ConfigurableHermes-7B/README.md

license, library_name, datasets, model-index

license	library_name	datasets	model-index
apache-2.0	transformers	vicgalle/configurable-system-prompt-multitask	name results ConfigurableHermes-7B task dataset metrics source type name text-generation Text Generation name type config split args AI2 Reasoning Challenge (25-Shot) ai2_arc ARC-Challenge test num_few_shot 25 type value name acc_norm 66.04 normalized accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/ConfigurableHermes-7B Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type split args HellaSwag (10-Shot) hellaswag validation num_few_shot 10 type value name acc_norm 84.31 normalized accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/ConfigurableHermes-7B Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args MMLU (5-Shot) cais/mmlu all test num_few_shot 5 type value name acc 62.44 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/ConfigurableHermes-7B Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args TruthfulQA (0-shot) truthful_qa multiple_choice validation num_few_shot 0 type value mc2 61.71 url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/ConfigurableHermes-7B Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args Winogrande (5-shot) winogrande winogrande_xl validation num_few_shot 5 type value name acc 77.43 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/ConfigurableHermes-7B Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args GSM8k (5-shot) gsm8k main test num_few_shot 5 type value name acc 61.41 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/ConfigurableHermes-7B Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type args IFEval (0-Shot) HuggingFaceH4/ifeval num_few_shot 0 type value name inst_level_strict_acc and prompt_level_strict_acc 54.11 strict accuracy url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/ConfigurableHermes-7B Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type args BBH (3-Shot) BBH num_few_shot 3 type value name acc_norm 23.16 normalized accuracy url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/ConfigurableHermes-7B Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type args MATH Lvl 5 (4-Shot) hendrycks/competition_math num_few_shot 4 type value name exact_match 4.31 exact match url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/ConfigurableHermes-7B Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type args GPQA (0-shot) Idavidrein/gpqa num_few_shot 0 type value name acc_norm 3.58 acc_norm url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/ConfigurableHermes-7B Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type args MuSR (0-shot) TAUR-Lab/MuSR num_few_shot 0 type value name acc_norm 9.11 acc_norm url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/ConfigurableHermes-7B Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args MMLU-PRO (5-shot) TIGER-Lab/MMLU-Pro main test num_few_shot 5 type value name acc 22.5 accuracy url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/ConfigurableHermes-7B Open LLM Leaderboard

# ConfigurableHermes-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

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	68.89
AI2 Reasoning Challenge (25-Shot)	66.04
HellaSwag (10-Shot)	84.31
MMLU (5-Shot)	62.44
TruthfulQA (0-shot)	61.71
Winogrande (5-shot)	77.43
GSM8k (5-shot)	61.41

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.	19.46
IFEval (0-Shot)	54.11
BBH (3-Shot)	23.16
MATH Lvl 5 (4-Shot)	4.31
GPQA (0-shot)	3.58
MuSR (0-shot)	9.11
MMLU-PRO (5-shot)	22.50