update must try
This commit is contained in:
parent
28a6af662a
commit
5a97d30247
|
@ -57,3 +57,4 @@ t.sh
|
|||
|
||||
unittest/outputs/
|
||||
unittest/tmp/
|
||||
**/tmp/
|
||||
|
|
73
README.md
73
README.md
|
@ -83,16 +83,81 @@ pip install -r requirements.txt && python setup.py develop
|
|||
```
|
||||
|
||||
## Must Try
|
||||
The follow codes and comments walk you through the key functionality of OpenDelta.
|
||||
|
||||
```python
|
||||
from transformers import AutoModelForSeq2SeqLM
|
||||
# use tranformers as usual.
|
||||
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
|
||||
t5 = AutoModelForSeq2SeqLM.from_pretrained("t5-large")
|
||||
from opendelta import AutoDeltaModel
|
||||
delta = AutoDeltaModel.from_finetuned("thunlp/FactQA_T5-large_Adapter", backbone_model=t5)
|
||||
t5_tokenizer = AutoTokenizer.from_pretrained("t5-large")
|
||||
inputs_ids = t5_tokenizer.encode("Is Harry Poter wrtten by JKrowling", return_tensors="pt")
|
||||
t5_tokenizer.decode(t5.generate(inputs_ids)[0])
|
||||
# >>> '<pad><extra_id_0>? Is it Harry Potter?</s>'
|
||||
|
||||
|
||||
# use existing delta models
|
||||
from opendelta import AutoDeltaModel, AutoDeltaConfig
|
||||
# use existing delta models from DeltaCenter
|
||||
delta = AutoDeltaModel.from_finetuned("thunlp/Spelling_Correction_T5_LRAdapter_demo", backbone_model=t5)
|
||||
# freeze the backbone model except the delta models.
|
||||
delta.freeze_module()
|
||||
# see the change
|
||||
delta.log()
|
||||
|
||||
|
||||
t5_tokenizer.decode(t5.generate(inputs_ids)[0])
|
||||
# >>> <pad> Is Harry Potter written by JK Rowling?</s>
|
||||
|
||||
|
||||
# Now save the delta models, not the whole backbone model to tmp
|
||||
delta.save_finetuned(".tmp")
|
||||
# >>> The state dict size is 1.443 MB
|
||||
# >>> We encourage users to push their final and public models to delta center to share them with the community!
|
||||
|
||||
|
||||
# reload the model from local url and add it to pre-trained T5.
|
||||
t5 = AutoModelForSeq2SeqLM.from_pretrained("t5-large")
|
||||
delta1 = AutoDeltaModel.from_finetuned(".tmp", backbone_model=t5)
|
||||
import shutil; shutil.rmtree(".tmp") # don't forget to remove the tmp files.
|
||||
t5_tokenizer.decode(t5.generate(inputs_ids)[0])
|
||||
# >>> <pad> Is Harry Potter written by JK Rowling?</s>
|
||||
|
||||
# detach the delta models, the model returns to the unmodified status.
|
||||
delta1.detach()
|
||||
t5_tokenizer.decode(t5.generate(inputs_ids)[0])
|
||||
# >>> '<pad><extra_id_0>? Is it Harry Potter?</s>'
|
||||
|
||||
# use default configuration for cunstomized wrapped models which have PLMs inside.
|
||||
import torch.nn as nn
|
||||
class WrappedModel(nn.Module):
|
||||
def __init__(self, inner_model):
|
||||
super().__init__()
|
||||
self.inner = inner_model
|
||||
def forward(self, *args, **kwargs):
|
||||
return self.inner(*args, **kwargs)
|
||||
|
||||
wrapped_model = WrappedModel(WrappedModel(t5))
|
||||
|
||||
# say we use LoRA
|
||||
delta_config = AutoDeltaConfig.from_dict({"delta_type":"lora"})
|
||||
delta2 = AutoDeltaModel.from_config(delta_config, backbone_model=wrapped_model)
|
||||
delta2.log()
|
||||
# >>> root
|
||||
# -- inner
|
||||
# -- inner
|
||||
# ...
|
||||
# ... lora_A:[8,1024], lora_B:[1024,8]
|
||||
delta2.detach()
|
||||
|
||||
# use a not default configuration
|
||||
# say we add lora to the last four layer of the decoder of t5, with lora rank=5
|
||||
delta_config3 = AutoDeltaConfig.from_dict({"delta_type":"lora", "modified_modules":["[r]decoder.*((20)|(21)|(22)|(23)).*DenseReluDense\.wi"], "lora_r":5})
|
||||
delta3 = AutoDeltaModel.from_config(delta_config3, backbone_model=wrapped_model)
|
||||
delta3.log()
|
||||
|
||||
```
|
||||
|
||||
## Verified Supported Models
|
||||
## Verified Default Configurations
|
||||
|
||||
- **You can try to use OpenDelta on *any* backbone models based on PyTorch.**
|
||||
- However, with small chances thatThe interface of the submodules of the backbone model is not supported. Therefore we verified some commonly
|
||||
|
|
Loading…
Reference in New Issue