NiklausDu

Results 7 issues of NiklausDu

请问有TensorFlow版本的萝卜塔英文预训练权重么?或者还未开源

pre-train masked language with BERT: python train_bert_lm.py [DONE] 请问这里的 [DONE] 是什么意思,.py脚本后不需要跟文件路径么?望指点。

对中英文混合的文本分类(主要是中午,夹杂一些英文关键词,如:我喜欢用TensorFlow框架进行机器学习任务。),encode文本的时候有以下问题,请教下: 1. 当前任务,推荐是使用提供多语言版本模型还是使用chinese版本模型? 2. 中英文文本的token切分是char-level还是word-level,具体机制是什么?自己尝试的例子出现: [['[CLS]', 'hell', '##o', 'world', '!', '[SEP]'], ['[CLS]', '我', '在', '吃', '饭', '[SEP]']] 3. 部分英文词汇属于重要的关键词,当前属于UNK,不能丢弃,请问该项目支持加自定义的词汇么?

您好,有几个问题请教下: 1.在分布式web server为何RedisStreamer类的init方法中未传入batch_size, max_latency,cuda_devices等参数 2.service-streamer.py中的run_redis_workers_forever方法应该是需要在RedisStreamer类初始化时调用,但是为何从未在任何地方调用?

File "/media/huaxin/tcl2/nlp/dumingyu_project/bertlk/web_service/advanced_deploy_api.py", line 76, in streamer = Streamer(model.predict, batch_size=8, max_latency=0.1, worker_num=1) File "/media/huaxin/tcl2/nlp/dumingyu_project/bertlk/web_service/service_streamer.py", line 296, in __init__ self._setup_gpu_worker() File "/media/huaxin/tcl2/nlp/dumingyu_project/bertlk/web_service/service_streamer.py", line 311, in _setup_gpu_worker p.start() File "/media/huaxin/tcl2/nlp/anaconda3/lib/python3.6/multiprocessing/process.py", line 105, in...

**Describe the bug** Running Quickstart.ipynb - Start new indexing job. When I checked the progress yesterday, it was 6.25%. It has been 24 hours now, and it is still 6.25%!...

bug