stas00 / porting
Helper scripts and notes that were used while porting various nlp models
☆44Updated 2 years ago
Related projects ⓘ
Alternatives and complementary repositories for porting
- Repo for training MLMs, CLMs, or T5-type models on the OLM pretraining data, but it should work with any hugging face text dataset.☆92Updated last year
- Official repository with code and data accompanying the NAACL 2021 paper "Hurdles to Progress in Long-form Question Answering" (https://a…☆46Updated 2 years ago
- ☆21Updated 3 years ago
- Training T5 to perform numerical reasoning.☆23Updated 3 years ago
- ☆73Updated 3 years ago
- Implementation of Marge, Pre-training via Paraphrasing, in Pytorch☆75Updated 3 years ago
- Google's BigBird (Jax/Flax & PyTorch) @ 🤗Transformers☆47Updated last year
- ☆95Updated last year
- SWIM-IR is a Synthetic Wikipedia-based Multilingual Information Retrieval training set with 28 million query-passage pairs spanning 33 la…☆44Updated last year
- Exploring Few-Shot Adaptation of Language Models with Tables☆23Updated 2 years ago
- Code and pre-trained models for "ReasonBert: Pre-trained to Reason with Distant Supervision", EMNLP'2021☆29Updated last year
- Tutorial to pretrain & fine-tune a 🤗 Flax T5 model on a TPUv3-8 with GCP☆58Updated 2 years ago
- LM Pretraining with PyTorch/TPU☆132Updated 5 years ago
- Implementation of the paper 'Sentence Bottleneck Autoencoders from Transformer Language Models'☆17Updated 2 years ago
- ☆55Updated last year
- Official code and model checkpoints for our EMNLP 2022 paper "RankGen - Improving Text Generation with Large Ranking Models" (https://arx…☆136Updated last year
- Shared code for training sentence embeddings with Flax / JAX☆27Updated 3 years ago
- A diff tool for language models☆42Updated 10 months ago
- ☆30Updated 3 years ago
- Generate BERT vocabularies and pretraining examples from Wikipedias☆18Updated 4 years ago
- On the Stability of Fine-tuning BERT: Misconceptions, Explanations, and Strong Baselines☆132Updated last year
- A 🤗-style implementation of BERT using lambda layers instead of self-attention☆70Updated 4 years ago
- Open source library for few shot NLP☆77Updated last year
- ☆67Updated 2 years ago
- No Parameter Left Behind: How Distillation and Model Size Affect Zero-Shot Retrieval☆27Updated 2 years ago
- M2D2: A Massively Multi-domain Language Modeling Dataset (EMNLP 2022) by Machel Reid, Victor Zhong, Suchin Gururangan, Luke Zettlemoyer☆55Updated 2 years ago
- ☆67Updated 3 years ago
- Apps built using Inspired Cognition's Critique.☆58Updated last year
- Mr. TyDi is a multi-lingual benchmark dataset built on TyDi, covering eleven typologically diverse languages.☆72Updated 2 years ago