基于GPT2的中文摘要生成模型

上传者: plawuyue | 上传时间: 2024-04-07 20:01:34 | 文件大小: 482KB | 文件类型: ZIP
本项目使用 GPT2-Chinese 的模型将wiki中文的数据导入模型训练了通用模型。 将GPT2-chitchat的对话任务稍作修改来适用于中文摘要任务。 将通用模型的权重应用在摘要问题上进行进一步训练的。 GPT2-Chinese 参考:https://github.com/Morizeyao/GPT2-Chinese GPT2-chitchat参考:https://link.zhihu.com/?target=https%3A//github.com/yangjianxin1/GPT2-chitchat 项目工作流程详见:https://zhuanlan.zhihu.com/p/113869509 本项目为GPT2-chitchat稍作修改的内容,在此也感谢大佬的分享。 由于NLPCC的摘要数据为新闻语料,涉及话题和内容较多,应用在垂直领域下效果会好一些。

文件下载

资源详情

[{"title":"( 109 个子文件 482KB ) 基于GPT2的中文摘要生成模型","children":[{"title":"model_config_dialogue_small.json <span style='color:#111;'> 175B </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 7.49KB </span>","children":null,"spread":false},{"title":"modeling_xlnet.py <span style='color:#111;'> 80.14KB </span>","children":null,"spread":false},{"title":"tokenization_utils.py <span style='color:#111;'> 68.48KB </span>","children":null,"spread":false},{"title":"modeling_bert.py <span style='color:#111;'> 68.39KB </span>","children":null,"spread":false},{"title":"modeling_utils.py <span style='color:#111;'> 67.55KB </span>","children":null,"spread":false},{"title":"modeling_auto.py <span style='color:#111;'> 61.87KB </span>","children":null,"spread":false},{"title":"modeling_tf_xlnet.py <span style='color:#111;'> 58.51KB </span>","children":null,"spread":false},{"title":"modeling_tf_auto.py <span style='color:#111;'> 57.01KB </span>","children":null,"spread":false},{"title":"modeling_tf_bert.py <span style='color:#111;'> 54.53KB </span>","children":null,"spread":false},{"title":"modeling_xlm.py <span style='color:#111;'> 45.72KB </span>","children":null,"spread":false},{"title":"modeling_t5.py <span style='color:#111;'> 42.64KB </span>","children":null,"spread":false},{"title":"modeling_transfo_xl.py <span style='color:#111;'> 39.76KB </span>","children":null,"spread":false},{"title":"modeling_albert.py <span style='color:#111;'> 39.18KB </span>","children":null,"spread":false},{"title":"modeling_tf_distilbert.py <span style='color:#111;'> 37.93KB </span>","children":null,"spread":false},{"title":"modeling_tf_xlm.py <span style='color:#111;'> 37.76KB </span>","children":null,"spread":false},{"title":"modeling_distilbert.py <span style='color:#111;'> 37.72KB </span>","children":null,"spread":false},{"title":"modeling_tf_albert.py <span style='color:#111;'> 37.27KB </span>","children":null,"spread":false},{"title":"modeling_tf_t5.py <span style='color:#111;'> 37.05KB </span>","children":null,"spread":false},{"title":"pipelines.py <span style='color:#111;'> 35.95KB </span>","children":null,"spread":false},{"title":"modeling_roberta.py <span style='color:#111;'> 35.50KB </span>","children":null,"spread":false},{"title":"modeling_tf_transfo_xl.py <span style='color:#111;'> 34.55KB </span>","children":null,"spread":false},{"title":"modeling_gpt2.py <span style='color:#111;'> 33.20KB </span>","children":null,"spread":false},{"title":"modeling_tf_gpt2.py <span style='color:#111;'> 31.36KB </span>","children":null,"spread":false},{"title":"tokenization_xlm.py <span style='color:#111;'> 30.51KB </span>","children":null,"spread":false},{"title":"modeling_openai.py <span style='color:#111;'> 30.43KB </span>","children":null,"spread":false},{"title":"modeling_tf_openai.py <span style='color:#111;'> 29.28KB </span>","children":null,"spread":false},{"title":"modeling_tf_utils.py <span style='color:#111;'> 29.02KB </span>","children":null,"spread":false},{"title":"squad_metrics.py <span style='color:#111;'> 28.03KB </span>","children":null,"spread":false},{"title":"squad.py <span style='color:#111;'> 26.62KB </span>","children":null,"spread":false},{"title":"modeling_ctrl.py <span style='color:#111;'> 23.63KB </span>","children":null,"spread":false},{"title":"modeling_tf_ctrl.py <span style='color:#111;'> 23.50KB </span>","children":null,"spread":false},{"title":"tokenization_bert.py <span style='color:#111;'> 22.30KB </span>","children":null,"spread":false},{"title":"modeling_tf_roberta.py <span style='color:#111;'> 22.03KB </span>","children":null,"spread":false},{"title":"tokenization_transfo_xl.py <span style='color:#111;'> 21.02KB </span>","children":null,"spread":false},{"title":"modeling_mmbt.py <span style='color:#111;'> 20.82KB </span>","children":null,"spread":false},{"title":"train.py <span style='color:#111;'> 20.47KB </span>","children":null,"spread":false},{"title":"glue.py <span style='color:#111;'> 19.40KB </span>","children":null,"spread":false},{"title":"modeling_xlm_roberta.py <span style='color:#111;'> 18.32KB </span>","children":null,"spread":false},{"title":"modeling_encoder_decoder.py <span style='color:#111;'> 17.53KB </span>","children":null,"spread":false},{"title":"modeling_camembert.py <span style='color:#111;'> 17.29KB </span>","children":null,"spread":false},{"title":"convert_pytorch_checkpoint_to_tf2.py <span style='color:#111;'> 16.10KB </span>","children":null,"spread":false},{"title":"file_utils.py <span style='color:#111;'> 13.42KB </span>","children":null,"spread":false},{"title":"configuration_utils.py <span style='color:#111;'> 13.13KB </span>","children":null,"spread":false},{"title":"modeling_transfo_xl_utilities.py <span style='color:#111;'> 12.88KB </span>","children":null,"spread":false},{"title":"modeling_tf_pytorch_utils.py <span style='color:#111;'> 12.71KB </span>","children":null,"spread":false},{"title":"utils.py <span style='color:#111;'> 12.62KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 12.22KB </span>","children":null,"spread":false},{"title":"interact_mmi.py <span style='color:#111;'> 12.00KB </span>","children":null,"spread":false},{"title":"configuration_auto.py <span style='color:#111;'> 11.98KB </span>","children":null,"spread":false},{"title":"modelcard.py <span style='color:#111;'> 11.06KB </span>","children":null,"spread":false},{"title":"optimization_tf.py <span style='color:#111;'> 9.75KB </span>","children":null,"spread":false},{"title":"tokenization_albert.py <span style='color:#111;'> 9.70KB </span>","children":null,"spread":false},{"title":"tokenization_auto.py <span style='color:#111;'> 9.53KB </span>","children":null,"spread":false},{"title":"tokenization_gpt2.py <span style='color:#111;'> 9.43KB </span>","children":null,"spread":false},{"title":"tokenization_bert_japanese.py <span style='color:#111;'> 9.42KB </span>","children":null,"spread":false},{"title":"tokenization_xlnet.py <span style='color:#111;'> 9.26KB </span>","children":null,"spread":false},{"title":"tokenization_xlm_roberta.py <span style='color:#111;'> 8.81KB </span>","children":null,"spread":false},{"title":"tokenization_ctrl.py <span style='color:#111;'> 7.83KB </span>","children":null,"spread":false},{"title":"interact.py <span style='color:#111;'> 7.79KB </span>","children":null,"spread":false},{"title":"convert_roberta_original_pytorch_checkpoint_to_pytorch.py <span style='color:#111;'> 7.73KB </span>","children":null,"spread":false},{"title":"modeling_tf_transfo_xl_utilities.py <span style='color:#111;'> 7.68KB </span>","children":null,"spread":false},{"title":"tokenization_openai.py <span style='color:#111;'> 7.66KB </span>","children":null,"spread":false},{"title":"tokenization_camembert.py <span style='color:#111;'> 7.63KB </span>","children":null,"spread":false},{"title":"optimization.py <span style='color:#111;'> 7.50KB </span>","children":null,"spread":false},{"title":"configuration_xlm.py <span style='color:#111;'> 6.83KB </span>","children":null,"spread":false},{"title":"tokenization_roberta.py <span style='color:#111;'> 6.78KB </span>","children":null,"spread":false},{"title":"tokenization_t5.py <span style='color:#111;'> 6.66KB </span>","children":null,"spread":false},{"title":"configuration_bert.py <span style='color:#111;'> 6.40KB </span>","children":null,"spread":false},{"title":"serving.py <span style='color:#111;'> 6.40KB </span>","children":null,"spread":false},{"title":"user.py <span style='color:#111;'> 6.29KB </span>","children":null,"spread":false},{"title":"convert.py <span style='color:#111;'> 6.26KB </span>","children":null,"spread":false},{"title":"train.py <span style='color:#111;'> 5.69KB </span>","children":null,"spread":false},{"title":"configuration_transfo_xl.py <span style='color:#111;'> 5.60KB </span>","children":null,"spread":false},{"title":"hf_api.py <span style='color:#111;'> 5.40KB </span>","children":null,"spread":false},{"title":"configuration_xlnet.py <span style='color:#111;'> 5.39KB </span>","children":null,"spread":false},{"title":"configuration_gpt2.py <span style='color:#111;'> 4.93KB </span>","children":null,"spread":false},{"title":"configuration_albert.py <span style='color:#111;'> 4.84KB </span>","children":null,"spread":false},{"title":"convert_transfo_xl_original_tf_checkpoint_to_pytorch.py <span style='color:#111;'> 4.80KB </span>","children":null,"spread":false},{"title":"configuration_ctrl.py <span style='color:#111;'> 4.68KB </span>","children":null,"spread":false},{"title":"configuration_t5.py <span style='color:#111;'> 4.04KB </span>","children":null,"spread":false},{"title":"convert_bert_pytorch_checkpoint_to_original_tf.py <span style='color:#111;'> 4.02KB </span>","children":null,"spread":false},{"title":"configuration_openai.py <span style='color:#111;'> 4.01KB </span>","children":null,"spread":false},{"title":"convert_xlnet_original_tf_checkpoint_to_pytorch.py <span style='color:#111;'> 3.60KB </span>","children":null,"spread":false},{"title":"run.py <span style='color:#111;'> 3.59KB </span>","children":null,"spread":false},{"title":"xnli.py <span style='color:#111;'> 2.90KB </span>","children":null,"spread":false},{"title":"convert_xlm_original_pytorch_checkpoint_to_pytorch.py <span style='color:#111;'> 2.90KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 2.85KB </span>","children":null,"spread":false},{"title":"configuration_distilbert.py <span style='color:#111;'> 2.76KB </span>","children":null,"spread":false},{"title":"generate_dialogue_subset.py <span style='color:#111;'> 2.61KB </span>","children":null,"spread":false},{"title":"tokenization_distilbert.py <span style='color:#111;'> 2.58KB </span>","children":null,"spread":false},{"title":"convert_openai_original_tf_checkpoint_to_pytorch.py <span style='color:#111;'> 2.58KB </span>","children":null,"spread":false},{"title":"convert_gpt2_original_tf_checkpoint_to_pytorch.py <span style='color:#111;'> 2.45KB </span>","children":null,"spread":false},{"title":"convert_albert_original_tf_checkpoint_to_pytorch.py <span style='color:#111;'> 2.11KB </span>","children":null,"spread":false},{"title":"convert_bert_original_tf_checkpoint_to_pytorch.py <span style='color:#111;'> 2.09KB </span>","children":null,"spread":false},{"title":"convert_t5_original_tf_checkpoint_to_pytorch.py <span style='color:#111;'> 2.05KB </span>","children":null,"spread":false},{"title":"configuration_xlm_roberta.py <span style='color:#111;'> 1.83KB </span>","children":null,"spread":false},{"title":"configuration_roberta.py <span style='color:#111;'> 1.65KB </span>","children":null,"spread":false},{"title":"configuration_mmbt.py <span style='color:#111;'> 1.31KB </span>","children":null,"spread":false},{"title":"download.py <span style='color:#111;'> 1.24KB </span>","children":null,"spread":false},{"title":"......","children":null,"spread":false},{"title":"<span style='color:steelblue;'>文件过多,未全部展示</span>","children":null,"spread":false}],"spread":true}]

评论信息

免责申明

【只为小站】的资源来自网友分享,仅供学习研究,请务必在下载后24小时内给予删除,不得用于其他任何用途,否则后果自负。基于互联网的特殊性,【只为小站】 无法对用户传输的作品、信息、内容的权属或合法性、合规性、真实性、科学性、完整权、有效性等进行实质审查;无论 【只为小站】 经营者是否已进行审查,用户均应自行承担因其传输的作品、信息、内容而可能或已经产生的侵权或权属纠纷等法律责任。
本站所有资源不代表本站的观点或立场,基于网友分享,根据中国法律《信息网络传播权保护条例》第二十二条之规定,若资源存在侵权或相关问题请联系本站客服人员,zhiweidada#qq.com,请把#换成@,本站将给予最大的支持与配合,做到及时反馈和处理。关于更多版权及免责申明参见 版权及免责申明