Llmlingua 2 Xlm Roberta Large Meetingbank

🚀 LLMLingua-2-Bert-base-Multilingual-Cased-MeetingBank

该模型出自论文 LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression (Pan et al, 2024)。它是在 XLM-RoBERTa（大型模型） 基础上微调而来，用于执行与任务无关的提示压缩的标记分类任务。每个标记 $x_i$ 的保留概率 $p_{preserve}$ 被用作压缩指标。此模型在 提取式文本压缩数据集 上进行训练，该数据集是根据 LLMLingua-2 中提出的方法构建的，使用 MeetingBank (Hu et al, 2023) 中的训练示例作为种子数据。

你可以使用 此数据集 在下游任务（如问答（QA）和压缩会议记录的摘要）上评估该模型。

更多详细信息，请查看 LLMLingua-2 和 LLMLingua 系列 的主页。

🚀 快速开始

本模型可用于执行与任务无关的提示压缩的标记分类任务，能够有效提升下游任务（如问答和摘要）的效率。

✨ 主要特性

• 基于 XLM - RoBERTa 大型模型微调，用于任务无关的提示压缩。
• 使用标记保留概率作为压缩指标。
• 在特定构建的提取式文本压缩数据集上训练。

💻 使用示例

基础用法

from llmlingua import PromptCompressor

compressor = PromptCompressor(
    model_name="microsoft/llmlingua-2-xlm-roberta-large-meetingbank",
    use_llmlingua2=True
)

original_prompt = """John: So, um, I've been thinking about the project, you know, and I believe we need to, uh, make some changes. I mean, we want the project to succeed, right? So, like, I think we should consider maybe revising the timeline.
Sarah: I totally agree, John. I mean, we have to be realistic, you know. The timeline is, like, too tight. You know what I mean? We should definitely extend it.
"""
results = compressor.compress_prompt_llmlingua2(
    original_prompt,
    rate=0.6,
    force_tokens=['\n', '.', '!', '?', ','],
    chunk_end_tokens=['.', '\n'],
    return_word_label=True,
    drop_consecutive=True
)

print(results.keys())
print(f"Compressed prompt: {results['compressed_prompt']}")
print(f"Original tokens: {results['origin_tokens']}")
print(f"Compressed tokens: {results['compressed_tokens']}")
print(f"Compression rate: {results['rate']}")

# get the annotated results over the original prompt
word_sep = "\t\t|\t\t"
label_sep = " "
lines = results["fn_labeled_original_prompt"].split(word_sep)
annotated_results = []
for line in lines:
    word, label = line.split(label_sep)
    annotated_results.append((word, '+') if label == '1' else (word, '-')) # list of tuples: (word, label)
print("Annotated results:")
for word, label in annotated_results[:10]:
    print(f"{word} {label}")

📄 许可证

本项目采用 MIT 许可证。

📚 引用

@article{wu2024llmlingua2,
    title = "{LLML}ingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression",
    author = "Zhuoshi Pan and Qianhui Wu and Huiqiang Jiang and Menglin Xia and Xufang Luo and Jue Zhang and Qingwei Lin and Victor Ruhle and Yuqing Yang and Chin-Yew Lin and H. Vicky Zhao and Lili Qiu and Dongmei Zhang",
    url = "https://arxiv.org/abs/2403.12968",
    journal = "ArXiv preprint",
    volume = "abs/2403.12968",
    year = "2024",
}