mirror of
https://github.com/hpcaitech/ColossalAI.git
synced 2025-09-07 20:10:17 +00:00
[gemini] improve compatibility and add static placement policy (#4479)
* [gemini] remove distributed-related part from colotensor (#4379) * [gemini] remove process group dependency * [gemini] remove tp part from colo tensor * [gemini] patch inplace op * [gemini] fix param op hook and update tests * [test] remove useless tests * [test] remove useless tests * [misc] fix requirements * [test] fix model zoo * [test] fix model zoo * [test] fix model zoo * [test] fix model zoo * [test] fix model zoo * [misc] update requirements * [gemini] refactor gemini optimizer and gemini ddp (#4398) * [gemini] update optimizer interface * [gemini] renaming gemini optimizer * [gemini] refactor gemini ddp class * [example] update gemini related example * [example] update gemini related example * [plugin] fix gemini plugin args * [test] update gemini ckpt tests * [gemini] fix checkpoint io * [example] fix opt example requirements * [example] fix opt example * [example] fix opt example * [example] fix opt example * [gemini] add static placement policy (#4443) * [gemini] add static placement policy * [gemini] fix param offload * [test] update gemini tests * [plugin] update gemini plugin * [plugin] update gemini plugin docstr * [misc] fix flash attn requirement * [test] fix gemini checkpoint io test * [example] update resnet example result (#4457) * [example] update bert example result (#4458) * [doc] update gemini doc (#4468) * [example] update gemini related examples (#4473) * [example] update gpt example * [example] update dreambooth example * [example] update vit * [example] update opt * [example] update palm * [example] update vit and opt benchmark * [hotfix] fix bert in model zoo (#4480) * [hotfix] fix bert in model zoo * [test] remove chatglm gemini test * [test] remove sam gemini test * [test] remove vit gemini test * [hotfix] fix opt tutorial example (#4497) * [hotfix] fix opt tutorial example * [hotfix] fix opt tutorial example
This commit is contained in:
@@ -17,6 +17,13 @@ def data_gen_fn():
|
||||
return dict(input_ids=input_ids, token_type_ids=token_type_ids, attention_mask=attention_mask)
|
||||
|
||||
|
||||
def data_gen_for_pretrain():
|
||||
inputs = data_gen_fn()
|
||||
inputs['labels'] = inputs['input_ids'].clone()
|
||||
inputs['sentence_order_label'] = torch.zeros(BATCH_SIZE, dtype=torch.int64)
|
||||
return inputs
|
||||
|
||||
|
||||
output_transform_fn = lambda x: x
|
||||
|
||||
config = transformers.AlbertConfig(embedding_size=128,
|
||||
@@ -26,14 +33,14 @@ config = transformers.AlbertConfig(embedding_size=128,
|
||||
intermediate_size=256)
|
||||
|
||||
model_zoo.register(name='transformers_albert',
|
||||
model_fn=lambda: transformers.AlbertModel(config),
|
||||
model_fn=lambda: transformers.AlbertModel(config, add_pooling_layer=False),
|
||||
data_gen_fn=data_gen_fn,
|
||||
output_transform_fn=output_transform_fn,
|
||||
model_attribute=ModelAttribute(has_control_flow=True))
|
||||
model_zoo.register(name='transformers_albert_for_pretraining',
|
||||
model_fn=lambda: transformers.AlbertForPreTraining(config),
|
||||
data_gen_fn=data_gen_fn,
|
||||
output_transform_fn=output_transform_fn,
|
||||
data_gen_fn=data_gen_for_pretrain,
|
||||
output_transform_fn=lambda x: dict(loss=x.loss),
|
||||
model_attribute=ModelAttribute(has_control_flow=True))
|
||||
model_zoo.register(name='transformers_albert_for_masked_lm',
|
||||
model_fn=lambda: transformers.AlbertForMaskedLM(config),
|
||||
|
Reference in New Issue
Block a user