zhangce

sgeadmin@master:~/CaffeConTroll$ ./caffe-ct train caffe_inputs/lenet_solver.prototxt Start writing 60000 to toprocess.bin... Finished writing images to toprocess.bin... Constructing CONV layer with Grouping = 1 (# Input Grouping=1) Constructing MAXPOOLING (# Input Grouping=1) Constructing...

TODO: Better Documentation for hyperparameters and fine tuning

3

1. How to reproduce HF App's behavior (hyper-parameters, exact prompt) 2. How to fine-tune models given a new corpus + things to be careful about and best practice

TODO: Add in the training script for the moderation model

deadlock

2

Given a rule like ``` A(x text). B(x text). C(x text). C(x) :- B(x). A(x) :- C(x). C(x) :- A(x). ``` I think the code currently deadlock. It is a...

Thanks [visarga](https://news.ycombinator.com/user?id=visarga) for the suggestion: https://news.ycombinator.com/item?id=38077521 - summary, for better topic embedding - named entities, for knowledge base - implicit tasks present in the text, what are the tasks a...