This is the configuration class to store the configuration of a [`LoraModel`]. Args: r (`int`): Lora attention dimension. ta

This module wraps a LLamaAttention module and injects adaption prompts.

Base model encompassing various Peft methods. Args: model ([`~transformers.PreTrainedModel`]): The base transformer model used for P

r""" The `torch.nn` model to encode the prefix. Args: config ([`PrefixTuningConfig`]): The configuration of the prefix encoder.

The model to encode virtual tokens into prompt embeddings. Args: config ([`PromptTuningConfig`]): The configuration of the prompt em

The prompt encoder network that is used to generate the virtual token embeddings for p-tuning. Args: config ([`PromptEncoderConfig`]

This is the configuration class to store the configuration of a [`PromptEmbedding`]. Args: prompt_tuning_init (Union[[`PromptTuningI

The RankAllocator for AdaLoraModel. Paper: https://openreview.net/pdf?id=lq62uWRJjiY Args: config ([`AdaLoraConfig`]): The configura

Create the empty memory buffer

This is the configuration class to store the configuration of a [`~peft.AdaLora`]. Args: target_r (`int`): The target average rank o

Creates AdaLoRA (Adaptive LoRA) model from a pretrained transformers model. Paper: https://openreview.net/pdf?id=lq62uWRJjiY Args:

Stores the configuration of an [`AdaptionPromptModel`].

Implements adaption prompts as described in https://arxiv.org/pdf/2303.16199.pdf. The top L attention modules are replaced with AdaptedAtten

Importance score calculator for TaSL method. Calculates importance scores for LoRA parameters based on parameter sensitivity. Args:

Creates Low Rank Adapter (Lora) model from a pretrained transformers model. Args: model ([`~transformers.PreTrainedModel`]): The mod

Implements Memory based Parameter Adaptation model

This is the base configuration class to store the configuration of a [`PeftModel`]. Args: peft_type (Union[[`~peft.utils.config.Peft

r""" This is the base configuration class for PEFT adapter models. It contains all the methods that are common to all PEFT adapter models. Thi

Peft model for causal language modeling. Args: model ([`~transformers.PreTrainedModel`]): Base transformer model. peft_confi

Peft model for sequence-to-sequence language modeling. Args: model ([`~transformers.PreTrainedModel`]): Base transformer model.

Peft model for sequence classification tasks. Args: model ([`~transformers.PreTrainedModel`]): Base transformer model. peft_

Peft model for token classification tasks. Args: model ([`~transformers.PreTrainedModel`]): Base transformer model. peft_con

This is the configuration class to store the configuration of a [`PrefixEncoder`]. Args: encoder_hidden_size (`int`): The hidden siz

This is the configuration class to store the configuration of a [`PromptEncoder`]. Args: encoder_reparameterization_type (Union[[`Pr

This is the base configuration class to store the configuration of [`PrefixTuning`], [`PromptEncoder`], or [`PromptTuning`]. Args: