yuxuan2015
yuxuan2015
### Rasa Open Source version rasa 2.3.1 ### Rasa SDK version rasa-sdk 2.3.1 ### Python version 3.6 ### What operating system are you using? Linux ### What happened? When I...
在lang.py添加"zh": "chinese",支持自动加载中文停用词,解决candidate_filtering的421行;stoplist为none的情况
Traceback (most recent call last): File "/data/git/text_similarity/kaggle-quora-question-pairs/bin/feature_engineering/graph.py", line 332, in demo() File "/data/git/text_similarity/kaggle-quora-question-pairs/bin/feature_engineering/graph.py", line 327, in demo GraphEdgeMaxCliqueSize(config_fp).extract('train') File "/data/git/text_similarity/kaggle-quora-question-pairs/bin/feature_engineering/graph.py", line 135, in __init__ UDG.__init__(self, config_fp) File "/data/git/text_similarity/kaggle-quora-question-pairs/bin/feature_engineering/graph.py", line 127,...
训练时间过长
当nlu的语料>20000条,训练的时候,如果不用ONNX模型花费的时间为15分钟,使用ONNX模型需要花费2个多小时,即使用GPU也是这样,这个有什么优化方法吗? ![企业微信截图_16448316568471](https://user-images.githubusercontent.com/15645056/153839605-413d0812-470d-4b9a-b717-10497146f943.png)
WARNING:tensorflow:Issue encountered when serializing global_step. Type is unsupported, or the types of the items don't match field type in CollectionDef. Note this is a warning and probably safe to ignore....
例如,text = "我说我下班七点下班",我想要得到"七点"和"2019-12-23 19:00:00",请问怎么把"七点"也输出来?
torchrun --nproc_per_node gpu example.py --ckpt_dir pyllama_data/7B --tokenizer_path pyllama_data/tokenizer.model Traceback (most recent call last): File "/data1/Semantic_team/speech/chatgpt/llama/example.py", line 119, in Traceback (most recent call last): File "/data1/Semantic_team/speech/chatgpt/llama/example.py", line 119, in fire.Fire(main) File...
![企业微信截图_16238418703954](https://user-images.githubusercontent.com/15645056/122209096-b3cfdf00-ced6-11eb-882a-62bfc3e9110f.png)