ecco
Language model explainer
An interactive visualization library for exploring and understanding transformer-based language models
Explain, analyze, and visualize NLP language models. Ecco creates interactive visualizations directly in Jupyter notebooks explaining the behavior of Transformer-based language models (like GPT2, BERT, RoBERTA, T5, and T0).
2k stars
24 watching
169 forks
Language: Jupyter Notebook
last commit: 3 months ago explorableslanguage-modelsnatural-language-processingnlppytorchvisualization
Related projects:
| Repository | Description | Stars |
|---|---|---|
 giuseppec/iml | Provides methods to interpret and explain the behavior of machine learning models | 492 |
 lantanacamara/lightgbmexplainer | An R package to provide interpretability features for LightGBM models. | 23 |
 elanmart/psmm | An implementation of a neural network model for character-level language modeling. | 50 |
 jcgood/desmeme | A software framework for analyzing and visualizing linguistic templates using graphs and similarity measures. | 4 |
 lxtgh/omg-seg | Develops an end-to-end model for multiple visual perception and reasoning tasks using a single encoder, decoder, and large language model. | 1,300 |
 marcotcr/anchor | Provides a method to generate explanations for predictions made by any black box classifier. | 798 |
 nytud/emlam | Preprocessing and modeling scripts for Hungarian language modeling using Python and TensorFlow. | 3 |
 dfki-nlp/gevalm | Evaluates German transformer language models with syntactic agreement tests | 7 |
 hit-scir/elmoformanylangs | Provides pre-trained ELMo representations for multiple languages to improve NLP tasks. | 1,463 |
 mshukor/evalign-icl | Evaluating and improving large multimodal models through in-context learning | 20 |
 thomasp85/lime | An R package for providing explanations of predictions made by black box classifiers. | 485 |
 l0sg/relational-rnn-pytorch | An implementation of DeepMind's Relational Recurrent Neural Networks (Santoro et al. 2018) in PyTorch for word language modeling | 244 |
 scicloj/scicloj.ml.clj-djl | Provides pre-trained machine learning models for natural language processing tasks using Clojure and the clj-djl framework. | 0 |
 01-ai/yi | A series of large language models trained from scratch to excel in multiple NLP tasks | 7,699 |
 vhellendoorn/code-lms | A guide to using pre-trained large language models in source code analysis and generation | 1,782 |