Train large COMET (T5-3B/GPT2-XL) with small memory (on 11GB memory GPUs like 1080/2080) using DeepSpeed.
☆14Jan 23, 2022Updated 4 years ago
Alternatives and similar repositories for comet-deepspeed
Users that are interested in comet-deepspeed are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Official code repository for the main conference paper in EMNLP 2022: SubeventWriter: Iterative Sub-event Sequence Generation with Cohere…☆11Oct 16, 2022Updated 3 years ago
- Code for EMNLP 2020 paper: Analogous Process Structure Induction for Sub-event Sequence Prediction☆11Oct 19, 2020Updated 5 years ago
- Official code repository for Findings of EMNLP 2022 paper: PseudoReasoner: Leveraging Pseudo Labels for Commonsense Knowledge Base Popula…☆11Oct 18, 2022Updated 3 years ago
- This is the code repo for Findings of EMNLP2022 paper: MICO: a multi-alternative contrastive learning framework for commonsense knowledg…☆10Nov 29, 2022Updated 3 years ago
- Source code for the paper 'Complex Hyperbolic Knowledge Graph Embeddings with Fast Fourier Transform'.☆12Nov 9, 2022Updated 3 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- SP-10K is a large-scale human-annotated selectional preference set. Five selectional preference relations are included.☆12May 6, 2020Updated 6 years ago
- Code and data for the paper Acquiring and Modelling Abstract Commonsense Knowledge via Conceptualization☆23Nov 21, 2022Updated 3 years ago
- WinoWhy provides human-annotated reasons for answering WSC questions.☆18May 13, 2020Updated 6 years ago
- Official code repository for the paper: AbsPyramid: Benchmarking the Abstration Ability of Language Models with a Unified Entailment Grap…☆13Oct 30, 2024Updated last year
- Codes for the EMNLP2021 paper: Benchmarking Commonsense Knowledge Base Population (https://aclanthology.org/2021.emnlp-main.705.pdf). An …☆26Feb 14, 2024Updated 2 years ago
- Code for the ACL2023 paper: CAT: A Contextualized Conceptualization and Instantiation Framework for Commonsense Reasoning (https://aclant…☆11May 9, 2023Updated 3 years ago
- Source Code for ICML 2022 paper "Boosting Graph Structure Learning with Dummy Nodes"☆19Apr 24, 2023Updated 3 years ago
- Code Repo for "Differentiable Open-Ended Commonsense Reasoning" (NAACL 2021)☆32Jun 30, 2023Updated 3 years ago
- A web application for playing 20 Questions to crowdsource common sense. 🤖☆17Sep 29, 2022Updated 3 years ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- [Findings of EMNLP22] From Mimicking to Integrating: Knowledge Integration for Pre-Trained Language Models☆19Mar 16, 2023Updated 3 years ago
- Extracting Cultural Commonsense Knowledge at Scale (WWW 2023)☆11Feb 15, 2024Updated 2 years ago
- ☆14Aug 10, 2023Updated 2 years ago
- Official code repository for the main conference paper in ACL2023: COLA: Contextualized Commonsense Causality Reasoning from the Causal I…☆34May 12, 2023Updated 3 years ago
- Dataset & Code for Com2Sense Benchmark☆13Sep 8, 2021Updated 4 years ago
- IJCNN 2021: Inductive Learning on Commonsense Knowledge Graph Completion (Depreciated)☆15Nov 13, 2023Updated 2 years ago
- Benchmark for Answering Existential First Order Queries with Single Free Variable (NeurIPS dataset and benchmark 2021)☆20May 3, 2023Updated 3 years ago
- The code of the paper "DivScene: Benchmarking LVLMs for Object Navigation with Diverse Scenes and Objects"☆19May 2, 2025Updated last year
- Data and Code for Paper "Reflect Not Reflex: Inference-Based Common Ground Improves Dialogue Response Quality" (EMNLP 2022)☆11Nov 28, 2022Updated 3 years ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- [EMNLP 2021] Dataset and PyTorch Code for ExplaGraphs: An Explanation Graph Generation Task for Structured Commonsense Reasoning☆14Nov 5, 2022Updated 3 years ago
- Experimenting with langchain, FAISS, OpenAI Embeddings, and GPT-3☆26Feb 10, 2023Updated 3 years ago
- Official implementaion of EMNLP 2022 paper "Generate, Discriminate, and Contrast: A Semi-Supervised Sentence Representation Learning Fram…☆23Nov 27, 2022Updated 3 years ago
- Longformer Encoder Decoder model for the legal domain, trained for long document abstractive summarization task.☆10Feb 26, 2021Updated 5 years ago
- K-PLUG: Knowledge-injected Pre-trained Language Model for Natural Language Understanding and Generation in E-Commerce (Findings of EMNLP …☆31Jan 6, 2023Updated 3 years ago
- [ACL'24 Oral] Analysing The Impact of Sequence Composition on Language Model Pre-Training☆23Aug 18, 2024Updated last year
- [ACL'25 (Findings)] Explorer: Scaling Exploration-driven Web Trajectory Synthesis for Multimodal Web Agents☆29Feb 17, 2026Updated 4 months ago
- ☆13Jun 14, 2026Updated 2 weeks ago
- A Python Commonsense Knowledge Inference Toolkit☆63Dec 13, 2023Updated 2 years ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- ☆74Apr 4, 2024Updated 2 years ago
- ☆10Nov 28, 2024Updated last year
- ☆10Nov 29, 2024Updated last year
- TransOMCS is a commonsense knowledge resource transferred from ASER. It is in the format of OMCS but two orders of magnitude larger.☆70Aug 25, 2020Updated 5 years ago
- Code for the paper "Knowledge-driven Data Construction for Zero-shot Evaluation in Commonsense Question Answering" (AAAI 2021)☆30Feb 19, 2021Updated 5 years ago
- EMNLP 2021 - Frustratingly Simple Pretraining Alternatives to Masked Language Modeling☆34Nov 21, 2021Updated 4 years ago
- ☆52Oct 24, 2023Updated 2 years ago