Bruno Cabral
Bruno Cabral
@My-Khan , You need to create a script yourself for injecting this kind of feature in your "mytrain.txt"
Yeah, I have been bitten by this too. Any chance of fixing it on a upcoming version?
@Optimox sorry for the bump, but do you have plans of merging this? I +1 on improvements on my particular problem 😄
I use for a Fintech credit model. I got an extra 5% in RMSE compared to master ( I ported this patch to Regression) It still not beat a well...
+1. This is a blocker for us, as we heavily use the SQLAlchemy 2. Talking about that, pynecone should drop the tiangolo/sqlmodel. This is an unmaintained project, and it is...
Just my +1 , generation speed improvement, especially with torch 2.0 is something very nice for make the model production ready
There is any chance of this making into the main branch? I and other confirmed that the results are real. Thank you @winglian
Thank you @GeekDuanLian
@usptact , I think he already did. https://github.com/tianjianjiang/crfsuite-openmp
@usptact could you please share what command line you used for ner with Vowpal? I was never able to come with a working command line for taggging.