Aligner 7b V1.0

🚀 對齊器模型卡片

對齊器（Aligner）是一個與模型無關的即插即用模塊，可在開源模型和基於API的模型上運行。它基於Llama2-Base進行訓練，並採用了殘差校正策略。

✨ 主要特性

• 模型無關性：可適配開源模型和基於API的模型。
• 訓練基礎：基於Llama2-Base訓練。
• 策略運用：採用殘差校正策略。

📦 安裝指南

文檔未提供安裝步驟，此部分跳過。

💻 使用示例

基礎用法

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.

高級用法

文檔未提供高級用法示例，此部分跳過。

📚 詳細文檔

模型來源

• 倉庫地址：https://github.com/Aligner2024/aligner
• 數據集地址：https://huggingface.co/datasets/aligner/aligner-20K
• 許可證：非商業許可證。

更多詳情

• 網站地址：https://aligner2024.github.io/

更多基於不同數據集（20K、30K、40K、50K）訓練的對齊器（7B、13B、70B）即將推出...

注意事項

⚠️ 重要提示

此示例包含可能令人反感或有害的數據。示例中表達的觀點並不代表對齊器作者或其任何成員的觀點。

🔧 技術細節

文檔未提供技術細節，此部分跳過。

📄 許可證

本項目使用非商業許可證。