mirror of
https://github.com/hpcaitech/ColossalAI.git
synced 2025-04-29 04:05:35 +00:00
* benchmark gpt2 * fix fix fix fix * [doc] fix typo in Colossal-LLaMA-2/README.md (#5247) * [workflow] fixed build CI (#5240) * [workflow] fixed build CI * polish * polish * polish * polish * polish * [ci] fixed booster test (#5251) * [ci] fixed booster test * [ci] fixed booster test * [ci] fixed booster test * [ci] fixed ddp test (#5254) * [ci] fixed ddp test * polish * fix typo in applications/ColossalEval/README.md (#5250) * [ci] fix shardformer tests. (#5255) * fix ci fix * revert: revert p2p * feat: add enable_metadata_cache option * revert: enable t5 tests --------- Co-authored-by: Wenhao Chen <cwher@outlook.com> * [doc] fix doc typo (#5256) * [doc] fix annotation display * [doc] fix llama2 doc * [hotfix]: add pp sanity check and fix mbs arg (#5268) * fix: fix misleading mbs arg * feat: add pp sanity check * fix: fix 1f1b sanity check * [workflow] fixed incomplete bash command (#5272) * [workflow] fixed oom tests (#5275) * [workflow] fixed oom tests * polish * polish * polish * [ci] fix test_hybrid_parallel_plugin_checkpoint_io.py (#5276) * fix ci fix * fix test * revert: revert p2p * feat: add enable_metadata_cache option * revert: enable t5 tests * fix --------- Co-authored-by: Wenhao Chen <cwher@outlook.com> * [shardformer] hybridparallelplugin support gradients accumulation. (#5246) * support gradients acc fix fix fix fix fix fix fix fix fix fix fix fix fix * fix fix * fix fix fix * [hotfix] Fix ShardFormer test execution path when using sequence parallelism (#5230) * fix auto loading gpt2 tokenizer (#5279) * [doc] add llama2-13B disyplay (#5285) * Update README.md * fix 13b typo --------- Co-authored-by: binmakeswell <binmakeswell@gmail.com> * fix llama pretrain (#5287) * fix * fix * fix fix * fix fix fix * fix fix * benchmark gpt2 * fix fix fix fix * [workflow] fixed build CI (#5240) * [workflow] fixed build CI * polish * polish * polish * polish * polish * [ci] fixed booster test (#5251) * [ci] fixed booster test * [ci] fixed booster test * [ci] fixed booster test * fix fix * fix fix fix * fix * fix fix fix fix fix * fix * Update shardformer.py --------- Co-authored-by: digger yu <digger-yu@outlook.com> Co-authored-by: Frank Lee <somerlee.9@gmail.com> Co-authored-by: Wenhao Chen <cwher@outlook.com> Co-authored-by: binmakeswell <binmakeswell@gmail.com> Co-authored-by: Zhongkai Zhao <kanezz620@gmail.com> Co-authored-by: Michelle <97082656+MichelleMa8@users.noreply.github.com> Co-authored-by: Desperado-Jia <502205863@qq.com>
33 lines
713 B
Python
33 lines
713 B
Python
from contextlib import contextmanager
|
|
|
|
import torch
|
|
import torch.nn as nn
|
|
|
|
|
|
@contextmanager
|
|
def low_precision_init(target_dtype: torch.dtype = torch.float16):
|
|
dtype = torch.get_default_dtype()
|
|
try:
|
|
torch.set_default_dtype(target_dtype)
|
|
yield
|
|
finally:
|
|
torch.set_default_dtype(dtype)
|
|
|
|
|
|
def get_model_numel(model: nn.Module) -> int:
|
|
return sum(p.numel() for p in model.parameters())
|
|
|
|
|
|
def format_numel_str(numel: int) -> str:
|
|
B = 1024**3
|
|
M = 1024**2
|
|
K = 1024
|
|
if numel >= B:
|
|
return f"{numel / B:.2f} B"
|
|
elif numel >= M:
|
|
return f"{numel / M:.2f} M"
|
|
elif numel >= K:
|
|
return f"{numel / K:.2f} K"
|
|
else:
|
|
return f"{numel}"
|