github/ColossalAI
1
0
Fork 0
mirror of https://github.com/hpcaitech/ColossalAI.git synced 2025-09-03 10:06:44 +00:00
Code Issues Packages Projects Releases Wiki Activity

[misc] update pre-commit and run all files (#4752)

Browse Source 
* [misc] update pre-commit

* [misc] run pre-commit

* [misc] remove useless configuration files

* [misc] ignore cuda for clang-format
This commit is contained in:
Hongxin Liu
2023-09-19 14:20:26 +08:00
committed by GitHub
parent 3c6b831c26
commit 079bf3cb26
1268 changed files with 50037 additions and 38444 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
examples/language/gpt/titans/configs/gpt3_zero3_pp1d.py
View File

@@ -11,8 +11,10 @@ HIDDEN_SIZE = 12288
TENSOR_SHAPE = (BATCH_SIZE // NUM_MICRO_BATCHES, SEQ_LEN, HIDDEN_SIZE)
# if you do no want zero, just comment out this dictionary
zero = dict(model_config=dict(tensor_placement_policy='cuda', shard_strategy=TensorShardStrategy()),
optimizer_config=dict(initial_scale=2**16))
zero = dict(
model_config=dict(tensor_placement_policy="cuda", shard_strategy=TensorShardStrategy()),
optimizer_config=dict(initial_scale=2**16),
)
optimizer = dict(
type=HybridAdam,
@@ -27,5 +29,5 @@ model = dict(type=GPT3_pipeline_hybrid, checkpoint=True, num_chunks=1)
# for the current model implementation, mode can only be 1D or None
parallel = dict(
pipeline=1,
tensor=dict(size=2, mode='1d'), # for the current model implementation, mode can only be 1D or None
tensor=dict(size=2, mode="1d"), # for the current model implementation, mode can only be 1D or None
)