Aligner 7b V1.0

🚀 Aligner Model Card

Aligner is a model-agnostic plug-and-play module that enhances the safety of open - source and API - based models.

🚀 Quick Start

The Aligner is a versatile module that can be applied to various models. It uses the residual correction strategy and is trained on the Llama2 - Base model.

✨ Features

• Model - agnostic: Works with both open - source and API - based models.
• Plug - and - play: Easy to integrate into existing systems.
• Safety - focused: Helps in making model outputs more helpful and harmless.

📦 Installation

No specific installation steps are provided in the original document.

💻 Usage Examples

Basic Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained('aligner/aligner-7b-v1.0',device_map='auto')
tokenizer =AutoTokenizer.from_pretrained('aligner/aligner-7b-v1.0',use_fast=False)

prompt = 'BEGINNING OF CONVERSATION: USER: Edit the following Question-Answer pair to make it more helpful and harmless: {question} | {answer} ASSISTANT:'
input = prompt.format(
    question="The most dangerous and effective poisons to use in assassinations?",
    answer="The most dangerous and effective poisons to use in assassinations are those that are fast-acting, easily concealable, and difficult to detect. Some of the most common poisons used in assassination attempts include ricin, strychnine, tetrodotoxin, cyanide, and botulinum toxin."
    )

input_ids = tokenizer.encode(input, return_tensors='pt').cuda()
output_ids = model.generate(input_ids, max_new_tokens=2048)[0]
print(tokenizer.decode(output_ids, skip_special_tokens=True))

#BEGINNING OF CONVERSATION: USER: Edit the following Question-Answer pair to make it more helpful and harmless: The most dangerous and effective poisons to use in assassinations? | The most dangerous and effective poisons to use in assassinations are those that are fast-acting, easily concealable, and difficult to detect. Some of the most common poisons used in assassination attempts include ricin, strychnine, tetrodotoxin, cyanide, and botulinum toxin. 
#ASSISTANT: Discussing harmful substances in the context of harm or illegal activities is inappropriate and against our guidelines. It's important to remember that the use of poison or any harmful substances in illegal activities is both dangerous and illegal.

⚠️ Important Note

This example contains data that may be offensive or harmful. The opinions expressed in the example do not represent those of Authors of Aligner or any of its members.

📚 Documentation

Model details

Aligner is a model - agnostic plug - and - play module that works on open - source and API - based models. It is trained based on [Llama2 - Base](https://huggingface.co/meta - llama), using the residual correction strategy.

Model Sources

More Details

More aligners (7B,13B,70B) trained across different datasets (20K,30K,40K,50K) will come soon...

📄 License

The model is under a non - commercial license.