JosselinSomervilleRoberts / BERT-Multitask-learning
Multitask-learning of a BERT backbone. Allows to easily train a BERT model with state-of-the-art method such as PCGrad, Gradient Vaccine, PALs, Scheduling, Class imbalance handling and many optimizations
☆18Updated last year
Alternatives and similar repositories for BERT-Multitask-learning:
Users that are interested in BERT-Multitask-learning are comparing it to the libraries listed below
- Fine-tuning LLM with LoRA (Low-Rank Adaptation) from scratch (Oct 2023)☆17Updated last year
- In this implementation, using the Flan T5 large language model, we performed the Text Classification task on the IMDB dataset and obtaine…☆21Updated last year
- A simple recipe for training and inferencing Transformer architecture for Multi-Task Learning on custom datasets. You can find two approa…☆95Updated 2 years ago
- ☆61Updated 2 years ago
- Tool for converting LLMs from uni-directional to bi-directional by removing causal mask for tasks like classification and sentence embedd…☆57Updated 2 months ago
- This repository contains a custom implementation of the BERT model, fine-tuned for specific tasks, along with an implementation of Low Ra…☆69Updated last year
- [NeurIPS 2023 Main Track] This is the repository for the paper titled "Don’t Stop Pretraining? Make Prompt-based Fine-tuning Powerful Lea…☆73Updated last year
- ☆44Updated 2 years ago
- ☆78Updated 2 years ago
- This is a simple implementation of how to leverage a Language Model for a prompt-based learning model☆44Updated 3 years ago
- ☆49Updated 2 years ago
- ☆23Updated 7 months ago
- [Neurips2023] Source code for Lift Yourself Up: Retrieval-augmented Text Generation with Self Memory☆58Updated last year
- Code for ECIR 2022 paper Local Citation Recommendation with Hierarchical-Attention Text Encoder and SciBERT-based Reranking☆25Updated 7 months ago
- Pytorch implementation of “Recursive Non-Autoregressive Graph-to-Graph Transformer for Dependency Parsing with Iterative Refinement”☆62Updated 3 years ago
- Benchmarking various Deep Learning models such as BERT, ALBERT, BiLSTMs on the task of sentence entailment using two datasets - MultiNLI …☆28Updated 4 years ago
- Prompting Large Language Models to Generate Dense and Sparse Representations for Zero-Shot Document Retrieval☆41Updated 4 months ago
- ConTextual Mask Auto-Encoder for Dense Passage Retrieval☆35Updated 3 months ago
- A extension of Transformers library to include T5ForSequenceClassification class.☆38Updated last year
- Timeline Summarization based on Event Graph Compression via Time-Aware Optimal Transport☆15Updated 3 years ago
- Code and Resources for the paper, "Better to Ask in English: Cross-Lingual Evaluation of Large Language Models for Healthcare Queries"☆15Updated 11 months ago
- ☆18Updated 3 years ago
- A Simple but Powerful SOTA NER Model | Official Code For Label Supervised LLaMA Finetuning☆153Updated 11 months ago
- Define Transformers, T5 model and RoBERTa Encoder decoder model for product names generation☆48Updated 3 years ago
- ☆35Updated last year
- Code and Data for the ACL 2022 paper "Rethinking Self-Supervision Objectives for Generalizable Coherence Modeling"☆11Updated 2 years ago
- Collection of scripts to pretrain T5 in unsupervised text, using PyTorch Lightning. CORD-19 pretraining provided as example.☆31Updated 3 years ago
- Data and code for our paper "Exploring and Predicting Transferability across NLP Tasks", to appear at EMNLP 2020.☆49Updated 3 years ago
- ALIGNIE: Few-Shot Fine-Grained Entity Typing with Automatic Label Interpretation and Instance Generation☆20Updated 2 years ago
- Implementation of ECIR 2022 Paper: How Can Graph Neural Networks Help Document Retrieval: A Case Study on CORD19 with Concept Map Generat…☆15Updated 2 years ago