mirror of
https://github.com/hpcaitech/ColossalAI.git
synced 2025-08-11 21:01:54 +00:00
36a519b49f
update Update test_ci.sh Update test_ci.sh Update test_ci.sh Update test_ci.sh Update test_ci.sh Update test_ci.sh Update run_chatgpt_examples.yml Update run_chatgpt_examples.yml Update run_chatgpt_examples.yml Update run_chatgpt_examples.yml Update run_chatgpt_examples.yml Update run_chatgpt_examples.yml Update test_ci.sh Update test_ci.sh update Update run_chatgpt_examples.yml Update run_chatgpt_examples.yml update ci Update test_ci.sh Update run_chatgpt_examples.yml Update run_chatgpt_examples.yml Update run_chatgpt_examples.yml Update run_chatgpt_examples.yml Update run_chatgpt_examples.yml Update run_chatgpt_examples.yml Update run_chatgpt_examples.yml Update test_ci.sh Update test_ci.sh Update run_chatgpt_examples.yml Update test_ci.sh Update test_ci.sh Update test_ci.sh update test ci RoBERTa for RLHF Stage 2 & 3 (still in testing) Revert "Add RoBERTa for RLHF Stage 2 & 3 (test)" This reverts commit06741d894d. Add RoBERTa for RLHF stage 2 & 3 1. add roberta folder under model folder 2. add roberta option in train_reward_model.py 3. add some test in testci Update test_ci.sh Revert "Update test_ci.sh" This reverts commit 9c7352b81766f3177d31eeec0ec178a301df966a. Add RoBERTa for RLHF Stage 2 & 3 (test) RoBERTa for RLHF Stage 2 & 3 (still in testing) Revert "Add RoBERTa for RLHF Stage 2 & 3 (test)" This reverts commit06741d894d. Add RoBERTa for RLHF stage 2 & 3 1. add roberta folder under model folder 2. add roberta option in train_reward_model.py 3. add some test in testci Update test_ci.sh Revert "Update test_ci.sh" This reverts commit 9c7352b81766f3177d31eeec0ec178a301df966a. update roberta with coati chat ci update Revert "chat ci update" This reverts commit 17ae7ae01fa752bd3289fc39069868fde99cf846. [test]chat_update_ci Update test_ci.sh Update test_ci.sh test Update gpt_critic.py Update gpt_critic.py Update run_chatgpt_unit_tests.yml update test ci update update update update Update test_ci.sh update Update test_ci.sh Update test_ci.sh Update run_chatgpt_examples.yml Update run_chatgpt_examples.yml
37 lines
1.2 KiB
Python
37 lines
1.2 KiB
Python
from typing import Optional
|
|
|
|
from transformers.models.gpt2.configuration_gpt2 import GPT2Config
|
|
from transformers.models.gpt2.modeling_gpt2 import GPT2LMHeadModel
|
|
|
|
from ..base import Actor
|
|
|
|
|
|
class GPTActor(Actor):
|
|
"""
|
|
GPT Actor model.
|
|
|
|
Args:
|
|
pretrained (str): Pretrained model name or path.
|
|
config (GPT2Config): Model config.
|
|
checkpoint (bool): Enable gradient checkpointing.
|
|
lora_rank (int): Rank of the LoRa layer.
|
|
lora_train_bias (str): Bias training strategy for the LoRa layer.
|
|
"""
|
|
|
|
def __init__(self,
|
|
pretrained: Optional[str] = None,
|
|
config: Optional[GPT2Config] = None,
|
|
checkpoint: bool = False,
|
|
lora_rank: int = 0,
|
|
lora_train_bias: str = 'none',
|
|
**kwargs) -> None:
|
|
if pretrained is not None:
|
|
model = GPT2LMHeadModel.from_pretrained(pretrained)
|
|
elif config is not None:
|
|
model = GPT2LMHeadModel(config)
|
|
else:
|
|
model = GPT2LMHeadModel(GPT2Config())
|
|
if checkpoint:
|
|
model.gradient_checkpointing_enable()
|
|
super().__init__(model, lora_rank, lora_train_bias, **kwargs)
|