ayaka14732 / TrAVis
TrAVis: Visualise BERT attention in your browser
β55Updated last year
Related projects β
Alternatives and complementary repositories for TrAVis
- JAX implementation of the bart-base modelβ29Updated last year
- πͺ A toolkit to help search for papers from aclanthology, arXiv and dblp.β43Updated last year
- YATO: Yet Another deep learning based Text analysis Open toolkitβ43Updated last year
- Reasoning by Communicating with Agentsβ21Updated last month
- The official implementation of "Distilling Relation Embeddings from Pre-trained Language Models, EMNLP 2021 main conference", a high-qualβ¦β46Updated last year
- Large-scale query-focused multi-document Summarization datasetβ10Updated 3 years ago
- Modified version of T5-DST for Dialogue State Tracking.β18Updated 2 years ago
- An open-source NLP library: fast text cleaning and preprocessingβ23Updated 3 years ago
- β11Updated 3 months ago
- ROUGE for multilingual Summarizationβ23Updated 3 years ago
- A Python implementation of Toolformer using Huggingface Transformersβ15Updated last year
- In-Context Alignment: Chat with Vanilla Language Models Before Fine-Tuningβ33Updated last year
- A GPT-based generative LM for combined text and math formulas, leveraging tree-based formula encoding.β33Updated last year
- The multilingual variant of GLM, a general language model trained with autoregressive blank infilling objectiveβ62Updated last year
- β27Updated last year
- This is a new metric that can be used to evaluate faithfulness of text generated by LLMs. The work behind this repository can be found heβ¦β31Updated last year
- Online BaseHangul Encoder And Decoderβ12Updated last year
- Are foundation LMs multilingual knowledge bases? (EMNLP 2023)β18Updated 11 months ago
- A library for computing diverse text characteristics and using them to analyze data sets and models with ease.β40Updated 2 years ago
- β14Updated last month
- Source code for the GPT-2 story generation models in the EMNLP 2020 paper "STORIUM: A Dataset and Evaluation Platform for Human-in-the-Loβ¦β38Updated 9 months ago
- The enhanced version of ZEN, larger and more powerful.β28Updated 2 years ago
- SWIM-IR is a Synthetic Wikipedia-based Multilingual Information Retrieval training set with 28 million query-passage pairs spanning 33 laβ¦β44Updated 11 months ago
- The unified platform for data-related resources.β131Updated last year
- Seahorse is a dataset for multilingual, multi-faceted summarization evaluation. It consists of 96K summaries with human ratings along 6 qβ¦β85Updated 8 months ago
- Can LLMs generate code-mixed sentences through zero-shot prompting?β11Updated last year
- β33Updated last year
- β27Updated 8 months ago
- This repo explores how AMR to address tasks difficult for LLMsβ11Updated 9 months ago