounds intresting.

Slerp Merge of AIDC-ai-business/Marcoroni-7B-v3 and jondurbin/bagel-dpo-7b-v0.1

.yaml file for mergekit

slices:
  - sources:
      - model: AIDC-ai-business/Marcoroni-7B-v3
        layer_range: [0, 32]
      - model: jondurbin/bagel-dpo-7b-v0.1
        layer_range: [0, 32]
merge_method: slerp
base_model: AIDC-ai-business/Marcoroni-7B-v3
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 # fallback for rest of tensors
dtype: bfloat16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric Value
Avg. 72.05
AI2 Reasoning Challenge (25-Shot) 69.11
HellaSwag (10-Shot) 85.91
MMLU (5-Shot) 65.45
TruthfulQA (0-shot) 63.36
Winogrande (5-shot) 81.69
GSM8k (5-shot) 66.79