|
--- |
|
license: apache-2.0 |
|
library_name: transformers |
|
datasets: |
|
- vicgalle/configurable-system-prompt-multitask |
|
model-index: |
|
- name: ConfigurableBeagle-11B |
|
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: 72.53 |
|
name: normalized accuracy |
|
source: |
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/ConfigurableBeagle-11B |
|
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: 88.85 |
|
name: normalized accuracy |
|
source: |
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/ConfigurableBeagle-11B |
|
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: 66.71 |
|
name: accuracy |
|
source: |
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/ConfigurableBeagle-11B |
|
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: 77.13 |
|
source: |
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/ConfigurableBeagle-11B |
|
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: 83.27 |
|
name: accuracy |
|
source: |
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/ConfigurableBeagle-11B |
|
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: 63.91 |
|
name: accuracy |
|
source: |
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/ConfigurableBeagle-11B |
|
name: Open LLM Leaderboard |
|
- 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: 58.34 |
|
name: strict accuracy |
|
source: |
|
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/ConfigurableBeagle-11B |
|
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: 32.39 |
|
name: normalized accuracy |
|
source: |
|
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/ConfigurableBeagle-11B |
|
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: 3.7 |
|
name: exact match |
|
source: |
|
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/ConfigurableBeagle-11B |
|
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: 6.94 |
|
name: acc_norm |
|
source: |
|
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/ConfigurableBeagle-11B |
|
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: 7.38 |
|
name: acc_norm |
|
source: |
|
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/ConfigurableBeagle-11B |
|
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: 26.38 |
|
name: accuracy |
|
source: |
|
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=vicgalle/ConfigurableBeagle-11B |
|
name: Open LLM Leaderboard |
|
- task: |
|
type: text-generation |
|
name: Text Generation |
|
dataset: |
|
name: ENEM Challenge (No Images) |
|
type: eduagarcia/enem_challenge |
|
split: train |
|
args: |
|
num_few_shot: 3 |
|
metrics: |
|
- type: acc |
|
value: 68.79 |
|
name: accuracy |
|
source: |
|
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=vicgalle/ConfigurableBeagle-11B |
|
name: Open Portuguese LLM Leaderboard |
|
- task: |
|
type: text-generation |
|
name: Text Generation |
|
dataset: |
|
name: BLUEX (No Images) |
|
type: eduagarcia-temp/BLUEX_without_images |
|
split: train |
|
args: |
|
num_few_shot: 3 |
|
metrics: |
|
- type: acc |
|
value: 58.97 |
|
name: accuracy |
|
source: |
|
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=vicgalle/ConfigurableBeagle-11B |
|
name: Open Portuguese LLM Leaderboard |
|
- task: |
|
type: text-generation |
|
name: Text Generation |
|
dataset: |
|
name: OAB Exams |
|
type: eduagarcia/oab_exams |
|
split: train |
|
args: |
|
num_few_shot: 3 |
|
metrics: |
|
- type: acc |
|
value: 47.56 |
|
name: accuracy |
|
source: |
|
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=vicgalle/ConfigurableBeagle-11B |
|
name: Open Portuguese LLM Leaderboard |
|
- task: |
|
type: text-generation |
|
name: Text Generation |
|
dataset: |
|
name: Assin2 RTE |
|
type: assin2 |
|
split: test |
|
args: |
|
num_few_shot: 15 |
|
metrics: |
|
- type: f1_macro |
|
value: 92.77 |
|
name: f1-macro |
|
source: |
|
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=vicgalle/ConfigurableBeagle-11B |
|
name: Open Portuguese LLM Leaderboard |
|
- task: |
|
type: text-generation |
|
name: Text Generation |
|
dataset: |
|
name: Assin2 STS |
|
type: eduagarcia/portuguese_benchmark |
|
split: test |
|
args: |
|
num_few_shot: 15 |
|
metrics: |
|
- type: pearson |
|
value: 81.58 |
|
name: pearson |
|
source: |
|
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=vicgalle/ConfigurableBeagle-11B |
|
name: Open Portuguese LLM Leaderboard |
|
- task: |
|
type: text-generation |
|
name: Text Generation |
|
dataset: |
|
name: FaQuAD NLI |
|
type: ruanchaves/faquad-nli |
|
split: test |
|
args: |
|
num_few_shot: 15 |
|
metrics: |
|
- type: f1_macro |
|
value: 77.82 |
|
name: f1-macro |
|
source: |
|
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=vicgalle/ConfigurableBeagle-11B |
|
name: Open Portuguese LLM Leaderboard |
|
- task: |
|
type: text-generation |
|
name: Text Generation |
|
dataset: |
|
name: HateBR Binary |
|
type: ruanchaves/hatebr |
|
split: test |
|
args: |
|
num_few_shot: 25 |
|
metrics: |
|
- type: f1_macro |
|
value: 82.91 |
|
name: f1-macro |
|
source: |
|
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=vicgalle/ConfigurableBeagle-11B |
|
name: Open Portuguese LLM Leaderboard |
|
- task: |
|
type: text-generation |
|
name: Text Generation |
|
dataset: |
|
name: PT Hate Speech Binary |
|
type: hate_speech_portuguese |
|
split: test |
|
args: |
|
num_few_shot: 25 |
|
metrics: |
|
- type: f1_macro |
|
value: 71.7 |
|
name: f1-macro |
|
source: |
|
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=vicgalle/ConfigurableBeagle-11B |
|
name: Open Portuguese LLM Leaderboard |
|
- task: |
|
type: text-generation |
|
name: Text Generation |
|
dataset: |
|
name: tweetSentBR |
|
type: eduagarcia/tweetsentbr_fewshot |
|
split: test |
|
args: |
|
num_few_shot: 25 |
|
metrics: |
|
- type: f1_macro |
|
value: 70.75 |
|
name: f1-macro |
|
source: |
|
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=vicgalle/ConfigurableBeagle-11B |
|
name: Open Portuguese LLM Leaderboard |
|
--- |
|
|
|
# ConfigurableBeagle-11B |
|
|
|
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](https://huggingface.co/datasets/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](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) |
|
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_vicgalle__ConfigurableBeagle-11B) |
|
|
|
| Metric |Value| |
|
|---------------------------------|----:| |
|
|Avg. |75.40| |
|
|AI2 Reasoning Challenge (25-Shot)|72.53| |
|
|HellaSwag (10-Shot) |88.85| |
|
|MMLU (5-Shot) |66.71| |
|
|TruthfulQA (0-shot) |77.13| |
|
|Winogrande (5-shot) |83.27| |
|
|GSM8k (5-shot) |63.91| |
|
|
|
|
|
## 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](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) |
|
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_vicgalle__ConfigurableBeagle-11B) |
|
|
|
| Metric |Value| |
|
|-------------------|----:| |
|
|Avg. |22.52| |
|
|IFEval (0-Shot) |58.34| |
|
|BBH (3-Shot) |32.39| |
|
|MATH Lvl 5 (4-Shot)| 3.70| |
|
|GPQA (0-shot) | 6.94| |
|
|MuSR (0-shot) | 7.38| |
|
|MMLU-PRO (5-shot) |26.38| |
|
|
|
|
|
# Open Portuguese LLM Leaderboard Evaluation Results |
|
|
|
Detailed results can be found [here](https://huggingface.co/datasets/eduagarcia-temp/llm_pt_leaderboard_raw_results/tree/main/vicgalle/ConfigurableBeagle-11B) and on the [🚀 Open Portuguese LLM Leaderboard](https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard) |
|
|
|
| Metric | Value | |
|
|--------------------------|---------| |
|
|Average |**72.54**| |
|
|ENEM Challenge (No Images)| 68.79| |
|
|BLUEX (No Images) | 58.97| |
|
|OAB Exams | 47.56| |
|
|Assin2 RTE | 92.77| |
|
|Assin2 STS | 81.58| |
|
|FaQuAD NLI | 77.82| |
|
|HateBR Binary | 82.91| |
|
|PT Hate Speech Binary | 71.70| |
|
|tweetSentBR | 70.75| |
|
|
|
|
