feedback

Author: stevhliu

docs/source/_toctree.yml

@@ -79,6 +79,8 @@
       title: LoKr
     - local: package_reference/lora
       title: LoRA
+    - local: package_reference/adapter_utils
+      title: LyCORIS
     - local: package_reference/multitask_prompt_tuning
       title: Multitask Prompt Tuning
     - local: package_reference/p_tuning
@@ -87,8 +89,6 @@
       title: Prefix tuning
     - local: package_reference/prompt_tuning
       title: Prompt tuning
-    - local: package_reference/adapter_utils
-      title: Utilities
     title: Adapters
   title: API reference
 

docs/source/package_reference/adapter_utils.md

@@ -14,7 +14,7 @@ rendered properly in your Markdown viewer.
 
 -->
 
-# Adapter utilities
+# LyCORIS
 
 [LyCORIS](https://hf.co/papers/2309.14859) (Lora beYond Conventional methods, Other Rank adaptation Implementations for Stable diffusion) are LoRA-like matrix decomposition adapters that modify the cross-attention layer of the UNet. The [LoHa](loha) and [LoKr](lokr) methods inherit from the `Lycoris` classes here.
 

docs/source/package_reference/config.md

@@ -4,7 +4,7 @@ rendered properly in your Markdown viewer.
 
 # Configuration
 
-The configuration classes stores the configuration of a [`PeftModel`], PEFT adapter models, and the configurations of [`PrefixTuning`], [`PromptTuning`], and [`PromptEncoder`]. They contain methods for saving and loading model configurations from the Hub, specifying the PEFT method to use, type of task to perform, and model configurations like number of layers and number of attention heads.
+[`PeftConfigMixin`] is the base configuration class for storing the adapter configuration of a [`PeftModel`], and [`PromptLearningConfig`] is the base configuration class for soft prompt methods (p-tuning, prefix tuning, and prompt tuning). These base classes contain methods for saving and loading model configurations from the Hub, specifying the PEFT method to use, type of task to perform, and model configurations like number of layers and number of attention heads.
 
 ## PeftConfigMixin
 

docs/source/package_reference/llama_adapter.md

@@ -16,7 +16,7 @@ rendered properly in your Markdown viewer.
 
 # Llama-Adapter
 
-[Llama-Adapter](https://hf.co/papers/2303.16199) is a PEFT method specifically designed for turning Llama into an instruction-following model. The Llama model is frozen and only a set of adaptation prompts prefixed to the input instruction tokens are learned. Since randomly initialized modules inserted into the model can cause the model to lose some of it's existing knowledge, Llama-Adapter uses zero-initialized attention with zero gating to progressively add the instructional prompts with the model.
+[Llama-Adapter](https://hf.co/papers/2303.16199) is a PEFT method specifically designed for turning Llama into an instruction-following model. The Llama model is frozen and only a set of adaptation prompts prefixed to the input instruction tokens are learned. Since randomly initialized modules inserted into the model can cause the model to lose some of its existing knowledge, Llama-Adapter uses zero-initialized attention with zero gating to progressively add the instructional prompts to the model.
 
 The abstract from the paper is:
 

docs/source/package_reference/peft_model.md

@@ -4,7 +4,7 @@ rendered properly in your Markdown viewer.
 
 # Models
 
-[`PeftModel`] is the base model class for specifying the base Transformer model and configuration to apply a PEFT method to. The base `PeftModel` contains methods for loading and saving models from the Hub, and supports the [`PromptEncoder`] for prompt learning.
+[`PeftModel`] is the base model class for specifying the base Transformer model and configuration to apply a PEFT method to. The base `PeftModel` contains methods for loading and saving models from the Hub.
 
 ## PeftModel
 

docs/source/package_reference/peft_types.md

@@ -16,7 +16,7 @@ rendered properly in your Markdown viewer.
 
 # PEFT types
 
-`PeftType` includes the supported adapters in PEFT, and `TaskType` includes PEFT-supported tasks.
+[`PeftType`] includes the supported adapters in PEFT, and [`TaskType`] includes PEFT-supported tasks.
 
 ## PeftType
 

docs/source/package_reference/tuners.md

@@ -16,7 +16,7 @@ rendered properly in your Markdown viewer.
 
 # Tuners
 
-A tuner (or adapter) is a module that can be plugged into a `torch.nn.Module`. [`BaseTuner`] base class for other tuners and provides shared methods and attributes for preparing an adapter configuration and replacing a target module with the adapter module. [`BaseTunerLayer`] is a tuner mixin offering methods and attributes for managing adapters such as merging and unmerging, and activating and disabling adapters.
+A tuner (or adapter) is a module that can be plugged into a `torch.nn.Module`. [`BaseTuner`] base class for other tuners and provides shared methods and attributes for preparing an adapter configuration and replacing a target module with the adapter module. [`BaseTunerLayer`] is a base class for adapter layers. It offers methods and attributes for managing adapters such as activating and disabling adapters.
 
 ## BaseTuner