tqfang / comet-deepspeedLinks
Train large COMET (T5-3B/GPT2-XL) with small memory (on 11GB memory GPUs like 1080/2080) using DeepSpeed.
☆14Updated 3 years ago
Alternatives and similar repositories for comet-deepspeed
Users that are interested in comet-deepspeed are comparing it to the libraries listed below
Sorting:
- Code for embedding and retrieval research.☆17Updated last year
- Code and resources for papers "Generation-Augmented Retrieval for Open-Domain Question Answering" and "Reader-Guided Passage Reranking fo…☆74Updated 3 years ago
- ☆67Updated 3 years ago
- ☆45Updated 3 years ago
- Code and data of the EMNLP 2022 Main Conference paper "Reduce Catastrophic Forgetting of Dense Retrieval Training with Teleportation Nega…☆18Updated last year
- Code for EMNLP 2021 paper "CLIFF: Contrastive Learning for Improving Faithfulness and Factuality in Abstractive Summarization"☆46Updated 3 years ago
- An original implementation of "Noisy Channel Language Model Prompting for Few-Shot Text Classification"☆131Updated 3 years ago
- Authors' implementation of the paper Adaptive Information Seeking for Open-Domain Question Answering, published in EMNLP 2021.☆37Updated 2 years ago
- ☆13Updated 4 years ago
- EMNLP'2021: Simple Entity-centric Questions Challenge Dense Retrievers https://arxiv.org/abs/2109.08535☆146Updated 3 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…☆109Updated 3 years ago
- Technical Report: Is ChatGPT a Good NLG Evaluator? A Preliminary Study☆43Updated 2 years ago
- [ACL 2022] Ditch the Gold Standard: Re-evaluating Conversational Question Answering☆44Updated 3 years ago
- [EMNLP 2022] Training Language Models with Memory Augmentation https://arxiv.org/abs/2205.12674☆196Updated 2 years ago
- ☆58Updated 3 years ago
- Code and models for the paper "Questions Are All You Need to Train a Dense Passage Retriever (TACL 2023)"☆63Updated 2 years ago
- We construct and introduce DIALFACT, a testing benchmark dataset crowd-annotated conversational claims, paired with pieces of evidence fr…☆43Updated 2 years ago
- Code of ACL 2022 paper Debiased Contrastive Learning of Unsupervised Sentence Representations☆31Updated 3 years ago
- Code repo for SIGIR 2021 paper "Few-Shot Conversational Dense Retrieval"☆43Updated 3 years ago
- Code for Aesop: Paraphrase Generation with Adaptive Syntactic Control (EMNLP 2021)☆26Updated 3 years ago
- Code and Data for NeurIPS2021 Paper "A Dataset for Answering Time-Sensitive Questions"☆73Updated 3 years ago
- Code for ACL2021 long paper: Knowledgeable or Educated Guess? Revisiting Language Models as Knowledge Bases☆29Updated 3 years ago
- [EMNLP 2021] MuVER: Improving First-Stage Entity Retrieval with Multi-View Entity Representations☆31Updated 3 years ago
- ☆117Updated 3 years ago
- [EMNLP 2022] Code for our paper “ZeroGen: Efficient Zero-shot Learning via Dataset Generation”.☆48Updated 3 years ago
- An Interpretable Neuro-Symbolic Framework for Task-Oriented Dialogue Generation☆24Updated 3 years ago
- EMNLP'2022: BERTScore is Unfair: On Social Bias in Language Model-Based Metrics for Text Generation☆41Updated 2 years ago
- Code for Editing Factual Knowledge in Language Models☆141Updated 3 years ago
- [EMNLP 2022] Summarization as Indirect Supervision for Relation Extraction (SuRE)☆28Updated 2 years ago
- Source code for paper on commonsense reasoning for 2020 Annual Conference of the Association for Computational Linguistics (ACL) 2020.☆29Updated last year