mirror of
https://github.com/hpcaitech/ColossalAI.git
synced 2025-07-08 04:49:07 +00:00
7c2f79fa98
* [pre-commit.ci] pre-commit autoupdate updates: - [github.com/PyCQA/autoflake: v2.2.1 → v2.3.1](https://github.com/PyCQA/autoflake/compare/v2.2.1...v2.3.1) - [github.com/pycqa/isort: 5.12.0 → 5.13.2](https://github.com/pycqa/isort/compare/5.12.0...5.13.2) - [github.com/psf/black-pre-commit-mirror: 23.9.1 → 24.4.2](https://github.com/psf/black-pre-commit-mirror/compare/23.9.1...24.4.2) - [github.com/pre-commit/mirrors-clang-format: v13.0.1 → v18.1.7](https://github.com/pre-commit/mirrors-clang-format/compare/v13.0.1...v18.1.7) - [github.com/pre-commit/pre-commit-hooks: v4.3.0 → v4.6.0](https://github.com/pre-commit/pre-commit-hooks/compare/v4.3.0...v4.6.0) * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
46 lines
1.6 KiB
Python
Executable File
46 lines
1.6 KiB
Python
Executable File
"""
|
|
reward model
|
|
"""
|
|
|
|
from typing import Optional
|
|
|
|
import torch
|
|
import torch.nn as nn
|
|
from coati.models import BaseModel
|
|
from transformers import PretrainedConfig
|
|
|
|
|
|
class RewardModel(BaseModel):
|
|
"""
|
|
Reward model class.
|
|
|
|
Args:
|
|
pretrained str: huggingface or local model path
|
|
config: PretrainedConfig object
|
|
**kwargs: all other kwargs as in AutoModel.from_pretrained
|
|
"""
|
|
|
|
def __init__(self, pretrained: str = None, config: Optional[PretrainedConfig] = None, **kwargs) -> None:
|
|
super().__init__(pretrained=pretrained, config=config, **kwargs)
|
|
self.value_head = nn.Linear(self.last_hidden_state_size, 1)
|
|
self.value_head.weight.data.normal_(mean=0.0, std=1 / (self.last_hidden_state_size + 1))
|
|
|
|
def forward(self, input_ids: torch.LongTensor, attention_mask: Optional[torch.Tensor] = None) -> torch.Tensor:
|
|
outputs = self.model(input_ids, attention_mask=attention_mask)
|
|
|
|
last_hidden_states = outputs["last_hidden_state"]
|
|
sequence_lengths = torch.max(attention_mask * torch.arange(input_ids.size(1), device=input_ids.device), dim=1)[
|
|
0
|
|
]
|
|
sequence_hidden_states = last_hidden_states[torch.arange(last_hidden_states.size(0)), sequence_lengths].type(
|
|
self.value_head.weight.dtype
|
|
)
|
|
values = self.value_head(sequence_hidden_states).squeeze(-1) # Ensure shape is (B,)
|
|
return values
|
|
|
|
def get_input_embeddings(self):
|
|
return self.model.get_input_embeddings()
|
|
|
|
def get_output_embeddings(self):
|
|
return self.model.get_output_embeddings()
|