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:
- [ACL 2022] Ditch the Gold Standard: Re-evaluating Conversational Question Answering☆45Updated 3 years ago
- This repository contains the code for "How many data points is a prompt worth?"☆48Updated 4 years ago
- The code of Paper "Locate Then Ask: Interpretable Stepwise Reasoning for Multi-hop Question Answering".☆21Updated 2 years ago
- Code for embedding and retrieval research.☆16Updated last year
- Code repo for SIGIR 2021 paper "Few-Shot Conversational Dense Retrieval"☆41Updated 3 years ago
- Code and data for "Retrieval Enhanced Model for Commonsense Generation" (ACL-IJCNLP 2021).☆28Updated 3 years ago
- EMNLP'2022: BERTScore is Unfair: On Social Bias in Language Model-Based Metrics for Text Generation☆41Updated 2 years ago
- A Structured Span Selector (NAACL 2022). A structured span selector with a WCFG for span selection tasks (coreference resolution, semanti…☆21Updated 3 years ago
- TBC☆27Updated 2 years ago
- ☆58Updated 3 years ago
- Code and Data for NeurIPS2021 Paper "A Dataset for Answering Time-Sensitive Questions"☆72Updated 3 years ago
- [NeurIPS 2022] Generating Training Data with Language Models: Towards Zero-Shot Language Understanding☆67Updated 2 years ago
- We construct and introduce DIALFACT, a testing benchmark dataset crowd-annotated conversational claims, paired with pieces of evidence fr…☆41Updated 2 years ago
- ☆21Updated 2 years ago
- [EMNLP 2022] Code for our paper “ZeroGen: Efficient Zero-shot Learning via Dataset Generation”.☆48Updated 3 years ago
- WinoWhy provides human-annotated reasons for answering WSC questions.☆18Updated 5 years ago
- The official implemetation of "Evidentiality-guided Generation for Knowledge-Intensive NLP Tasks" (NAACL 2022).☆44Updated 2 years ago
- [EMNLP 2022] Code for our paper “ZeroGen: Efficient Zero-shot Learning via Dataset Generation”.☆16Updated 3 years ago
- ☆45Updated 3 years ago
- Technical Report: Is ChatGPT a Good NLG Evaluator? A Preliminary Study☆43Updated 2 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
- Resources for Retrieval Augmentation for Commonsense Reasoning: A Unified Approach. EMNLP 2022.☆22Updated 2 years ago
- Understanding Factual Errors in Summarization: Errors, Summarizers, Datasets, Error Detectors (ACL 2023)☆25Updated last year
- The project page for "SCITAB: A Challenging Benchmark for Compositional Reasoning and Claim Verification on Scientific Tables"☆22Updated last year
- Bootstrapped Unsupervised Sentence Representation Learning (ACL 2021)☆30Updated 3 years ago
- [EMNLP 2021] Dataset and PyTorch Code for ExplaGraphs: An Explanation Graph Generation Task for Structured Commonsense Reasoning☆12Updated 2 years ago
- Code for the paper Code for the paper InstructDial: Improving Zero and Few-shot Generalization in Dialogue through Instruction Tuning☆100Updated 2 years ago
- ☆117Updated 3 years ago
- The code implementation of the EMNLP2022 paper: DisCup: Discriminator Cooperative Unlikelihood Prompt-tuning for Controllable Text Gene…☆26Updated last year
- Pytorch implementation of paper "Efficient Nearest Neighbor Language Models" (EMNLP 2021)☆73Updated 3 years ago