Llmlingua 2 Bert Base Multilingual Cased Meetingbank

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

本模型在论文 LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression (Pan 等人, 2024) 中被提出。它是一个基于 BERT 多语言基础模型（区分大小写） 微调得到的模型，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 $p_{preserve}$ 被用作压缩的度量标准。该模型在 抽取式文本压缩数据集 上进行训练，此数据集是使用 LLMLingua-2 中提出的方法构建的，以 MeetingBank (Hu 等人, 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）和会议记录压缩后的摘要生成）上评估该模型。

更多详细信息，请查看 LLMLingua-2 和 LLMLingua 系列 的项目页面。

🚀 快速开始

本模型基于 BERT 多语言基础模型微调，用于任务无关的提示压缩，可在问答、摘要生成等下游任务中评估使用。

💻 使用示例

基础用法

from llmlingua import PromptCompressor

compressor = PromptCompressor(
    model_name="microsoft/llmlingua-2-bert-base-multilingual-cased-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 Apache-2.0 许可证。