6 个仓库
Awesome GitHub RepositoriesWeight Extraction
Retrieving and standardizing internal model weights for structural analysis across different architectures.
Distinct from Model Architecture Analysis: Distinct from model extraction (surrogates) or parameter tuning; focuses on the technical retrieval and formatting of weights.
Explore 6 awesome GitHub repositories matching artificial intelligence & ml · Weight Extraction. Refine with filters or upvote what's useful.
Awesome Weight Extraction GitHub Repositories
用 AI 发现最棒的仓库。我们将通过 AI 为您搜索最匹配的仓库。
- opengvlab/llama-adapter
OpenGVLab/LLaMA-Adapter
5,921在 GitHub 上查看LLaMA-Adapter 是一个参数高效的微调框架，旨在利用最少的可训练参数来适配大型语言模型。它作为一个指令微调工具和多模态适配器，允许预训练模型遵循人类指令并处理非文本数据。 该项目专注于将图像、视频、音频和传感器数据集成到语言模型中，以实现跨模态理解。它通过使用轻量级适配器实现 LLaMA 模型的定制，允许独立于完整模型检查点提取和存储学习到的权重。 该框架涵盖了整个训练和评估生命周期，包括适配器预训练和精炼。它提供了多模态数据集成功能，并针对基准数据集评估模型性能，以衡量响应准确性。
Isolates trained adapter parameters from full model checkpoints for lightweight storage and portable deployment.
Python - tachibanayoshino/animeganv2
TachibanaYoshino/AnimeGANv2
5,366在 GitHub 上查看AnimeGANv2 是一个生成对抗网络训练框架和图像风格化工具，旨在将真实世界的照片和视频转换为动漫风格的图像。它作为动漫风格生成器，通过监督式风格迁移将真实场景转换为动画。 该项目提供了一个用于训练风格模型并从深度学习检查点提取特定生成器权重参数的系统，从而创建用于推理的轻量级模型。它专注于风景图像风格化以及从提供的训练集中模仿特定艺术风格的能力。 该框架支持照片转动漫和视频转动漫，通过在单个视频帧之间应用一致的美学效果。其功能涵盖通用 AI 艺术生成以及训练生成器以复制目标风格。
Isolates generator weight parameters from training checkpoints for use during model inference.
Python - tachibanayoshino/animegan
TachibanaYoshino/AnimeGAN
4,603在 GitHub 上查看AnimeGAN 是一个使用 TensorFlow 开发的生成对抗网络（GAN）和图像转换器。它专为照片转动漫风格迁移而设计，利用深度学习系统将现实世界的照片和视频帧转换为动漫风格的图像。 该系统包括一个视频转动漫转换器，可在连续帧之间应用一致的视觉转换。它既支持在艺术数据集上训练生成网络以复制特定风格，也支持从检查点（Checkpoints）提取生成器权重以进行高效推理。 该项目提供图像优化工具，包括边缘平滑和模糊处理，以增强视觉过渡。它还通过连续帧流水线管理视频文件的处理。
Isolates generator weights from trained checkpoints to enable lightweight style transfer inference.
Pythonanime-imagesanimeganhayao-style - bowang-lab/medsam
bowang-lab/MedSAM
4,316在 GitHub 上查看MedSAM 是一个深度学习框架，旨在自动化 2D 和 3D 医学影像中解剖结构的分割。它提供专门的工具，用于在自定义医学数据集上微调预训练的分割权重，并根据真实标签评估这些预测的准确性。 该项目专注于将 Segment Anything Model (SAM) 架构应用于医学领域，通过边界框和点提示等提示引导方法实现特定解剖结构的隔离。 该系统涵盖了完整的医学 AI 工作流，包括用于强度归一化和空间重采样的数据工程，以及用于检查点转换和权重提取的模型管理。它支持通过单 GPU 或分布式 GPU 流水线进行训练，以处理大规模影像数据集。
Provides tools for extracting and standardizing model weights from checkpoints to ensure correct loading during inference.
Jupyter Notebook - stability-ai/stable-audio-tools
Stability-AI/stable-audio-tools
3,790在 GitHub 上查看Stable-audio-tools is a toolkit for training and deploying latent diffusion models for high-fidelity audio synthesis. It provides a framework for generating audio by iteratively refining noise within a compressed latent space, using specialized encoders to preserve temporal and spectral features of the audio signal. The project features a system for adapting pre-trained audio checkpoints to new datasets through modular initialization and configuration files. It includes utilities for weight extraction and inference model export, which remove training metadata and optimizer states to create li
Extracts core weights from training wrappers to reduce file size for efficient inference and training.
Python - transformerlensorg/transformerlens
TransformerLensOrg/TransformerLens
3,098在 GitHub 上查看TransformerLens is a library for mechanistic interpretability research designed to reverse engineer the learned algorithms within large language models. It provides a standardized framework for wrapping diverse transformer architectures, allowing researchers to extract, manipulate, and analyze internal activations and weights through a consistent interface. The project distinguishes itself through a comprehensive system of activation hooks that can capture, patch, and ablate internal tensors during the forward pass. It includes specialized utilities for decomposing fused projections, material
Extracts internal model weights and converts them into a standardized format to facilitate analysis across diverse architectures.
Python
