awesome-repositories.com
Blog
awesome-repositories.com

Descoperă cele mai bune repository-uri open source cu căutare AI.

ExploreazăCăutări recomandateAlternative open-sourceSoftware self-hostedBlogHartă site
ProiectDespreCum realizăm clasamentulPresăServer MCP
LegalConfidențialitateTermeni
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
·
cdpierse avatar

cdpierse/transformers-interpret

0
View on GitHub↗
1,412 stele·100 fork-uri·Jupyter Notebook·Apache-2.0·6 vizualizări

Transformers Interpret

Transformers-interpret este o bibliotecă de diagnosticare concepută pentru interpretarea modelelor de machine learning bazate pe transformatoare. Aceasta funcționează ca un framework de atribuire care cuantifică contribuția token-urilor individuale de intrare la predicțiile finale ale unui model, permițând utilizatorilor să auditeze modelele de decizie și să depaneze sarcinile de procesare a limbajului natural (NLP).

Biblioteca utilizează analiza bazată pe gradient și introspecția bazată pe hook-uri pentru a urmări modul în care caracteristicile specifice de intrare influențează output-urile modelului. Prin maparea scorurilor de atribuire numerice abstracte înapoi la unități lingvistice lizibile pentru oameni, aceasta oferă o vedere clară asupra modului în care modelele procesează textul. Framework-ul suportă analiza țintită, permițând utilizatorilor să explice predicțiile pentru clase specifice sau să examineze relațiile de intrare pereche.

Dincolo de atribuirea de bază, instrumentul include capabilități de vizualizare care generează reprezentări grafice și tabelare ale importanței caracteristicilor. Aceste output-uri ajută la verificarea faptului că modelele se bazează pe date relevante în loc de modele neintenționate, facilitând o înțelegere mai profundă a comportamentului modelului în diverse arhitecturi de transformatoare.

Features

  • Attribution Libraries - Provides a diagnostic utility for inspecting model behavior by generating graphical representations of how specific text segments drive classification outcomes.
  • Transformer Explainability - Provides diagnostic tools to quantify and visualize how individual input tokens influence predictions in transformer-based machine learning models.
  • Model Interpretability Frameworks - Provides a toolkit for analyzing feature importance and decision patterns in deep learning architectures by quantifying token contributions.
  • Token Attribution - Determines the contribution of individual input tokens to a model prediction to reveal which specific features drive classification outcomes.
  • Feature Importance Attribution - Quantifies the contribution of input data to model outputs to better understand the underlying logic and decision patterns.
  • Attribution Gradients - Computes feature importance by backpropagating model outputs through the computational graph to input gradients.
  • Activation and Gradient Hooking - Intercepts internal neural network activations and gradients by attaching listeners to specific layers during execution.
  • Integrated Gradients Attribution Methods - Approximates the integral of gradients along a path from a baseline input to the target to ensure accurate attribution.
  • Model Auditing Tools - Verifies that a predictive model relies on relevant features rather than unintended patterns when making decisions.
  • Agnostic Attribution Engines - Provides a framework-agnostic engine that decouples attribution logic from specific transformer model architectures.
  • Model Explanation Visualizations - Creates interactive or static visual representations of feature importance to facilitate detailed analysis of model behavior.
  • Class-Specific Explainers - Targets a specific output class for attribution analysis to verify if a model relies on expected features for a particular category.
  • Transformer Explainability Tools - Visualizes how individual words or tokens influence the final predictions made by deep learning models built with transformer architectures.
  • Target Class Explainers - Computes attribution scores for specific output classes regardless of the primary prediction to verify if the model focuses on relevant input features.
  • NLP Debugging Tools - Identifies which specific parts of an input text cause a model to make incorrect or biased classification decisions.
  • Pairwise Relationship Analyzers - Measures how specific text segments influence similarity scores between two inputs to understand the underlying logic behind model comparisons.
  • Attribution Visualizers - Generates graphical representations of token importance scores to help users interpret how specific inputs influence model output decisions.

Istoric stele

Graficul istoricului de stele pentru cdpierse/transformers-interpretGraficul istoricului de stele pentru cdpierse/transformers-interpret

Căutare AI

Explorează mai multe repository-uri excelente

Descrie ce ai nevoie în limbaj simplu — AI-ul sortează mii de proiecte open source selectate în funcție de relevanță.

Start searching with AI

Colecții curatoriate care includ Transformers Interpret

Colecții selectate manual în care apare Transformers Interpret.
  • Instrumente pentru interpretarea modelelor de Machine Learning

Întrebări frecvente

Ce face cdpierse/transformers-interpret?

Transformers-interpret este o bibliotecă de diagnosticare concepută pentru interpretarea modelelor de machine learning bazate pe transformatoare. Aceasta funcționează ca un framework de atribuire care cuantifică contribuția token-urilor individuale de intrare la predicțiile finale ale unui model, permițând utilizatorilor să auditeze modelele de decizie și să depaneze sarcinile de procesare a limbajului natural (NLP).

Care sunt principalele funcționalități ale cdpierse/transformers-interpret?

Principalele funcționalități ale cdpierse/transformers-interpret sunt: Attribution Libraries, Transformer Explainability, Model Interpretability Frameworks, Token Attribution, Feature Importance Attribution, Attribution Gradients, Activation and Gradient Hooking, Integrated Gradients Attribution Methods.

Care sunt câteva alternative open-source pentru cdpierse/transformers-interpret?

Alternativele open-source pentru cdpierse/transformers-interpret includ: pytorch/captum — Captum is an open-source library for explaining model predictions by attributing them to input features, neurons, and… jacobgil/vit-explain — Vit-explain is a diagnostic framework designed to interpret the decision-making processes of vision transformer… pair-code/lit — Lit is a machine learning interpretability framework and model debugging tool designed to analyze model behavior and… rexying/gnn-model-explainer — This toolkit serves as a framework for interpreting the decision-making processes of graph neural networks. It… marcotcr/lime — This project is an agnostic model interpretability framework and explainability tool designed to provide local… shap/shap — SHAP is an explainable AI toolkit that provides a game theoretic framework for interpreting machine learning model…

Alternative open-source pentru Transformers Interpret

Proiecte open-source similare, clasificate după numărul de funcționalități comune cu Transformers Interpret.
  • pytorch/captumAvatar pytorch

    pytorch/captum

    5,652Vezi pe GitHub↗

    Captum is an open-source library for explaining model predictions by attributing them to input features, neurons, and layers using gradient-based and perturbation-based methods. It provides a modular framework for implementing, evaluating, and combining a range of explanation techniques, including gradient-based attribution, perturbation-based analysis, game-theoretic Shapley value approximation, and surrogate model explanations, with support for parallelization and noise stabilization. The library distinguishes itself through its breadth of attribution methods and its support for advanced in

    Python
    Vezi pe GitHub↗5,652
  • jacobgil/vit-explainAvatar jacobgil

    jacobgil/vit-explain

    1,090Vezi pe GitHub↗

    Vit-explain is a diagnostic framework designed to interpret the decision-making processes of vision transformer models. It functions as a toolkit for inspecting internal model states, allowing users to map visual attention and analyze how specific image features influence classification outcomes. The project distinguishes itself by providing post-hoc model interpretation, which enables the analysis of trained neural networks without requiring architectural modifications or retraining. It employs techniques such as hook-based feature extraction to intercept internal activations during the forw

    Pythondeep-learningexplainable-aipytorch
    Vezi pe GitHub↗1,090
  • pair-code/litAvatar PAIR-code

    PAIR-code/lit

    3,636Vezi pe GitHub↗

    Lit is a machine learning interpretability framework and model debugging tool designed to analyze model behavior and performance. It serves as an interpretability dashboard for large language models and a general performance analyzer for text, image, and tabular datasets. The project distinguishes itself through a comprehensive suite of interpretability tools, including salience map generation for feature attribution, the creation of synthetic and counterfactual examples to test robustness, and the projection of high-dimensional embeddings into visual spaces via UMAP or PCA. It further enable

    TypeScriptmachine-learningnatural-language-processingvisualization
    Vezi pe GitHub↗3,636
  • rexying/gnn-model-explainerAvatar RexYing

    RexYing/gnn-model-explainer

    1,051Vezi pe GitHub↗

    This toolkit serves as a framework for interpreting the decision-making processes of graph neural networks. It functions as a library for analyzing how these models process complex network data, providing methods to identify the specific node attributes and structural patterns that influence predictive outcomes. The project distinguishes itself by employing mask-optimized subgraph extraction and gradient-based attribution mapping to isolate the minimal components of a graph that preserve a model's original prediction. By separating graph processing layers from explanation logic, the architect

    Python
    Vezi pe GitHub↗1,051
Vezi toate cele 27 alternative pentru Transformers Interpret→