Atma's starred repositories
OKD-Reading-List
Papers for Open Knowledge Discovery
paper-reading
深度学习经典、新论文逐段精读
haystack
:mag: LLM orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.
HowToTrainYourMAMLPytorch
The original code for the paper "How to train your MAML" along with a replication of the original "Model Agnostic Meta Learning" (MAML) paper in Pytorch.
Meta-tuning
EMNLP 2021 Adapting Language Models for Zero-shot Learning by Meta-tuning on Dataset and Prompt Collections
templateNER
Source code for template-based NER
GNNLearner
Solution of KDD cup 2021
Megatron-LM
Ongoing research training transformer models at scale
fairseq-rl
Modified version of fairseq, including new implementations for criterions using reinforcement learning methods.
Bert-Multi-Label-Text-Classification
This repo contains a PyTorch implementation of a pretrained BERT model for multi-label text classification.
NeuralNLP-NeuralClassifier
An Open-source Neural Hierarchical Multi-label Text Classification Toolkit
transformers-tutorials
Github repo with tutorials to fine tune transformers for diff NLP tasks
meta-dataset
A dataset of datasets for learning to learn from few examples