README.md

metadata

license: cc-by-nc-sa-4.0

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

This model was introduced in the paper LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression (Pan et al, 2024). It is a XLM-RoBERTa (large-sized model) finetuned to perform token classification for task agnostic prompt compression. The probability $p_{preserve}$ of each token $x_i$ is used as the metric for compression. This model is trained on an extractive text compression dataset constructed with the methodology proposed in the LLMLingua-2, using training examples from MeetingBank (Hu et al, 2023) as the seed data.

For more details, please check the home page of LLMLingua-2 and LLMLingua Series.

Usage

from llmlingua import PromptCompressor

compressor = PromptCompressor(
        model_name="qianhuiwu/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}")

Citation

{}