---
language:
- en
license: apache-2.0
model-index:
- name: merge_model_test2
  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: 79.35
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kimdeokgi/merge_model_test2
      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: 89.75
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kimdeokgi/merge_model_test2
      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: 67.89
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kimdeokgi/merge_model_test2
      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: 71.58
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kimdeokgi/merge_model_test2
      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: 86.58
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kimdeokgi/merge_model_test2
      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: 55.57
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kimdeokgi/merge_model_test2
      name: Open LLM Leaderboard
---

# kimdeokgi/merge_model_test2


# **Introduction**
This model is test version, alignment-tuned model.

We utilize state-of-the-art instruction fine-tuning methods including direct preference optimization (DPO).
After DPO training, we linearly merged models to boost performance.
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_kimdeokgi__merge_model_test2)

|             Metric              |Value|
|---------------------------------|----:|
|Avg.                             |75.12|
|AI2 Reasoning Challenge (25-Shot)|79.35|
|HellaSwag (10-Shot)              |89.75|
|MMLU (5-Shot)                    |67.89|
|TruthfulQA (0-shot)              |71.58|
|Winogrande (5-shot)              |86.58|
|GSM8k (5-shot)                   |55.57|