microsoft / Lightweight-Low-Resource-NMT
Official code for "Too Brittle To Touch: Comparing the Stability of Quantization and Distillation Towards Developing Lightweight Low-Resource MT Models" to appear in WMT 2022.
☆17Updated last year
Alternatives and similar repositories for Lightweight-Low-Resource-NMT:
Users that are interested in Lightweight-Low-Resource-NMT are comparing it to the libraries listed below
- CyBERTron-LM is a project which collects some pre-trained Transformer-based models.☆12Updated last year
- We release the UICaption dataset. The dataset consists of UI images (icons and screenshots) and associated text descriptions. This datase…☆38Updated 2 years ago
- Fault-aware neural code rankers☆28Updated 2 years ago
- UNISUMM: Unified Few-shot Summarization with Multi-Task Pre-Training and Prefix-Tuning☆60Updated last year
- ☆84Updated last year
- DeFacto - Demonstrations and Feedback for improving factual consistency of text summarization☆29Updated 2 years ago
- [NeurIPS 2022] code for "K-LITE: Learning Transferable Visual Models with External Knowledge" https://arxiv.org/abs/2204.09222☆51Updated last year
- ☆17Updated last week
- ☆22Updated last year
- ☆206Updated last month
- ☆77Updated last year
- Pipeline for pulling and processing online language model pretraining data from the web☆177Updated last year
- Evaluation pipeline for the BabyLM Challenge 2023.☆75Updated last year
- This repo contains data and code for the paper "Reasoning over Public and Private Data in Retrieval-Based Systems."☆46Updated 8 months ago
- Building modular LMs with parameter-efficient fine-tuning.☆98Updated last week
- 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 he…☆31Updated last year
- A client library for LAION's effort to filter CommonCrawl with CLIP, building a large scale image-text dataset.☆33Updated 2 years ago
- Code used for the creation of OBELICS, an open, massive and curated collection of interleaved image-text web documents, containing 141M d…☆199Updated 7 months ago
- Training a model similar to OpenAI DALL-E with volunteers from all over the Internet using hivemind and dalle-pytorch (NeurIPS 2021 demo)☆26Updated last year
- ☆97Updated 2 years ago
- AutoMoE: Neural Architecture Search for Efficient Sparsely Activated Transformers☆44Updated 2 years ago
- An instruction-based benchmark for text improvements.☆141Updated 2 years ago
- ☆44Updated 4 months ago
- code for paper "Accessing higher dimensions for unsupervised word translation"☆21Updated last year
- ☆65Updated last year
- ☆89Updated 2 years ago
- Generating Captions via Perceiver-Resampler Cross-Attention Networks☆16Updated 2 years ago
- [WIP] A 🔥 interface for running code in the cloud☆86Updated 2 years ago
- Safety Score for Pre-Trained Language Models☆94Updated last year
- Repo for training MLMs, CLMs, or T5-type models on the OLM pretraining data, but it should work with any hugging face text dataset.☆93Updated 2 years ago