Ecosyste.ms: Issues

An open API service for providing issue and pull request metadata for open source projects.

GitHub / jopetty/growing-tokens issues and pull requests

#24 - Update README.md

Pull Request - State: closed - Opened by jopetty 6 months ago

#23 - fdsa

Pull Request - State: closed - Opened by jopetty 7 months ago

#22 - Remove unks

Pull Request - State: closed - Opened by craaaa 7 months ago

#21 - Logging

Pull Request - State: closed - Opened by jopetty 7 months ago

#20 - Fix space splitter

Pull Request - State: closed - Opened by craaaa 7 months ago

#19 - Logging works

Pull Request - State: closed - Opened by jopetty 7 months ago

#18 - fix alpha issue

Pull Request - State: closed - Opened by jopetty 7 months ago

#17 - Add linear vocab growth baseline

Pull Request - State: closed - Opened by craaaa 7 months ago

#16 - optimized merger

Pull Request - State: closed - Opened by jopetty 7 months ago

#15 - add mpl, formatting

Pull Request - State: closed - Opened by jopetty 7 months ago

#14 - Fixes

Pull Request - State: closed - Opened by jopetty 7 months ago

#13 - Initial alphabet isn't normalized

Issue - State: open - Opened by craaaa 7 months ago

#12 - Do tokens split across spaces?

Issue - State: open - Opened by craaaa 7 months ago

#11 - added vocab updater

Pull Request - State: closed - Opened by wtimkey 7 months ago

#10 - Morphology metrics + reference loading

Pull Request - State: closed - Opened by craaaa 7 months ago - 1 comment

#9 - Pt

Pull Request - State: closed - Opened by jopetty 7 months ago

#8 - Add tokenizer scoring metrics

Pull Request - State: closed - Opened by craaaa 7 months ago - 1 comment

#7 - Cleaning babylm data

Issue - State: open - Opened by wtimkey 7 months ago

#6 - Tokenization comparison metrics

Issue - State: closed - Opened by craaaa 7 months ago

#5 - retokenize every k steps

Issue - State: open - Opened by jopetty 7 months ago

#4 - Training baselines

Issue - State: open - Opened by jopetty 7 months ago

#3 - BPE Tokenizer Trainer

Pull Request - State: closed - Opened by craaaa 7 months ago

#2 - first pass at a training loop

Pull Request - State: closed - Opened by jopetty 8 months ago

#1 - Tokenizer baselines

Issue - State: closed - Opened by craaaa 8 months ago