Bergen
BERGEN is a library for benchmarking question-answering retrieval-augmented generation (RAG) systems.
Guide: Run and evaluate a BERGEN RAG benchmarkExplore AI, agents, blockchain and crypto through official sources, concrete tasks and practical guides.
Browse by purpose and evidence; use an exact name, ticker or addressable project domain to narrow the search.
BERGEN is a library for benchmarking question-answering retrieval-augmented generation (RAG) systems.
Guide: Run and evaluate a BERGEN RAG benchmarkBerkeley Neural Parser is a Python NLP parser that generates constituency trees using pretrained neural models for 11 languages.
Guide: Set up the parser with spaCy for EnglishBert is a Python and TensorFlow repository providing pre-trained BERT models and code for natural-language processing and fine-tuning.
Guide: Select and download a compact BERT checkpointBert Classification Tutorial is a Python code repository that teaches BERT fine-tuning for text classification through a worked Japanese livedoor news-categorization example and a reusable data-preparation, training and evaluation workflow.
Guide: Set up the tutorial environment with PoetryBert Faiss Qa System is a Python application for asking questions about a document collection.
Guide: Set up and open the local document Q&A interfaceBert Multi Label Text Classification is a Python/PyTorch implementation for multi-label text classification with pretrained BERT and XLNet models.
Guide: Prepare and fine-tune the BERT exampleBert Nli is an open-source Python project that provides fine-tuned BERT and ALBERT models and code for natural-language inference: classifying a sentence pair as contradiction, entailment or neutral.
Guide: Set up the project and download its datasets and modelBert Of Theseus is an open-source Python and PyTorch implementation for compressing BERT by progressively replacing its components with smaller successor components.
Guide: Load the pretrained MNLI modelBert Relation Extraction is a public Python and PyTorch implementation of BERT-family relation-extraction models based on the ACL 2019 “Matching the Blanks” paper, with additional ALBERT and BioBERT variants.
Guide: Run sentence-level relation inferenceBert Sklearn is a Python library that wraps BERT fine-tuning in scikit-learn-style classifier, regressor and token-classifier workflows.
Guide: Install Bert SklearnBert Squeeze is a Python library of code for reducing the size or inference latency of Transformer-based models, with implementations for distillation, pruning and quantization and early exiting listed among its techniques.
Guide: Set up the Bert Squeeze repositoryBert4Torch is an open-source Python library that implements transformer models using PyTorch and provides workflows for fine-tuning, NLP tasks, large-language-model inference, and serving.
Guide: Start a documented local model-serving modeBertbasedcorrectionmodels is a Python repository of PyTorch implementations of BERT-based Chinese spelling-error correction models, with configurations and examples for preparing SIGHAN data, training models and running inference.
Guide: Run inference on text with a project checkpointBertclassifier is an MIT-licensed Python project that uses PyTorch and Hugging Face Transformers to train and run a BERT-based Chinese text classifier.
Guide: Set up and run the documented CNews workflowBERTimbau is a repository of pretrained, cased BERT-Base and BERT-Large models for Portuguese, with TensorFlow and PyTorch artifacts and usage materials for downstream NLP tasks.
Guide: Load a pretrained model with Hugging Face TransformersBertopic is the public project for BERTopic, a Python library that uses BERT-based text representations and class-based TF-IDF to discover and represent interpretable topics in document collections.
Guide: Install BERTopic in a Python environmentBERTScore is an open-source Python library and command-line tool for evaluating generated text against reference text using contextual representations from pretrained language models.
Guide: Score candidate text files against referencesBertsearch is a Python search application that uses a pretrained BERT model to vectorize document text, stores the vectors in Elasticsearch, and provides a browser interface for searching indexed documents.
Guide: Set up Bertsearch and index CSV documents