 artek0chumak
|
a43265a6ea
style
|
%!s(int64=2) %!d(string=hai) anos |
|
artek0chumak
|
d14debea35
Fixes and test
|
%!s(int64=2) %!d(string=hai) anos |
|
artek0chumak
|
a22ecc524d
Style
|
%!s(int64=2) %!d(string=hai) anos |
|
artek0chumak
|
1387711236
Workable version
|
%!s(int64=2) %!d(string=hai) anos |
|
artek0chumak
|
9b2f4f6791
saving
|
%!s(int64=2) %!d(string=hai) anos |
|
Artem Chumachenko
|
9de60e7895
Provide attention mask
|
%!s(int64=2) %!d(string=hai) anos |
|
artek0chumak
|
98b962631a
Style
|
%!s(int64=2) %!d(string=hai) anos |
|
artek0chumak
|
3a66dd19d4
Workable version
|
%!s(int64=2) %!d(string=hai) anos |
|
artek0chumak
|
d2d0403a11
saving
|
%!s(int64=2) %!d(string=hai) anos |
|
Artem Chumachenko
|
4e478782a4
Provide attention mask
|
%!s(int64=2) %!d(string=hai) anos |
 Alexander Borzunov
|
5d7395e1b5
Prompt-tuning notebooks: suggest to use a smaller model for faster prototyping (#234)
|
%!s(int64=2) %!d(string=hai) anos |
|
Artem Chumachenko
|
d4c687daca
Fix dtype error in fine-tuning notebooks (#231)
|
%!s(int64=2) %!d(string=hai) anos |
 Muhtasham Oblokulov
|
0ebf6de117
Add citation to readme (#219)
|
%!s(int64=2) %!d(string=hai) anos |
 justheuristic
|
c4938bc23e
Merge inference pools into one to increase inference speed (#225)
|
%!s(int64=2) %!d(string=hai) anos |
 Shuchang Zhou
|
3189b395f0
Fix a typo in error message (#227)
|
%!s(int64=2) %!d(string=hai) anos |
|
Alexander Borzunov
|
fa5ac6e3b4
Mention BLOOMZ in readme (#221)
|
%!s(int64=2) %!d(string=hai) anos |
|
Alexander Borzunov
|
e651d73f11
Add one more link to the "Getting started" tutorial (#218)
|
%!s(int64=2) %!d(string=hai) anos |
|
Alexander Borzunov
|
af3da5bb04
Choose --num_blocks automatically for all models (#217)
|
%!s(int64=2) %!d(string=hai) anos |
|
Alexander Borzunov
|
cea83d3356
Bump version to 1.1.1 (#214)
|
%!s(int64=2) %!d(string=hai) anos |
|
Alexander Borzunov
|
702bb5a2c2
CI: Update deprecated actions, don't measure network RPS (#215)
|
%!s(int64=2) %!d(string=hai) anos |
|
Alexander Borzunov
|
825f5dbf2d
CI: Convert model only when convert_model.py or setup.cfg change (#213)
|
%!s(int64=2) %!d(string=hai) anos |
|
Alexander Borzunov
|
5ff250bee9
Improve errors in case of missing blocks, suggest to join your own server (#212)
|
%!s(int64=2) %!d(string=hai) anos |
|
Alexander Borzunov
|
6ba63c6cc8
Fix output shape when resuming generation (#211)
|
%!s(int64=2) %!d(string=hai) anos |
|
Alexander Borzunov
|
cc5e5d32c0
Don't switch blocks if it makes swarm disjoint (#210)
|
%!s(int64=2) %!d(string=hai) anos |
|
Alexander Borzunov
|
6b12b0d050
Report server version and dht.client_mode in rpc_info(), check for updates on startup (#209)
|
%!s(int64=2) %!d(string=hai) anos |
|
justheuristic
|
771ca590e7
Add service checking direct reachability from peers (#195)
|
%!s(int64=2) %!d(string=hai) anos |
|
justheuristic
|
5f58f00649
Return available cache size in rpc_info() (#191)
|
%!s(int64=2) %!d(string=hai) anos |
|
Alexander Borzunov
|
37373a66c3
Update Anaconda installation commands (#205)
|
%!s(int64=2) %!d(string=hai) anos |
|
justheuristic
|
012f840f7e
Use length-weighted sampling in routing for inference (#204)
|
%!s(int64=2) %!d(string=hai) anos |
|
Alexander Borzunov
|
42d1bbb568
Fix --no_auto_relay help (#199)
|
%!s(int64=2) %!d(string=hai) anos |
