Summary Loop10

🚀 摘要生成模型

本項目提供了一個基於GPT2架構的摘要生成模型，可用於對文本進行摘要提取。該模型使用cnn_dailymail數據集進行訓練，在摘要生成任務上具有一定的效果。

🚀 快速開始

在右側面板中，你可以嘗試使用該模型（儘管它僅處理較短的序列長度）。在右側面板中輸入你想要摘要的文檔。

📦 安裝指南

基於GPT2基礎架構的模型可以通過以下方式加載：

from transformers import GPT2LMHeadModel, GPT2TokenizerFast

model = GPT2LMHeadModel.from_pretrained("philippelaban/summary_loop10")
tokenizer = GPT2TokenizerFast.from_pretrained("philippelaban/summary_loop10")

💻 使用示例

基礎用法

以下是一個使用該模型進行摘要生成的示例：

document = "Bouncing Boulders Point to Quakes on Mars. A preponderance of boulder tracks on the red planet may be evidence of recent seismic activity. If a rock falls on Mars, and no one is there to see it, does it leave a trace? Yes, and it's a beautiful herringbone-like pattern, new research reveals. Scientists have now spotted thousands of tracks on the red planet created by tumbling boulders. Delicate chevron-shaped piles of Martian dust and sand frame the tracks, the team showed, and most fade over the course of a few years. Rockfalls have been spotted elsewhere in the solar system, including on the moon and even a comet. But a big open question is the timing of these processes on other worlds — are they ongoing or did they predominantly occur in the past?"

tokenized_document = tokenizer([document], max_length=300, truncation=True, return_tensors="pt")["input_ids"].cuda()
input_shape = tokenized_document.shape
outputs = model.generate(tokenized_document, do_sample=False, max_length=500, num_beams=4, num_return_sequences=4, no_repeat_ngram_size=6, return_dict_in_generate=True, output_scores=True)
candidate_sequences = outputs.sequences[:, input_shape[1]:] # Remove the encoded text, keep only the summary
candidate_scores = outputs.sequences_scores.tolist()

for candidate_tokens, score in zip(candidate_sequences, candidate_scores):
    summary = tokenizer.decode(candidate_tokens)
    print("[Score: %.3f] %s" % (score, summary[:summary.index("END")]))

示例輸出

運行上述代碼，可能會得到以下輸出：

[Score: -0.084]  Here's what you need to know about rockfalls
[Score: -0.087]  Here's what you need to know about these tracks
[Score: -0.091]  Here's what we know so far about these tracks
[Score: -0.101]  Here's what you need to know about rockfall

📚 詳細文檔

你可以在GitHub倉庫中獲取更多信息、訪問評分函數、訓練腳本或示例訓練日誌：https://github.com/CannyLab/summary_loop

📄 許可證

本項目採用Apache 2.0許可證。