🚀 摘要生成模型
本项目提供了一个基于GPT2架构的摘要生成模型,可对输入的文档进行摘要提取。该模型使用cnn_dailymail
数据集进行训练,并以ROUGE
作为评估指标,采用Apache-2.0
许可证。
🚀 快速开始
在右侧面板中,你可以尝试使用该模型(尽管它仅处理短序列长度)。在右侧面板中输入你想要摘要的文档。
📦 安装指南
基于GPT2基础架构的模型可以按以下方式加载:
from transformers import GPT2LMHeadModel, GPT2TokenizerFast
model = GPT2LMHeadModel.from_pretrained("philippelaban/summary_loop46")
tokenizer = GPT2TokenizerFast.from_pretrained("philippelaban/summary_loop46")
💻 使用示例
基础用法
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]:]
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")]))
示例输出
[Score: -0.153] These tracks have been spotted elsewhere on Mars. If a rockfalls on Mars has been spotted elsewhere on the red planet. Scientists have spotted thousands of tracks on Mars. A rockfalls on Mars have been spotted elsewhere on the Red Planet.
[Score: -0.154] These tracks have been spotted elsewhere on Mars. If a rockfalls on Mars has been spotted elsewhere on the red planet. Scientists have spotted thousands of tracks on Mars. A rockfalls on Mars have been spotted elsewhere on the planet.
[Score: -0.154] These tracks have been spotted elsewhere on Mars. If a rockfalls on Mars has been spotted elsewhere on the red planet. Scientists have spotted thousands of tracks on Mars. A rockfalls have been spotted elsewhere on the Red Planet.
[Score: -0.195] These tracks have been spotted elsewhere on Mars. If a rockfalls on Mars has been spotted elsewhere on the red planet. Scientists have spotted thousands of tracks on Mars. A rockfalls on Mars have been spotted elsewhere on the Red Planet. A rockfalls have been spotted everywhere on the red planet.
📚 详细文档
你可以在GitHub仓库中获取更多信息、访问评分函数、训练脚本或示例训练日志:https://github.com/CannyLab/summary_loop
📄 许可证
本项目采用Apache-2.0
许可证。
属性 |
详情 |
模型类型 |
基于GPT2架构的摘要生成模型 |
训练数据 |
cnn_dailymail |
评估指标 |
ROUGE |
许可证 |
Apache-2.0 |