Ce face p-e-w/heretic?

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.

Care sunt principalele funcționalități ale p-e-w/heretic?

Principalele funcționalități ale p-e-w/heretic sunt: Directional Ablations, Censorship Removal, Censorship Removal Frameworks, Visualizations, Visualizers, Internal State Analysis, Residual Visualizations, Weight Manipulations.

Care sunt câteva alternative open-source pentru p-e-w/heretic?

Alternativele open-source pentru p-e-w/heretic includ: elder-plinius/obliteratus — Obliteratus is a weight ablation framework and refusal removal tool designed to identify and delete the internal… open-compass/opencompass — OpenCompass is an open-source framework for standardized benchmarking of large language models. It provides a… internlm/opencompass — OpenCompass is a comprehensive evaluation platform, benchmarking suite, and distributed model evaluator designed to… tflearn/tflearn — tflearn is a deep learning framework and high-level API wrapper for TensorFlow. It provides a toolkit for designing… kiln-ai/kiln — Kiln is an LLM development workbench and evaluation framework designed for designing, testing, and optimizing prompts… huggingface/sentence-transformers — This project is a transformer-based framework for generating dense and sparse vector embeddings of text and multimodal…

Heretic - remove LLM safety filters

Name: p-e-w/heretic
Author: p-e-w

Features

Directional Ablations - Provides a quantitative workflow using vector visualization to optimize directional ablation for removing model refusals.
Censorship Removal - Removes safety alignment and refusal constraints from language models to restore unrestricted output capabilities.
Censorship Removal Frameworks - Implements a system for removing safety alignment and censorship constraints to restore original output capabilities.
Visualizations - Generates 2D scatter plots of high-dimensional residual vectors to track model activation transformations across layers.
Visualizers - Generates 2D scatter plots to visualize how residual vectors transform across model layers.
Internal State Analysis - Analyzes hidden states and residual vectors to understand how language models process and categorize specific prompts.
Residual Visualizations - Computes hidden states and generates 2D scatter plots to visualize how residuals transform across model layers.
Weight Manipulations - Directly alters internal transformer parameters to suppress specific behavioral triggers without requiring full model retraining.
Residual Geometry Analysis - Calculates quantitative metrics and cosine similarity tables to analyze relationships between residual vectors of prompts.
Residual Vector Analysis - Computes hidden states and analyzes geometric relationships between residual vectors of harmful and harmless prompts.
Model Alignment Removal - Provides a specialized toolkit for removing safety alignment and refusal constraints using directional ablation.
LLM Evaluation Frameworks - Quantifies the effectiveness of censorship removal by measuring refusal rates and divergence from the base model.
Model Evaluation Metrics - Provides metrics to measure behavioral divergence between original and modified models to ensure intelligence preservation.
Model Evaluation Frameworks - Quantifies censorship removal effectiveness by measuring refusal rates and divergence from original model behavior.
Ablation Optimizations - Optimizes directional ablation parameters to suppress model refusals while preserving overall model intelligence.
Training and Fine-Tuning - Tool for removing censorship from language models.

Alternative open-source pentru Heretic

Proiecte open-source similare, clasificate după numărul de funcționalități comune cu Heretic.

elder-plinius/obliteratus
elder-plinius/OBLITERATUS
6,736Vezi pe GitHub
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
Python
Vezi pe GitHub6,736
open-compass/opencompass
open-compass/opencompass
6,678Vezi pe GitHub
OpenCompass is an open-source framework for standardized benchmarking of large language models. It provides a configurable evaluation pipeline that supports both objective and subjective assessment, using a dual-engine architecture to handle closed-form answer comparison and open-ended response rating. The framework is designed as a modular platform where datasets, models, and metrics are composed through declarative YAML configuration files. The framework distinguishes itself through its extensible model integration layer, which supports custom models, HuggingFace models, and third-party API
Pythonbenchmarkchatgptevaluation
Vezi pe GitHub6,678
internlm/opencompass
InternLM/opencompass
7,096Vezi pe GitHub
OpenCompass is a comprehensive evaluation platform, benchmarking suite, and distributed model evaluator designed to measure the performance and accuracy of large language models. It provides a framework for benchmarking both open-source and API-based models against diverse datasets using standardized metrics and reproducible pipelines. The project features an automated judging framework that uses language models as judges to score and verify the quality of generated text. It includes a performance leaderboard system for comparing the relative capabilities of various models across industry-sta
Python
Vezi pe GitHub7,096
tflearn/tflearn
tflearn/tflearn
9,579Vezi pe GitHub
tflearn is a deep learning framework and high-level API wrapper for TensorFlow. It provides a toolkit for designing neural network architectures and a system for executing training loops and optimizing model weights across CPUs and GPUs. The project simplifies the process of building and training models through a modular interface and a high-level API for prototyping. It includes specialized utilities for deep learning visualization, allowing for the generation of graphical diagrams to analyze network structures, weights, gradients, and activations. The framework covers a broad range of capa
Pythondata-sciencedeep-learningmachine-learning
Vezi pe GitHub9,579

Vezi toate cele 30 alternative pentru Heretic

Alternative open-source pentru Heretic

Proiecte open-source similare, clasificate după numărul de funcționalități comune cu Heretic.

elder-plinius/obliteratus
elder-plinius/OBLITERATUS
6,736Vezi pe GitHub
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
Python
Vezi pe GitHub6,736
open-compass/opencompass
open-compass/opencompass
6,678Vezi pe GitHub
OpenCompass is an open-source framework for standardized benchmarking of large language models. It provides a configurable evaluation pipeline that supports both objective and subjective assessment, using a dual-engine architecture to handle closed-form answer comparison and open-ended response rating. The framework is designed as a modular platform where datasets, models, and metrics are composed through declarative YAML configuration files. The framework distinguishes itself through its extensible model integration layer, which supports custom models, HuggingFace models, and third-party API
Pythonbenchmarkchatgptevaluation
Vezi pe GitHub6,678
internlm/opencompass
InternLM/opencompass
7,096Vezi pe GitHub
OpenCompass is a comprehensive evaluation platform, benchmarking suite, and distributed model evaluator designed to measure the performance and accuracy of large language models. It provides a framework for benchmarking both open-source and API-based models against diverse datasets using standardized metrics and reproducible pipelines. The project features an automated judging framework that uses language models as judges to score and verify the quality of generated text. It includes a performance leaderboard system for comparing the relative capabilities of various models across industry-sta
Python
Vezi pe GitHub7,096
tflearn/tflearn
tflearn/tflearn
9,579Vezi pe GitHub
tflearn is a deep learning framework and high-level API wrapper for TensorFlow. It provides a toolkit for designing neural network architectures and a system for executing training loops and optimizing model weights across CPUs and GPUs. The project simplifies the process of building and training models through a modular interface and a high-level API for prototyping. It includes specialized utilities for deep learning visualization, allowing for the generation of graphical diagrams to analyze network structures, weights, gradients, and activations. The framework covers a broad range of capa
Pythondata-sciencedeep-learningmachine-learning
Vezi pe GitHub9,579

Vezi toate cele 30 alternative pentru Heretic

p-e-wheretic

Heretic

Features

Alternative open-source pentru Heretic

elder-plinius/OBLITERATUS

open-compass/opencompass

InternLM/opencompass

tflearn/tflearn

Întrebări frecvente

Istoric stele

Alternative open-source pentru Heretic

elder-plinius/OBLITERATUS

open-compass/opencompass

InternLM/opencompass

tflearn/tflearn

Întrebări frecvente