Commit Graph

341 Commits (b03efb1ef500aa65e120a38aa09f340552249542)
 

Author SHA1 Message Date
justheuristic 8092bd31ff swap to int64 (rationale: pytorch does not support uint64) 2 years ago
justheuristic 62d7fde8af pre-check type 2 years ago
justheuristic 7fba411dff extended run_serverexample 2 years ago
justheuristic 20497f81d1 switch to hivemind-master 2 years ago
justheuristic 5a15c13ca7 switch to hivemind-master 2 years ago
Pavel Samygin 57f4e0a899 add identity path 2 years ago
justheuristic 35310698f0 newer hivemind version 2 years ago
justheuristic 8959727dea add minimalistic benchmarks 2 years ago
justheuristic a798ea04a6 add minimalistic benchmarks 2 years ago
justheuristic e3a7d5af30 inference mode 2 years ago
justheuristic 3b16d6ffdb black-isort 2 years ago
justheuristic a28ea0aa6f
Merge pull request #9 from learning-at-home/rpc
Rudimentary decentralization
2 years ago
justheuristic 14e316b52a black-isort 2 years ago
justheuristic eea9287182 RemoteTransformerBlock 2 years ago
justheuristic 3e9fd63a02 RemoteTransformerBlock 2 years ago
justheuristic 1cca611c9f undo rename 2 years ago
justheuristic 7ce7cd7a97 basic backend 2 years ago
justheuristic 1c49bcb741 basic backend 2 years ago
justheuristic 3215945882 use logger 2 years ago
justheuristic ce5dedd2c7 rename 2 years ago
justheuristic 8f5d022d18 save hidden size 2 years ago
justheuristic e2e9d0e94c memory cache for attention KVs 2 years ago
justheuristic e5e8c9ed12 expel all bloom-specific files to src.bloom 2 years ago
justheuristic 324ea2dc96 save non-transformer params separately 2 years ago
justheuristic 54cf292374 backend schema 2 years ago
justheuristic 3ccd0b5e2d account for layer_past in alibi 2 years ago
justheuristic fb3bfbb78f optimization TODOs for later 2 years ago
justheuristic 902bf6400a [temp workaround] create alibi 2 years ago
justheuristic 05faa0b3c8 add quantization script for cpu 2 years ago
justheuristic ffb56a65ed keep hidden_size as property 2 years ago
justheuristic ffce7718ac layer.py -> block.py 2 years ago
justheuristic 9c929b6f3b layer.py -> bloom_block.py 2 years ago
justheuristic 79925fc5f7 [more disclaimers] 2 years ago
justheuristic fde9d50850 remove slow_but_exact, add quantization 2 years ago
justheuristic 43399d7898 remove slow_but_exact, add quantization 2 years ago
justheuristic 51e96ac19b adopt transformers bloom model
Co-authored-by: Thomwolf <thomwolf@gmail.com>
Co-authored-by: Thomas Wolf <thomas@huggingface.co>
Co-authored-by: thomasw21 <24695242+thomasw21@users.noreply.github.com>
Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>
Co-authored-by: sIncerass <sheng.s@berkeley.edu>
Co-authored-by: Stas Bekman <stas00@users.noreply.github.com>
Co-authored-by: Niklas Muennighoff <n.muennighoff@gmail.com>
Co-authored-by: Nicolas Patry <Narsil@users.noreply.github.com>
Co-authored-by: thomasw21 <thomasw21@users.noreply.github.com>
Co-authored-by: sgugger <sgugger@users.noreply.github.com>
Co-authored-by: patrickvonplaten <patrickvonplaten@users.noreply.github.com>
Co-authored-by: LysandreJik <LysandreJik@users.noreply.github.com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: justheuristic <justheuristic@gmail.com>
Co-authored-by: Stas Bekman <stas@stason.org>
2 years ago
justheuristic 99059ae667 install script 2 years ago
justheuristic 71717c5f00 Merge remote-tracking branch 'origin/main' into main 2 years ago
justheuristic b370b43110 freeze hivemind and transformers versions 2 years ago
justheuristic c1a908dc66
Update README.md 2 years ago
justheuristic af04479cf9
Initial commit 2 years ago