README.md

---
license: mit
model-index:
- name: openhermes_dpo_norobot_0201
  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: 62.03
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jae24/openhermes_dpo_norobot_0201
      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: 83.4
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jae24/openhermes_dpo_norobot_0201
      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: 62.4
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jae24/openhermes_dpo_norobot_0201
      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: 47.44
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jae24/openhermes_dpo_norobot_0201
      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: 78.22
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jae24/openhermes_dpo_norobot_0201
      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: 49.2
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jae24/openhermes_dpo_norobot_0201
      name: Open LLM Leaderboard
---

This variant of the model has undergone reinforcement learning (RL) fine-tuning and is based on teknium/OpenHermes-2.5-Mistral-7B. The fine-tuning process utilized a preference dataset derived from HuggingFace's no robots dataset, incorporating Differential Privacy Optimization (DPO) techniques.
# [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_jae24__openhermes_dpo_norobot_0201)

|             Metric              |Value|
|---------------------------------|----:|
|Avg.                             |63.78|
|AI2 Reasoning Challenge (25-Shot)|62.03|
|HellaSwag (10-Shot)              |83.40|
|MMLU (5-Shot)                    |62.40|
|TruthfulQA (0-shot)              |47.44|
|Winogrande (5-shot)              |78.22|
|GSM8k (5-shot)                   |49.20|