Han

[seq2seq translate] - cannot unsqueeze empty tensor

6

### Hi all, I'm trying to run the seq 2seq model. (seq2seq-translation-batched.ipnb) My environment is python 3.6.4, torch 0.4.0 And I make some modification: 1. disable anything related to CUDA...

Is this module support "traditional\simplified chinese" identification

3

請問是否支援繁體\簡體中文辨識功能? 我嘗試找一些 python 的方案，但沒看到合適的 ...

匯入自定義字詞\用語功能

1

請問是否有文件說明如何導入自定義的 字\詞\用語 對照表? 若沒有，是否有計畫要提供? 或是簡述基本匯入流程也可以。 感謝!

Hi, I follow the instructions on [SAML SSO with Auth0 as Service Provider and as an Identity Provider](https://auth0.com/docs/protocols/saml/samlsso-auth0-to-auth0#1-establish-two-auth0-tenants) Everything is fine until I try step 9 [Test your sample application](https://auth0.com/docs/protocols/saml/samlsso-auth0-to-auth0#1-establish-two-auth0-tenants)...

I try to apply your work to other language. Is it possible for me to use existing models shown in README, fine-tuning them with my data. Any suggestion is appreciated.

自動摘要 fine tune

1

請教一下， 有看到您提供的 text summarization sample code，想問問如果要加入自己的文章進行 fine tune 應該要如何進行? 如果是 abstractive summarization，應該可以參考這個吧? https://huggingface.co/course/chapter7/5?fw=tf 若是 extractive summarization，那我就不知道怎麼做了....

As title, Is it possible to use these pre-train word vectors to creata a pre-train model. Then use my own documents to finetune the model? Any suggestion is appreciated.

個人理解，目前的作法為 BoW 還是我只要把 `get_similarity` 改寫即可?

您好 我所處理的文章，通常在正式的內容中還會夾雜一些與文章主題本身相關性較小的"廢文" 主要是用來吸引讀者，確保他們能夠看到最後 然而，這樣的文章 直接套您的工具的話，會導致一些無關緊要的字句排到很前面 因此想請教一下，是否能狗透過一些手段，提供 model 一點 guide 達到類似於 semi-supervised 的效果?

Since I cannot find any "rules" from the examples on README, I suppose that I can choose any pre-train model I want from HuggingFace regardless of which kind of task...