tanmoyio / sahajBERT
β13Updated 3 years ago
Alternatives and similar repositories for sahajBERT:
Users that are interested in sahajBERT are comparing it to the libraries listed below
- This project shows how to derive the total number of training tokens from a large text dataset from π€ datasets with Apache Beam and Dataβ¦β24Updated 2 years ago
- This repository hosts the code to port NumPy model weights of BiT-ResNets to TensorFlow SavedModel format.β14Updated 3 years ago
- β38Updated 2 years ago
- Minimal implementation of Denoised Smoothing (https://arxiv.org/abs/2003.01908) in TensorFlow.β20Updated 3 years ago
- An attempt at the implementation of GLOM, Geoffrey Hinton's paper for emergent part-whole hierarchies from dataβ37Updated 3 years ago
- Shows how to do parameter ensembling using differential evolution.β10Updated 3 years ago
- Version control for software 2.0β64Updated 3 years ago
- Highly specialized crate to parse and use `google/sentencepiece` 's precompiled_charsmap in `tokenizers`β18Updated 2 years ago
- Memory-efficient transformer. Work in progress.β19Updated 2 years ago
- A client library for LAION's effort to filter CommonCrawl with CLIP, building a large scale image-text dataset.β32Updated last year
- Tutorial to pretrain & fine-tune a π€ Flax T5 model on a TPUv3-8 with GCPβ58Updated 2 years ago
- A GPT, made only of MLPs, in Jaxβ57Updated 3 years ago
- Training a model similar to OpenAI DALL-E with volunteers from all over the Internet using hivemind and dalle-pytorch (NeurIPS 2021 demo)β26Updated last year
- This repository contains example code to build models on TPUsβ30Updated last year
- Execute arbitrary SQL queries on π€ Datasetsβ32Updated last year
- Code for scaling Transformersβ26Updated 4 years ago
- A tutorial example for nbdevβ15Updated 2 years ago
- Simple tooling for marking deprecated functions or classes and re-routing to the new successors' instance.β51Updated 3 weeks ago
- Implementation of N-Grammer in Flaxβ16Updated 2 years ago
- HomebrewNLP in JAX flavour for maintable TPU-Trainingβ47Updated last year
- TPU support for the fastai libraryβ13Updated 3 years ago
- β13Updated 6 years ago
- URL downloader supporting checkpointing and continuous checksumming.β19Updated last year
- β30Updated 4 years ago
- PyTorch implementation of GLOMβ21Updated 2 years ago
- β15Updated 2 years ago
- A case study of efficient training of large language models using commodity hardware.β68Updated 2 years ago
- Standalone pre-training recipe with JAX+Flaxβ31Updated last year
- β16Updated last year
- Contains Colab Notebooks show cool use-cases of different GCP ML APIs.β10Updated 4 years ago