- Complete transformer implementation from scratch - Training pipeline with gradient accumulation and mixed precision - Optimized inference with KV caching - Multi-format data processing (PDFs, images, code, text) - Comprehensive documentation - Apache 2.0 license - Example training plots included in docs/images/
369 lines
1.8 KiB
Plaintext
369 lines
1.8 KiB
Plaintext
_10083
|
|
_10083-h
|
|
1996
|
|
1997
|
|
1998
|
|
1999
|
|
2000
|
|
2001
|
|
2002
|
|
2003
|
|
2004
|
|
20041201
|
|
2005
|
|
2006
|
|
2007
|
|
2008
|
|
2009
|
|
2010
|
|
2011
|
|
2012
|
|
2013
|
|
2014
|
|
2015
|
|
2016
|
|
2017
|
|
2018
|
|
2019
|
|
2020
|
|
2020-06-27
|
|
2020-12-19
|
|
2020-12-28
|
|
2021
|
|
2021-01-26
|
|
2021-01-27
|
|
2022
|
|
2023
|
|
2024
|
|
2025
|
|
aaaa
|
|
aaab
|
|
aaac
|
|
aaad
|
|
aaae
|
|
aaaf
|
|
aaag
|
|
aaah
|
|
aaai
|
|
aaaj
|
|
aaak
|
|
aaal
|
|
aaam
|
|
aaan
|
|
aaao
|
|
aaap
|
|
aaaq
|
|
aaar
|
|
aaas
|
|
aaat
|
|
aaau
|
|
aaav
|
|
aaaw
|
|
aaax
|
|
aaay
|
|
aaaz
|
|
aaba
|
|
aabb
|
|
aabc
|
|
aabd
|
|
aabe
|
|
aabf
|
|
aabg
|
|
aabh
|
|
aabi
|
|
aabj
|
|
aabk
|
|
aabl
|
|
aabm
|
|
aabn
|
|
aabo
|
|
aabp
|
|
aabq
|
|
aabr
|
|
aabs
|
|
aabt
|
|
aabu
|
|
aabv
|
|
aabw
|
|
aabx
|
|
aaby
|
|
aabz
|
|
aaca
|
|
aacb
|
|
aacc
|
|
aacd
|
|
aace
|
|
aacf
|
|
aacg
|
|
aach
|
|
aaci
|
|
aacj
|
|
aack
|
|
aacl
|
|
aacm
|
|
aacn
|
|
aaco
|
|
aacp
|
|
aacq
|
|
aacr
|
|
aacs
|
|
aact
|
|
aacu
|
|
aacv
|
|
aacw
|
|
aacx
|
|
aacy
|
|
aacz
|
|
aada
|
|
aadb
|
|
aadc
|
|
aadd
|
|
aade
|
|
aadf
|
|
aadg
|
|
aadh
|
|
aadi
|
|
aadj
|
|
aadk
|
|
aadl
|
|
aadm
|
|
aadn
|
|
aado
|
|
aadp
|
|
aadq
|
|
aadr
|
|
aads
|
|
aadt
|
|
aadu
|
|
aadv
|
|
aadw
|
|
aadx
|
|
aady
|
|
aadz
|
|
aaea
|
|
aaeb
|
|
aaec
|
|
aaed
|
|
aaee
|
|
aaef
|
|
aaeg
|
|
aaeh
|
|
aaei
|
|
aaej
|
|
aaek
|
|
aael
|
|
aaem
|
|
aaen
|
|
aaeo
|
|
aaep
|
|
aaeq
|
|
aaer
|
|
aaes
|
|
aaet
|
|
aaeu
|
|
aaev
|
|
aaew
|
|
aaex
|
|
aaey
|
|
aaez
|
|
aafa
|
|
aafb
|
|
aafc
|
|
aafd
|
|
aafe
|
|
aaff
|
|
aafg
|
|
aafh
|
|
aafi
|
|
aafj
|
|
aafk
|
|
aafl
|
|
aafm
|
|
aafn
|
|
aafo
|
|
aafp
|
|
aafq
|
|
aafr
|
|
aafs
|
|
aaft
|
|
aafu
|
|
aafv
|
|
aafw
|
|
aafx
|
|
aafy
|
|
aafz
|
|
aaga
|
|
aagb
|
|
aagc
|
|
aagd
|
|
aage
|
|
aagf
|
|
aagg
|
|
aagh
|
|
aagi
|
|
aagj
|
|
aagk
|
|
aagl
|
|
aagm
|
|
aagn
|
|
aago
|
|
aagp
|
|
aagq
|
|
aagr
|
|
aags
|
|
aagt
|
|
aagu
|
|
aagv
|
|
aagw
|
|
aagx
|
|
aagy
|
|
aagz
|
|
aaha
|
|
aahb
|
|
aahc
|
|
aahd
|
|
aahe
|
|
aahf
|
|
aahg
|
|
aahh
|
|
aahi
|
|
aahj
|
|
aahk
|
|
aahl
|
|
aahm
|
|
aahn
|
|
aaho
|
|
aahp
|
|
aahq
|
|
aahr
|
|
aahs
|
|
aaht
|
|
aahu
|
|
aahv
|
|
aahw
|
|
aahx
|
|
aahy
|
|
aahz
|
|
aaia
|
|
aaib
|
|
aaic
|
|
aaid
|
|
aaie
|
|
aaif
|
|
aaig
|
|
aaih
|
|
aaii
|
|
aaij
|
|
aaik
|
|
aail
|
|
aaim
|
|
aain
|
|
aaio
|
|
aaip
|
|
aaiq
|
|
aair
|
|
aais
|
|
aait
|
|
aaiu
|
|
aaiv
|
|
aaiw
|
|
aaix
|
|
aaiy
|
|
aaiz
|
|
aaja
|
|
aajb
|
|
aajc
|
|
aajd
|
|
aaje
|
|
aajf
|
|
aajg
|
|
aajh
|
|
aaji
|
|
aajj
|
|
aajk
|
|
aajl
|
|
aajm
|
|
aajn
|
|
aajo
|
|
aajp
|
|
aajq
|
|
aajr
|
|
aajs
|
|
aajt
|
|
aaju
|
|
aajv
|
|
aajw
|
|
aajx
|
|
aajy
|
|
aajz
|
|
aaka
|
|
aakb
|
|
aakc
|
|
aakd
|
|
aake
|
|
aakf
|
|
aakg
|
|
aakh
|
|
aaki
|
|
aakj
|
|
aakk
|
|
aakl
|
|
aakm
|
|
aakn
|
|
aako
|
|
aakp
|
|
ALL
|
|
AUS
|
|
brl
|
|
bz2
|
|
cache
|
|
css
|
|
db
|
|
dcs
|
|
doc
|
|
DS_Store
|
|
eps
|
|
gif
|
|
gz
|
|
htm
|
|
ico
|
|
_images
|
|
iso
|
|
jigdo
|
|
jpg
|
|
JPG
|
|
jsonl
|
|
lit
|
|
ly
|
|
md5
|
|
message
|
|
mid
|
|
mp3
|
|
_old
|
|
PAR
|
|
PAR2
|
|
pdf
|
|
png
|
|
prc
|
|
py
|
|
pyc
|
|
rar
|
|
rtf
|
|
selected_editor
|
|
sfv
|
|
sh
|
|
sib
|
|
static
|
|
svg
|
|
tar
|
|
template
|
|
tex
|
|
txt
|
|
txt~
|
|
TXT
|
|
xml
|
|
zcompdump
|
|
zip
|
|
zip~
|
|
zshrc
|
|
zst |