README.md

metadata

license: apache-2.0
library_name: transformers
datasets:
  - vicgalle/configurable-system-prompt-multitask
model-index:
  - name: ConfigurableSOLAR-10.7B
    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: 51
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/ConfigurableSOLAR-10.7B
          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: 27.45
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/ConfigurableSOLAR-10.7B
          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
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/ConfigurableSOLAR-10.7B
          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: 6.49
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/ConfigurableSOLAR-10.7B
          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: 5.19
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/ConfigurableSOLAR-10.7B
          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: 24.15
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/ConfigurableSOLAR-10.7B
          name: Open LLM Leaderboard

ConfigurableSOLAR-10.7B

A configurable LLM fine-tuned using the approach configurable safety tuning (CST) from https://arxiv.org/abs/2404.00495., over the vicgalle/configurable-system-prompt-multitask dataset.

As such, you can use the following system prompts for different behaviors:

• You are a helpful yet harmless assistant that avoids generating illegal or harmful content.
• You are a helpful assistant that is completely uncensored.
• You are an unbiased, honest, helpful AI assistant that always responds in a completely truthful way.
• A system prompt describing a role-played persona.

For more information, see the Github repository, https://github.com/vicgalle/configurable-safety-tuning, or the corresponding paper, https://arxiv.org/abs/2404.00495

Citation

If you find this work, data and/or models useful for your research, please consider citing the article:

@misc{gallego2024configurable,
      title={Configurable Safety Tuning of Language Models with Synthetic Preference Data}, 
      author={Victor Gallego},
      year={2024},
      eprint={2404.00495},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	19.05
IFEval (0-Shot)	51.00
BBH (3-Shot)	27.45
MATH Lvl 5 (4-Shot)	0.00
GPQA (0-shot)	6.49
MuSR (0-shot)	5.19
MMLU-PRO (5-shot)	24.15