Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
montebicyclelo
on April 26, 2023
|
parent
|
context
|
favorite
| on:
Transformers from Scratch (2021)
Huggingface have good guides on tokenization, and tokenizer training. BPE (e.g. used by gpt) and wordpiece (e.g. used by bert) are two commonly used methods
https://huggingface.co/learn/nlp-course/chapter6/5?fw=pt
Consider applying for YC's W25 batch! Applications are open till Nov 12.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
