• LORA项目源码解读

    大模型fineturn技术中类似于核武器的LORA，简单而又高效。其理论基础为：在将通用大模型迁移到具体专业领域时，仅需要对其高维参数的低秩子空间进行更新。基于该朴素的逻辑，LORA降低大模型的fineturn门槛，模型训练时不需要保存原始参数的梯度，仅需对低秩子空间参数进行优化即可。且其低秩子空间在训练完成后，可以叠加到原始参数中，从而实现模型能力的专业领域迁移。为了解这种高维参数空间=》低秩子空间投影实现研究其项目源码。

    项目地址：https://github.com/microsoft/LoRA LORA提出至今已经2年了，但现在任然在更新项目代码
    论文地址：https://arxiv.org/pdf/2106.09685.pdf
    简读地址：https://blog.csdn.net/a486259/article/details/132767182?spm=1001.2014.3001.5501

    1、基本介绍

    1.1 实施效果

    LORA技术使用RoBERTa（Liu et al.，2019）base和large以及DeBERTa（He et al.，2020）XXL 1.5B在GLUE基准上获得了与完全微调相当或优于完全微调的结果，而只训练和存储了一小部分参数。 LORA技术展现了与全参数迁移学习相同甚至更优的效果
    在这里插入图片描述
    在GPT-2上，LoRA与完全微调和其他大模型微调的方法（如Adapter（Houlsby et al.，2019）和Prefix（Li和Liang，2021））相比都要好。
    在这里插入图片描述
    以上两图不仅展示了LORA在大模型上的微调效果，同时也透露了大模型性能提升的困难。DeBERTa
    XXL的参数量是RoBERTa base的一百倍以上，而平均精度仅高4.6%；GPT2 L的参数量是GPT M的两倍以上，而平均精度仅高0.5%左右。这种参数增长与精度增长的差异在图像领域是少见的，尤其是目标检测|语义分割|图像分类中。

    1.2 安装使用

    这里仅限于官网给出的使用案例。LORA的实际使用应该是基于其他框架展开的

    安装命令
    pip install loralib
# Alternatively
# pip install git+https://github.com/microsoft/LoRA

    • 1
    • 2
    • 3
    构建可低秩训练层

    LORA目前除了Linear层外，还支持其他layer。基于lora创建的layer是lora的子类，同时也是torch.nn.module的子类。

    # ===== Before =====
# layer = nn.Linear(in_features, out_features)

# ===== After ======
import loralib as lora
# Add a pair of low-rank adaptation matrices with rank r=16
layer = lora.Linear(in_features, out_features, r=16)

    • 1
    • 2
    • 3
    • 4
    • 5
    • 6
    • 7
    设置仅LORA层可训练

    这里要求model对象中的一些层是lora的子类，mark_only_lora_as_trainable函数会将参数name中不包含lora_的部分都设置为不可训练

    import loralib as lora
model = BigModel()
# This sets requires_grad to False for all parameters without the string "lora_" in their names
lora.mark_only_lora_as_trainable(model)
# Training loop
for batch in dataloader:
   ...

    • 1
    • 2
    • 3
    • 4
    • 5
    • 6
    • 7
    保存模型参数

    包含LORA层的模型，参数保存分两步完成，第一步保存原始模型的参数（通常可以忽略），第二步才是保存lora层的参数,对应代码为：torch.save(lora.lora_state_dict(model), checkpoint_path)

    # ===== Before =====
torch.save(model.state_dict(), checkpoint_path)
# ===== After =====
torch.save(lora.lora_state_dict(model), checkpoint_path)

    • 1
    • 2
    • 3
    • 4
    加载模型参数

    包含lora层的模型参数加载也是分两步完成，第一步加载原始参数，第二步为加载lora层参数。

    # Load the pretrained checkpoint first
model.load_state_dict(torch.load('ckpt_pretrained.pt'), strict=False)
# Then load the LoRA checkpoint
model.load_state_dict(torch.load('ckpt_lora.pt'), strict=False)

    • 1
    • 2
    • 3
    • 4
    额外说明

    某些Transformer实现使用单个nn.Linear。查询、键和值的投影矩阵为nn.Linear。如果希望将更新的秩约束到单个矩阵，则必须将其分解为三个单独的矩阵或使用lora.MergedLinear。如果选择分解层，请确保相应地修改checkpoint 。

    # ===== Before =====
# qkv_proj = nn.Linear(d_model, 3*d_model)
# ===== After =====
# Break it up (remember to modify the pretrained checkpoint accordingly)
q_proj = lora.Linear(d_model, d_model, r=8)
k_proj = nn.Linear(d_model, d_model)
v_proj = lora.Linear(d_model, d_model, r=8)
# Alternatively, use lora.MergedLinear (recommended)
qkv_proj = lora.MergedLinear(d_model, 3*d_model, r=8, enable_lora=[True, False, True])

    • 1
    • 2
    • 3
    • 4
    • 5
    • 6
    • 7
    • 8
    • 9

    2、代码解读

    lora项目的源码如下所示，其核心代码仅有layers.py和utils.py两个文件。
    examples是两个使用案例，为第三方代码，这里不深入探讨。
    在这里插入图片描述

    2.1 Layer.py

    在lora源码中，共有Embedding、Linear、MergedLinear、ConvLoRA 四种layer对象，均为nn.Module与 LoRALayer的子类。

    样板layer解析

    lora源码中layer对象比较多，这里只对Linear和·ConvLoRA 进行详细描述

    Linear

    在lora中，对于Linear的低秩分解由矩阵A、B的乘法所实现，其在forward时，lora分支BAlora_dropout操作，并对BA的输出结果进行scale操作。当调用layer.train(True)时，会根据self.merged参数将weight中的BA参数累加进行移除，当调用layer.train(False)时，则会将将BA参数累加到weight中。
    这里需要注意，LoRA.Linear是nn.Linear的子类，在使用时直接参考nn.Linear的用法即可。

    class Linear(nn.Linear, LoRALayer):
    # LoRA implemented in a dense layer
    def __init__(
        self, 
        in_features: int, 
        out_features: int, 
        r: int = 0, 
        lora_alpha: int = 1, 
        lora_dropout: float = 0.,
        fan_in_fan_out: bool = False, # Set this to True if the layer to replace stores weight like (fan_in, fan_out)
        merge_weights: bool = True,
        **kwargs
    ):
        nn.Linear.__init__(self, in_features, out_features, **kwargs)
        LoRALayer.__init__(self, r=r, lora_alpha=lora_alpha, lora_dropout=lora_dropout,
                           merge_weights=merge_weights)

        self.fan_in_fan_out = fan_in_fan_out
        # Actual trainable parameters
        if r > 0:
            self.lora_A = nn.Parameter(self.weight.new_zeros((r, in_features)))
            self.lora_B = nn.Parameter(self.weight.new_zeros((out_features, r)))
            self.scaling = self.lora_alpha / self.r
            # Freezing the pre-trained weight matrix
            self.weight.requires_grad = False
        self.reset_parameters()
        if fan_in_fan_out:
            self.weight.data = self.weight.data.transpose(0, 1)

    def reset_parameters(self):
        nn.Linear.reset_parameters(self)
        if hasattr(self, 'lora_A'):
            # initialize A the same way as the default for nn.Linear and B to zero
            nn.init.kaiming_uniform_(self.lora_A, a=math.sqrt(5))
            nn.init.zeros_(self.lora_B)

    def train(self, mode: bool = True):
        def T(w):
            return w.transpose(0, 1) if self.fan_in_fan_out else w
        nn.Linear.train(self, mode)
        if mode:
            if self.merge_weights and self.merged:
                # Make sure that the weights are not merged
                if self.r > 0:
                    self.weight.data -= T(self.lora_B @ self.lora_A) * self.scaling
                self.merged = False
        else:
            if self.merge_weights and not self.merged:
                # Merge the weights and mark it
                if self.r > 0:
                    self.weight.data += T(self.lora_B @ self.lora_A) * self.scaling
                self.merged = True       

    def forward(self, x: torch.Tensor):
        def T(w):
            return w.transpose(0, 1) if self.fan_in_fan_out else w
        if self.r > 0 and not self.merged:
            result = F.linear(x, T(self.weight), bias=self.bias)            
            result += (self.lora_dropout(x) @ self.lora_A.transpose(0, 1) @ self.lora_B.transpose(0, 1)) * self.scaling
            return result
        else:
            return F.linear(x, T(self.weight), bias=self.bias)

    • 1
    • 2
    • 3
    • 4
    • 5
    • 6
    • 7
    • 8
    • 9
    • 10
    • 11
    • 12
    • 13
    • 14
    • 15
    • 16
    • 17
    • 18
    • 19
    • 20
    • 21
    • 22
    • 23
    • 24
    • 25
    • 26
    • 27
    • 28
    • 29
    • 30
    • 31
    • 32
    • 33
    • 34
    • 35
    • 36
    • 37
    • 38
    • 39
    • 40
    • 41
    • 42
    • 43
    • 44
    • 45
    • 46
    • 47
    • 48
    • 49
    • 50
    • 51
    • 52
    • 53
    • 54
    • 55
    • 56
    • 57
    • 58
    • 59
    • 60
    • 61
    • 62
    ConvLoRA

    LORA能对conv进行低秩分解，是博主意料之外的。该操作完整的将LoRALinear的思想应用到conv kernel中，有self.lora_B 和 self.lora_A两个可训练参数表述conv的kernel参数，将self.lora_B @ self.lora_A的结果直接作用到conv.weight中，然后调用self.conv._conv_forward完成卷积操作。
    这里需要注意的是，使用ConvLoRA跟使用torch.nn.Conv是没有任何区别。这里只有一个问题，我们不能直接将conv对象转换为ConvLoRA对象。需要在构建网络时就使用ConvLoRA layer

    class Conv2d(ConvLoRA):
    def __init__(self, *args, **kwargs):
        super(Conv2d, self).__init__(nn.Conv2d, *args, **kwargs)

class Conv1d(ConvLoRA):
    def __init__(self, *args, **kwargs):
        super(Conv1d, self).__init__(nn.Conv1d, *args, **kwargs)

class Conv3d(ConvLoRA):
    def __init__(self, *args, **kwargs):
        super(Conv3d, self).__init__(nn.Conv3d, *args, **kwargs)
        
class ConvLoRA(nn.Module, LoRALayer):
    def __init__(self, conv_module, in_channels, out_channels, kernel_size, r=0, lora_alpha=1, lora_dropout=0., merge_weights=True, **kwargs):
        super(ConvLoRA, self).__init__()
        self.conv = conv_module(in_channels, out_channels, kernel_size, **kwargs)
        LoRALayer.__init__(self, r=r, lora_alpha=lora_alpha, lora_dropout=lora_dropout, merge_weights=merge_weights)
        assert isinstance(kernel_size, int)
        # Actual trainable parameters
        if r > 0:
            self.lora_A = nn.Parameter(
                self.conv.weight.new_zeros((r * kernel_size, in_channels * kernel_size))
            )
            self.lora_B = nn.Parameter(
              self.conv.weight.new_zeros((out_channels//self.conv.groups*kernel_size, r*kernel_size))
            )
            self.scaling = self.lora_alpha / self.r
            # Freezing the pre-trained weight matrix
            self.conv.weight.requires_grad = False
        self.reset_parameters()
        self.merged = False

    def reset_parameters(self):
        self.conv.reset_parameters()
        if hasattr(self, 'lora_A'):
            # initialize A the same way as the default for nn.Linear and B to zero
            nn.init.kaiming_uniform_(self.lora_A, a=math.sqrt(5))
            nn.init.zeros_(self.lora_B)

    def train(self, mode=True):
        super(ConvLoRA, self).train(mode)
        if mode:
            if self.merge_weights and self.merged:
                if self.r > 0:
                    # Make sure that the weights are not merged
                    self.conv.weight.data -= (self.lora_B @ self.lora_A).view(self.conv.weight.shape) * self.scaling
                self.merged = False
        else:
            if self.merge_weights and not self.merged:
                if self.r > 0:
                    # Merge the weights and mark it
                    self.conv.weight.data += (self.lora_B @ self.lora_A).view(self.conv.weight.shape) * self.scaling
                self.merged = True

    def forward(self, x):
        if self.r > 0 and not self.merged:
            return self.conv._conv_forward(
                x, 
                self.conv.weight + (self.lora_B @ self.lora_A).view(self.conv.weight.shape) * self.scaling,
                self.conv.bias
            )
        return self.conv(x)

    • 1
    • 2
    • 3
    • 4
    • 5
    • 6
    • 7
    • 8
    • 9
    • 10
    • 11
    • 12
    • 13
    • 14
    • 15
    • 16
    • 17
    • 18
    • 19
    • 20
    • 21
    • 22
    • 23
    • 24
    • 25
    • 26
    • 27
    • 28
    • 29
    • 30
    • 31
    • 32
    • 33
    • 34
    • 35
    • 36
    • 37
    • 38
    • 39
    • 40
    • 41
    • 42
    • 43
    • 44
    • 45
    • 46
    • 47
    • 48
    • 49
    • 50
    • 51
    • 52
    • 53
    • 54
    • 55
    • 56
    • 57
    • 58
    • 59
    • 60
    • 61
    • 62
    完整代码
    #  ------------------------------------------------------------------------------------------
#  Copyright (c) Microsoft Corporation. All rights reserved.
#  Licensed under the MIT License (MIT). See LICENSE in the repo root for license information.
#  ------------------------------------------------------------------------------------------
import torch
import torch.nn as nn
import torch.nn.functional as F

import math
from typing import Optional, List

class LoRALayer():
    def __init__(
        self, 
        r: int, 
        lora_alpha: int, 
        lora_dropout: float,
        merge_weights: bool,
    ):
        self.r = r
        self.lora_alpha = lora_alpha
        # Optional dropout
        if lora_dropout > 0.:
            self.lora_dropout = nn.Dropout(p=lora_dropout)
        else:
            self.lora_dropout = lambda x: x
        # Mark the weight as unmerged
        self.merged = False
        self.merge_weights = merge_weights


class Embedding(nn.Embedding, LoRALayer):
    # LoRA implemented in a dense layer
    def __init__(
        self,
        num_embeddings: int,
        embedding_dim: int,
        r: int = 0,
        lora_alpha: int = 1,
        merge_weights: bool = True,
        **kwargs
    ):
        nn.Embedding.__init__(self, num_embeddings, embedding_dim, **kwargs)
        LoRALayer.__init__(self, r=r, lora_alpha=lora_alpha, lora_dropout=0,
                           merge_weights=merge_weights)
        # Actual trainable parameters
        if r > 0:
            self.lora_A = nn.Parameter(self.weight.new_zeros((r, num_embeddings)))
            self.lora_B = nn.Parameter(self.weight.new_zeros((embedding_dim, r)))
            self.scaling = self.lora_alpha / self.r
            # Freezing the pre-trained weight matrix
            self.weight.requires_grad = False
        self.reset_parameters()

    def reset_parameters(self):
        nn.Embedding.reset_parameters(self)
        if hasattr(self, 'lora_A'):
            # initialize A the same way as the default for nn.Linear and B to zero
            nn.init.zeros_(self.lora_A)
            nn.init.normal_(self.lora_B)

    def train(self, mode: bool = True):
        nn.Embedding.train(self, mode)
        if mode:
            if self.merge_weights and self.merged:
                # Make sure that the weights are not merged
                if self.r > 0:
                    self.weight.data -= (self.lora_B @ self.lora_A).transpose(0, 1) * self.scaling
                self.merged = False
        else:
            if self.merge_weights and not self.merged:
                # Merge the weights and mark it
                if self.r > 0:
                    self.weight.data += (self.lora_B @ self.lora_A).transpose(0, 1) * self.scaling
                self.merged = True
        
    def forward(self, x: torch.Tensor):
        if self.r > 0 and not self.merged:
            result = nn.Embedding.forward(self, x)
            after_A = F.embedding(
                x, self.lora_A.transpose(0, 1), self.padding_idx, self.max_norm,
                self.norm_type, self.scale_grad_by_freq, self.sparse
            )
            result += (after_A @ self.lora_B.transpose(0, 1)) * self.scaling
            return result
        else:
            return nn.Embedding.forward(self, x)
            

class Linear(nn.Linear, LoRALayer):
    # LoRA implemented in a dense layer
    def __init__(
        self, 
        in_features: int, 
        out_features: int, 
        r: int = 0, 
        lora_alpha: int = 1, 
        lora_dropout: float = 0.,
        fan_in_fan_out: bool = False, # Set this to True if the layer to replace stores weight like (fan_in, fan_out)
        merge_weights: bool = True,
        **kwargs
    ):
        nn.Linear.__init__(self, in_features, out_features, **kwargs)
        LoRALayer.__init__(self, r=r, lora_alpha=lora_alpha, lora_dropout=lora_dropout,
                           merge_weights=merge_weights)

        self.fan_in_fan_out = fan_in_fan_out
        # Actual trainable parameters
        if r > 0:
            self.lora_A = nn.Parameter(self.weight.new_zeros((r, in_features)))
            self.lora_B = nn.Parameter(self.weight.new_zeros((out_features, r)))
            self.scaling = self.lora_alpha / self.r
            # Freezing the pre-trained weight matrix
            self.weight.requires_grad = False
        self.reset_parameters()
        if fan_in_fan_out:
            self.weight.data = self.weight.data.transpose(0, 1)

    def reset_parameters(self):
        nn.Linear.reset_parameters(self)
        if hasattr(self, 'lora_A'):
            # initialize A the same way as the default for nn.Linear and B to zero
            nn.init.kaiming_uniform_(self.lora_A, a=math.sqrt(5))
            nn.init.zeros_(self.lora_B)

    def train(self, mode: bool = True):
        def T(w):
            return w.transpose(0, 1) if self.fan_in_fan_out else w
        nn.Linear.train(self, mode)
        if mode:
            if self.merge_weights and self.merged:
                # Make sure that the weights are not merged
                if self.r > 0:
                    self.weight.data -= T(self.lora_B @ self.lora_A) * self.scaling
                self.merged = False
        else:
            if self.merge_weights and not self.merged:
                # Merge the weights and mark it
                if self.r > 0:
                    self.weight.data += T(self.lora_B @ self.lora_A) * self.scaling
                self.merged = True       

    def forward(self, x: torch.Tensor):
        def T(w):
            return w.transpose(0, 1) if self.fan_in_fan_out else w
        if self.r > 0 and not self.merged:
            result = F.linear(x, T(self.weight), bias=self.bias)            
            result += (self.lora_dropout(x) @ self.lora_A.transpose(0, 1) @ self.lora_B.transpose(0, 1)) * self.scaling
            return result
        else:
            return F.linear(x, T(self.weight), bias=self.bias)


class MergedLinear(nn.Linear, LoRALayer):
    # LoRA implemented in a dense layer
    def __init__(
        self, 
        in_features: int, 
        out_features: int, 
        r: int = 0, 
        lora_alpha: int = 1, 
        lora_dropout: float = 0.,
        enable_lora: List[bool] = [False],
        fan_in_fan_out: bool = False,
        merge_weights: bool = True,
        **kwargs
    ):
        nn.Linear.__init__(self, in_features, out_features, **kwargs)
        LoRALayer.__init__(self, r=r, lora_alpha=lora_alpha, lora_dropout=lora_dropout,
                           merge_weights=merge_weights)
        assert out_features % len(enable_lora) == 0, \
            'The length of enable_lora must divide out_features'
        self.enable_lora = enable_lora
        self.fan_in_fan_out = fan_in_fan_out
        # Actual trainable parameters
        if r > 0 and any(enable_lora):
            self.lora_A = nn.Parameter(
                self.weight.new_zeros((r * sum(enable_lora), in_features)))
            self.lora_B = nn.Parameter(
                self.weight.new_zeros((out_features // len(enable_lora) * sum(enable_lora), r))
            ) # weights for Conv1D with groups=sum(enable_lora)
            self.scaling = self.lora_alpha / self.r
            # Freezing the pre-trained weight matrix
            self.weight.requires_grad = False
            # Compute the indices
            self.lora_ind = self.weight.new_zeros(
                (out_features, ), dtype=torch.bool
            ).view(len(enable_lora), -1)
            self.lora_ind[enable_lora, :] = True
            self.lora_ind = self.lora_ind.view(-1)
        self.reset_parameters()
        if fan_in_fan_out:
            self.weight.data = self.weight.data.transpose(0, 1)

    def reset_parameters(self):
        nn.Linear.reset_parameters(self)
        if hasattr(self, 'lora_A'):
            # initialize A the same way as the default for nn.Linear and B to zero
            nn.init.kaiming_uniform_(self.lora_A, a=math.sqrt(5))
            nn.init.zeros_(self.lora_B)

    def zero_pad(self, x):
        result = x.new_zeros((len(self.lora_ind), *x.shape[1:]))
        result[self.lora_ind] = x
        return result

    def merge_AB(self):
        def T(w):
            return w.transpose(0, 1) if self.fan_in_fan_out else w
        delta_w = F.conv1d(
            self.lora_A.unsqueeze(0), 
            self.lora_B.unsqueeze(-1), 
            groups=sum(self.enable_lora)
        ).squeeze(0)
        return T(self.zero_pad(delta_w))

    def train(self, mode: bool = True):
        def T(w):
            return w.transpose(0, 1) if self.fan_in_fan_out else w
        nn.Linear.train(self, mode)
        if mode:
            if self.merge_weights and self.merged:
                # Make sure that the weights are not merged
                if self.r > 0 and any(self.enable_lora):
                    self.weight.data -= self.merge_AB() * self.scaling
                self.merged = False
        else:
            if self.merge_weights and not self.merged:
                # Merge the weights and mark it
                if self.r > 0 and any(self.enable_lora):
                    self.weight.data += self.merge_AB() * self.scaling
                self.merged = True        

    def forward(self, x: torch.Tensor):
        def T(w):
            return w.transpose(0, 1) if self.fan_in_fan_out else w
        if self.merged:
            return F.linear(x, T(self.weight), bias=self.bias)
        else:
            result = F.linear(x, T(self.weight), bias=self.bias)
            if self.r > 0:
                result += self.lora_dropout(x) @ T(self.merge_AB().T) * self.scaling
            return result

class ConvLoRA(nn.Module, LoRALayer):
    def __init__(self, conv_module, in_channels, out_channels, kernel_size, r=0, lora_alpha=1, lora_dropout=0., merge_weights=True, **kwargs):
        super(ConvLoRA, self).__init__()
        self.conv = conv_module(in_channels, out_channels, kernel_size, **kwargs)
        LoRALayer.__init__(self, r=r, lora_alpha=lora_alpha, lora_dropout=lora_dropout, merge_weights=merge_weights)
        assert isinstance(kernel_size, int)
        # Actual trainable parameters
        if r > 0:
            self.lora_A = nn.Parameter(
                self.conv.weight.new_zeros((r * kernel_size, in_channels * kernel_size))
            )
            self.lora_B = nn.Parameter(
              self.conv.weight.new_zeros((out_channels//self.conv.groups*kernel_size, r*kernel_size))
            )
            self.scaling = self.lora_alpha / self.r
            # Freezing the pre-trained weight matrix
            self.conv.weight.requires_grad = False
        self.reset_parameters()
        self.merged = False

    def reset_parameters(self):
        self.conv.reset_parameters()
        if hasattr(self, 'lora_A'):
            # initialize A the same way as the default for nn.Linear and B to zero
            nn.init.kaiming_uniform_(self.lora_A, a=math.sqrt(5))
            nn.init.zeros_(self.lora_B)

    def train(self, mode=True):
        super(ConvLoRA, self).train(mode)
        if mode:
            if self.merge_weights and self.merged:
                if self.r > 0:
                    # Make sure that the weights are not merged
                    self.conv.weight.data -= (self.lora_B @ self.lora_A).view(self.conv.weight.shape) * self.scaling
                self.merged = False
        else:
            if self.merge_weights and not self.merged:
                if self.r > 0:
                    # Merge the weights and mark it
                    self.conv.weight.data += (self.lora_B @ self.lora_A).view(self.conv.weight.shape) * self.scaling
                self.merged = True

    def forward(self, x):
        if self.r > 0 and not self.merged:
            return self.conv._conv_forward(
                x, 
                self.conv.weight + (self.lora_B @ self.lora_A).view(self.conv.weight.shape) * self.scaling,
                self.conv.bias
            )
        return self.conv(x)

class Conv2d(ConvLoRA):
    def __init__(self, *args, **kwargs):
        super(Conv2d, self).__init__(nn.Conv2d, *args, **kwargs)

class Conv1d(ConvLoRA):
    def __init__(self, *args, **kwargs):
        super(Conv1d, self).__init__(nn.Conv1d, *args, **kwargs)

# Can Extend to other ones like this

class Conv3d(ConvLoRA):
    def __init__(self, *args, **kwargs):
        super(Conv3d, self).__init__(nn.Conv3d, *args, **kwargs)

    • 1
    • 2
    • 3
    • 4
    • 5
    • 6
    • 7
    • 8
    • 9
    • 10
    • 11
    • 12
    • 13
    • 14
    • 15
    • 16
    • 17
    • 18
    • 19
    • 20
    • 21
    • 22
    • 23
    • 24
    • 25
    • 26
    • 27
    • 28
    • 29
    • 30
    • 31
    • 32
    • 33
    • 34
    • 35
    • 36
    • 37
    • 38
    • 39
    • 40
    • 41
    • 42
    • 43
    • 44
    • 45
    • 46
    • 47
    • 48
    • 49
    • 50
    • 51
    • 52
    • 53
    • 54
    • 55
    • 56
    • 57
    • 58
    • 59
    • 60
    • 61
    • 62
    • 63
    • 64
    • 65
    • 66
    • 67
    • 68
    • 69
    • 70
    • 71
    • 72
    • 73
    • 74
    • 75
    • 76
    • 77
    • 78
    • 79
    • 80
    • 81
    • 82
    • 83
    • 84
    • 85
    • 86
    • 87
    • 88
    • 89
    • 90
    • 91
    • 92
    • 93
    • 94
    • 95
    • 96
    • 97
    • 98
    • 99
    • 100
    • 101
    • 102
    • 103
    • 104
    • 105
    • 106
    • 107
    • 108
    • 109
    • 110
    • 111
    • 112
    • 113
    • 114
    • 115
    • 116
    • 117
    • 118
    • 119
    • 120
    • 121
    • 122
    • 123
    • 124
    • 125
    • 126
    • 127
    • 128
    • 129
    • 130
    • 131
    • 132
    • 133
    • 134
    • 135
    • 136
    • 137
    • 138
    • 139
    • 140
    • 141
    • 142
    • 143
    • 144
    • 145
    • 146
    • 147
    • 148
    • 149
    • 150
    • 151
    • 152
    • 153
    • 154
    • 155
    • 156
    • 157
    • 158
    • 159
    • 160
    • 161
    • 162
    • 163
    • 164
    • 165
    • 166
    • 167
    • 168
    • 169
    • 170
    • 171
    • 172
    • 173
    • 174
    • 175
    • 176
    • 177
    • 178
    • 179
    • 180
    • 181
    • 182
    • 183
    • 184
    • 185
    • 186
    • 187
    • 188
    • 189
    • 190
    • 191
    • 192
    • 193
    • 194
    • 195
    • 196
    • 197
    • 198
    • 199
    • 200
    • 201
    • 202
    • 203
    • 204
    • 205
    • 206
    • 207
    • 208
    • 209
    • 210
    • 211
    • 212
    • 213
    • 214
    • 215
    • 216
    • 217
    • 218
    • 219
    • 220
    • 221
    • 222
    • 223
    • 224
    • 225
    • 226
    • 227
    • 228
    • 229
    • 230
    • 231
    • 232
    • 233
    • 234
    • 235
    • 236
    • 237
    • 238
    • 239
    • 240
    • 241
    • 242
    • 243
    • 244
    • 245
    • 246
    • 247
    • 248
    • 249
    • 250
    • 251
    • 252
    • 253
    • 254
    • 255
    • 256
    • 257
    • 258
    • 259
    • 260
    • 261
    • 262
    • 263
    • 264
    • 265
    • 266
    • 267
    • 268
    • 269
    • 270
    • 271
    • 272
    • 273
    • 274
    • 275
    • 276
    • 277
    • 278
    • 279
    • 280
    • 281
    • 282
    • 283
    • 284
    • 285
    • 286
    • 287
    • 288
    • 289
    • 290
    • 291
    • 292
    • 293
    • 294
    • 295
    • 296
    • 297
    • 298
    • 299
    • 300
    • 301
    • 302
    • 303
    • 304
    • 305
    • 306
    • 307
    • 308

    2.2 utils.py

    期内有mark_only_lora_as_trainable、lora_state_dict两个函数。mark_only_lora_as_trainable函数用于冻结模型的非lora layer参数，该函数基于name区分lora layer 层name中包含lora_。其参数bias设置用于设model中的bias是否可训练，bias == 'none'表示忽略bias，bias == 'all'表示所有偏置都可以训练，bias == 'lora_only'表示仅有lora layer的bias可以训练

    lora_state_dict函数用于加载lora保存的参数，参数bias == 'none'表明只加载lora参数，参数bias == 'all'表明加载lora参数和所有bias参数，

    import torch
import torch.nn as nn
from typing import Dict
from .layers import LoRALayer

def mark_only_lora_as_trainable(model: nn.Module, bias: str = 'none') -> None:
    for n, p in model.named_parameters():
        if 'lora_' not in n:
            p.requires_grad = False
    if bias == 'none':
        return
    elif bias == 'all':
        for n, p in model.named_parameters():
            if 'bias' in n:
                p.requires_grad = True
    elif bias == 'lora_only':
        for m in model.modules():
            if isinstance(m, LoRALayer) and \
                hasattr(m, 'bias') and \
                m.bias is not None:
                    m.bias.requires_grad = True
    else:
        raise NotImplementedError


def lora_state_dict(model: nn.Module, bias: str = 'none') -> Dict[str, torch.Tensor]:
    my_state_dict = model.state_dict()
    if bias == 'none':
        return {k: my_state_dict[k] for k in my_state_dict if 'lora_' in k}
    elif bias == 'all':
        return {k: my_state_dict[k] for k in my_state_dict if 'lora_' in k or 'bias' in k}
    elif bias == 'lora_only':
        to_return = {}
        for k in my_state_dict:
            if 'lora_' in k:
                to_return[k] = my_state_dict[k]
                bias_name = k.split('lora_')[0]+'bias'
                if bias_name in my_state_dict:
                    to_return[bias_name] = my_state_dict[bias_name]
        return to_return
    else:
        raise NotImplementedError

    • 1
    • 2
    • 3
    • 4
    • 5
    • 6
    • 7
    • 8
    • 9
    • 10
    • 11
    • 12
    • 13
    • 14
    • 15
    • 16
    • 17
    • 18
    • 19
    • 20
    • 21
    • 22
    • 23
    • 24
    • 25
    • 26
    • 27
    • 28
    • 29
    • 30
    • 31
    • 32
    • 33
    • 34
    • 35
    • 36
    • 37
    • 38
    • 39
    • 40
    • 41
    • 42
  • 相关阅读:
    第一次pta认证P测试C++
    青团平台全新上线，效果图渲染单张优惠低至2元封顶
    电脑文件夹莫名其妙消失？不用担心，6招教你轻松找回
    聚观早报 | 脸书泄露数据被罚20亿；iPhone15将全系支持灵动岛
    java计算机毕业设计框架的电脑测评系统源码+数据库+lw文档+系统
    【SSM框架】Mybatis详解06 对象分析、注册别名、设置日志输出
    cookie和session区别
    windows下域名解析及修改hosts文件不起作用的问题解决
    Vue的事件类型&组件中数据和事件的传递
    MySQL的JDBC 编程
  • 原文地址：https://blog.csdn.net/a486259/article/details/132768138