Open-source alternatives to LLMSanitize

Make any LLM to think deeper like OpenAI o1 and deepseek R1!

This is a fork of CyberZHG/keras_bert which supports Keras BERT on TPU.

Multi-Modal Multi-Task Learning

BertViz is a diagnostic toolset for visualizing attention heads and internal model behaviors to interpret how language models process text. It serves as an interpretability tool and debugger for natural language processing models, specifically providing interactive maps of attention mechanisms within Transformer architectures. The project enables the analysis of token relationships through detailed views of specific attention heads and layers. It supports global attention visualization across all layers, encoder-decoder attention mapping, and the inspection of individual neurons within query

LLM Reasoners is a library to enable LLMs to conduct complex reasoning, with advanced reasoning algorithms. It approaches multi-step reasoning as planning and searches for the optimal reasoning chain, which achieves the best balance of exploration vs exploitation with the idea of "World Model"…

This repo contains end-to-end recipes to pretrain and finetune the BERT (Bidirectional Encoder Representations from Transformers) language representation model using Azure Machine Learning service.

Read more about AIDungeon2 and how it was built here.

CodeTF: One-stop Transformer Library for State-of-the-art Code LLM

1. (ICLR 2024) A Semantic Invariant Robust Watermark for Large Language Models

This Word Does Not Exist

The original code is from https://github.com/memray/seq2seq-keyphrase-pytorch, which is used to do keyphrase generation using seq2seq with attention model.

This is a repository of Japanese BERT model with SentencePiece tokenizer.

EasyEdit is a framework and toolkit designed for updating, inserting, or erasing specific factual information within large language models without requiring full retraining. It functions as a parameter modifier and knowledge editing system capable of performing targeted weight updates across diverse model architectures. The project distinguishes itself by supporting both text-based and multimodal model editing, allowing for knowledge updates across image and text modalities. It provides utilities for model steering to adjust personality and reasoning patterns in real time via activation inter