Results for “parseur”

Protocol-level two-agent paper writing workflow. Use when the user wants Codex to plan and review from global context while DeepSeek writes or revises the manuscript through the global deepseek-agent skill, with muxing-style-review used for explicit prose style checks.

Trains and analyzes Sparse Autoencoders (SAEs) with SAELens to decompose neural network activations into interpretable features, covering loading pre-trained SAEs, training custom ones, and feature steering.

Process large-scale ML datasets with distributed streaming execution across CPU/GPU, supporting Parquet, CSV, JSON, images, and integration with PyTorch, TensorFlow, and Ray Train.

Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.

Train and analyze Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features for mechanistic interpretability research.

Assesses genome, transcriptome, and protein completeness with BUSCO v6, automatically resolving the correct lineage from an organism description and generating reproducible reports.

Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or enabling faster inference on hardware accelerators. Covers unstructured pruning, structured pruning, N:M sparsity, magnitude pruning, and one-shot methods.