jarobyte91 / pytorch_beam_search
A lightweight implementation of Beam Search for sequence models in PyTorch.
☆43Updated 2 months ago
Related projects: ⓘ
- ☆95Updated 2 years ago
- PyTorch reimplementation of REALM and ORQA☆22Updated 2 years ago
- ☆59Updated last year
- Implementation of the GBST block from the Charformer paper, in Pytorch☆117Updated 3 years ago
- Official Implementation of "DialogLM: Pre-trained Model for Long Dialogue Understanding and Summarization."☆137Updated last year
- Reduce the size of pretrained Hugging Face models via vocabulary trimming.☆39Updated last year
- [TMLR'23] Contrastive Search Is What You Need For Neural Text Generation☆118Updated last year
- A PyTorch implementation of paper "Learning Shared Semantic Space for Speech-to-Text Translation", ACL (Findings) 2021☆46Updated 2 years ago
- Code and Models for the paper "End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answering" (NeurIPS 20…☆107Updated 2 years ago
- Systems submitted to IWSLT 2021 by the MT-UPC group.☆14Updated last year
- An official implementation of "BPE-Dropout: Simple and Effective Subword Regularization" algorithm.☆48Updated 3 years ago
- ☆155Updated last month
- Code for Editing Factual Knowledge in Language Models☆134Updated 2 years ago
- ☆92Updated 2 years ago
- code associated with ACL 2021 DExperts paper☆109Updated last year
- DiffusER: Discrete Diffusion via Edit-based Reconstruction (Reid, Hellendoorn & Neubig, 2022)☆54Updated last year
- Pytorch implementation of “Recursive Non-Autoregressive Graph-to-Graph Transformer for Dependency Parsing with Iterative Refinement”☆61Updated 3 years ago
- back translation for NLP☆24Updated 3 years ago
- Code for "Finetuning Pretrained Transformers into Variational Autoencoders"☆35Updated 2 years ago
- Semi-autoregressive Simplex-based Diffusion Language Model for Text Generation and Modular Control☆63Updated last year
- ☆10Updated 3 years ago
- The original Backpack Language Model implementation, a fork of FlashAttention☆63Updated last year
- DSTC10 Track 2 - Knowledge-grounded Task-oriented Dialogue Modeling on Spoken Conversations☆61Updated last year
- [EMNLP'21] Mirror-BERT: Converting Pretrained Language Models to universal text encoders without labels.☆75Updated 2 years ago
- Code and models for the paper "Questions Are All You Need to Train a Dense Passage Retriever (TACL 2023)"☆61Updated last year
- ☆57Updated 2 years ago
- Semantic parsers based on encoder-decoder framework☆90Updated last year
- ☆73Updated 5 months ago
- Pytorch implementation of paper "Efficient Nearest Neighbor Language Models" (EMNLP 2021)☆71Updated 2 years ago
- Long-context pretrained encoder-decoder models☆95Updated last year