newbietuan
newbietuan
Hi, Thanks for the great work. Due to the needs of specific tasks, i want to train CLIP from scratch without using BPE coding and the length limit of 77,...
Hello, thanks for the great dataset,you said "a fully-connected layer is used for transforming the [CLS] token representation to the matching score", can you explain this step in more detail?...
**Describe the bug**  when i run the demo code,there something wrong about “nlp.add_pipe(quickumls_component)”, Traceback (most recent call last): File "umlsdemo.py", line 8, in nlp.add_pipe(quickumls_component) File "/home/mayt/anaconda3/envs/umls/lib/python3.7/site-packages/spacy/language.py", line 769, in...
hello there, thank for your good work. i want to download a small portion of cc(to run through the whole process firstly) when i run the code 'python -m cc_net...
hello, there. i want to get the zh data of one dump. How much disk space will be occupied during data download and processing, and the final data size