4 Repos
Processes and tools for fine-tuning and adapting machine learning models for specific output requirements.
Distinguishing note: Focuses on the workflow of model adaptation rather than the training of base models.
Explore 4 awesome GitHub repositories matching artificial intelligence & ml · Model Optimization Workflows. Refine with filters or upvote what's useful.
Fooocus is a generative image interface designed to simplify the creation of high-quality visual content from text descriptions. It functions as a latent diffusion pipeline and model orchestrator, managing the complex interactions between neural network layers, mathematical samplers, and hardware resource allocation to produce professional-grade imagery. The project distinguishes itself through a sophisticated prompt engineering engine and modular style management. Users can dynamically modify output characteristics by injecting style adapters directly into prompts or by utilizing wildcards a
Optimizes image generation models using custom style adapters and refined parameter tuning.
Heretic is a specialized toolkit for removing safety alignment and refusal constraints from transformer-based language models. It utilizes directional ablation to suppress model refusals and restore unrestricted output capabilities. The project provides a framework for quantifying the effectiveness of these modifications by measuring refusal rates and evaluating divergence from the original model behavior. It also includes a suite for residual vector analysis, allowing for the calculation of geometric relationships between prompts and the visualization of hidden states across model layers. A
Provides a quantitative workflow using vector visualization to optimize directional ablation for removing model refusals.
Obliteratus is a weight ablation framework and refusal removal tool designed to identify and delete the internal representations responsible for content refusals in large language models without retraining. It functions as a circuit analysis suite that maps the geometric structure of model guardrails to isolate the specific layers and attention heads that enforce refusals. The project enables the removal of these behaviors through geometric projection, rank-1 adapter ablation for reversible modifications, and the application of steering vectors to alter behavior during inference. It includes
Uses directional ablation workflows to remove specific model behaviors without altering base weights.
This is the companion code repository for the third edition of the book Python Machine Learning. It delivers the entire learning path as a structured collection of Jupyter notebooks that progress from classical machine learning algorithms to advanced deep learning models, with every concept demonstrated through executable code and narrative text. What distinguishes this resource is its pedagogical design. Each notebook cell encapsulates a single conceptual step, letting readers run, inspect, and modify discrete units of learning. The code provides interchangeable implementations of deep lea
Refines model performance through systematic hyperparameter tuning and cross-validation techniques.