README.md

---
language:
- en
license: gemma
tags:
- supernova
- moth
- gemma
- gemma-2
- gemma-2-it
- gemma-2-9b-it
- 9b
- general
- conversational
- chat
- instruct
base_model: google/gemma-2-9b-it
datasets:
- sequelbox/Supernova
pipeline_tag: text-generation
model-index:
- name: gemma-2-9B-MOTH
  results:
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: IFEval (0-Shot)
      type: HuggingFaceH4/ifeval
      args:
        num_few_shot: 0
    metrics:
    - type: inst_level_strict_acc and prompt_level_strict_acc
      value: 20.59
      name: strict accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sequelbox/gemma-2-9B-MOTH
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: BBH (3-Shot)
      type: BBH
      args:
        num_few_shot: 3
    metrics:
    - type: acc_norm
      value: 3.21
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sequelbox/gemma-2-9B-MOTH
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MATH Lvl 5 (4-Shot)
      type: hendrycks/competition_math
      args:
        num_few_shot: 4
    metrics:
    - type: exact_match
      value: 0.0
      name: exact match
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sequelbox/gemma-2-9B-MOTH
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: GPQA (0-shot)
      type: Idavidrein/gpqa
      args:
        num_few_shot: 0
    metrics:
    - type: acc_norm
      value: 1.34
      name: acc_norm
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sequelbox/gemma-2-9B-MOTH
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MuSR (0-shot)
      type: TAUR-Lab/MuSR
      args:
        num_few_shot: 0
    metrics:
    - type: acc_norm
      value: 0.62
      name: acc_norm
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sequelbox/gemma-2-9B-MOTH
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MMLU-PRO (5-shot)
      type: TIGER-Lab/MMLU-Pro
      config: main
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 1.56
      name: accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=sequelbox/gemma-2-9B-MOTH
      name: Open LLM Leaderboard
---


- MOTH is a general chat AI.
- MOTH is finetuned on [high quality synthetic data.](https://huggingface.co/datasets/sequelbox/Supernova)
- MOTH is trained on a variety of skills and specialties.
- This version of MOTH is trained on the [Gemma 2 Instruct format.](https://huggingface.co/google/gemma-2-9b-it)
- MOTH is also available for [Llama 3.1;](https://huggingface.co/sequelbox/Llama3.1-8B-MOTH) more MOTH finetunes for other models to follow.
- MOTH has not been manually tested and uses automatically generated datasets.
- Do as you will.
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_sequelbox__gemma-2-9B-MOTH)

|      Metric       |Value|
|-------------------|----:|
|Avg.               | 4.55|
|IFEval (0-Shot)    |20.59|
|BBH (3-Shot)       | 3.21|
|MATH Lvl 5 (4-Shot)| 0.00|
|GPQA (0-shot)      | 1.34|
|MuSR (0-shot)      | 0.62|
|MMLU-PRO (5-shot)  | 1.56|