eren23's picture
Adding Evaluation Results (#2)
825ef7a verified
metadata
language:
  - en
license: cc-by-nc-4.0
library_name: transformers
tags:
  - text-generation-inference
datasets:
  - argilla/OpenHermesPreferences
pipeline_tag: text2text-generation
model-index:
  - name: ogno-monarch-jaskier-merge-7b-OH-PREF-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: 73.12
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=eren23/ogno-monarch-jaskier-merge-7b-OH-PREF-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: 89.09
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=eren23/ogno-monarch-jaskier-merge-7b-OH-PREF-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: 64.8
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=eren23/ogno-monarch-jaskier-merge-7b-OH-PREF-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: 77.45
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=eren23/ogno-monarch-jaskier-merge-7b-OH-PREF-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: 84.77
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=eren23/ogno-monarch-jaskier-merge-7b-OH-PREF-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: 69.45
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=eren23/ogno-monarch-jaskier-merge-7b-OH-PREF-DPO
          name: Open LLM Leaderboard

Model Card for Model ID

disclaimer

just experimented with the model I had https://huggingface.co/eren23/ogno-monarch-jaskier-merge-7b here with the new preferences dataset of argillia here: https://huggingface.co/datasets/argilla/OpenHermesPreferences

I didn't test the model and the perf wasn't that good when training so use/test it with caution

disclaimer 2

It turns out the model performs well in benchmarks :D

GGUF: https://huggingface.co/eren23/ogno-monarch-jaskier-merge-7b-OH-PREF-DPO-GGUF

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric Value
Avg. 76.45
AI2 Reasoning Challenge (25-Shot) 73.12
HellaSwag (10-Shot) 89.09
MMLU (5-Shot) 64.80
TruthfulQA (0-shot) 77.45
Winogrande (5-shot) 84.77
GSM8k (5-shot) 69.45