stas00 / porting
Helper scripts and notes that were used while porting various nlp models
β45Updated 3 years ago
Alternatives and similar repositories for porting:
Users that are interested in porting are comparing it to the libraries listed below
- Repo for training MLMs, CLMs, or T5-type models on the OLM pretraining data, but it should work with any hugging face text dataset.β93Updated 2 years ago
- Tutorial to pretrain & fine-tune a π€ Flax T5 model on a TPUv3-8 with GCPβ58Updated 2 years ago
- β97Updated 2 years ago
- Official repository with code and data accompanying the NAACL 2021 paper "Hurdles to Progress in Long-form Question Answering" (https://aβ¦β46Updated 2 years ago
- Implementation of Marge, Pre-training via Paraphrasing, in Pytorchβ75Updated 4 years ago
- β75Updated 3 years ago
- A BART version of an open-domain QA model in a closed-book setupβ119Updated 4 years ago
- β38Updated 2 years ago
- A diff tool for language modelsβ42Updated last year
- Factorization of the neural parameter space for zero-shot multi-lingual and multi-task transferβ39Updated 4 years ago
- Generate BERT vocabularies and pretraining examples from Wikipediasβ18Updated 4 years ago
- Training T5 to perform numerical reasoning.β23Updated 3 years ago
- Research code for the paper "How Good is Your Tokenizer? On the Monolingual Performance of Multilingual Language Models"β26Updated 3 years ago
- β46Updated 2 years ago
- β21Updated 3 years ago
- Official code and model checkpoints for our EMNLP 2022 paper "RankGen - Improving Text Generation with Large Ranking Models" (https://arxβ¦β136Updated last year
- Implementation of the paper 'Sentence Bottleneck Autoencoders from Transformer Language Models'β17Updated 3 years ago
- Code and dataset "ZEST" from "Learning from task descriptions", Weller et al, EMNLP 2020β17Updated 4 years ago
- β97Updated 2 years ago
- β47Updated 4 years ago
- On the Stability of Fine-tuning BERT: Misconceptions, Explanations, and Strong Baselinesβ135Updated last year
- Few-shot NLP benchmark for unified, rigorous evalβ91Updated 2 years ago
- Official repository for our EACL 2023 paper "LongEval: Guidelines for Human Evaluation of Faithfulness in Long-form Summarization" (httpsβ¦β43Updated 7 months ago
- LM Pretraining with PyTorch/TPUβ134Updated 5 years ago
- Mr. TyDi is a multi-lingual benchmark dataset built on TyDi, covering eleven typologically diverse languages.β74Updated 3 years ago
- Code and pre-trained models for "ReasonBert: Pre-trained to Reason with Distant Supervision", EMNLP'2021β29Updated 2 years ago
- No Parameter Left Behind: How Distillation and Model Size Affect Zero-Shot Retrievalβ28Updated 2 years ago
- β54Updated 2 years ago
- Generative Retrieval Transformerβ28Updated last year
- EMNLP 2021 Tutorial: Multi-Domain Multilingual Question Answeringβ38Updated 3 years ago