Hanlard

Electra_CRF_NER

We start a company-name recognition task with a small scale and low quality training data, then using skills to enhanced model training speed and predicting performance with least artificial participation. The methods we use involve lite pre-training models such as Albert-small or Electra-small with financial corpus, knowledge of distillation and multi-stage learning. The result is that we improve the recall rate of company names recognition task from 0.73 to 0.92 and get 4 times as fast as BERT-Bilstm-CRF model.

PCL-Tongyan

通言模型是在M2M-100模型结构上进行改进的多语种机器翻译模型，通过参数复用和增量式训练，将模型参数从1.2B提升至13.2B，在一带一路多个小语种的翻译上大幅提升。

chinese_gpt

100G中文清洗后语料训练的gpt模型

DPO_based_on_TRLX

Reproducing the code of "Direct Preference Optimization: Your Language Model is Secretly a Reward Model"

CLUE

中文语言理解基准测评 Chinese Language Understanding Evaluation Benchmark: datasets, baselines, pre-trained models, corpus and leaderboard

CPPO

ICLR 2024 CPPO: Continual Learning for Reinforcement Learning with Human Feedback

albert_pytorch

A Lite Bert For Self-Supervised Learning Language Representations

albert_zh

A LITE BERT FOR SELF-SUPERVISED LEARNING OF LANGUAGE REPRESENTATIONS, 海量中文预训练ALBERT模型

attention-visualization

bert_distill

BERT distillation（基于BERT的蒸馏实验 ）

chatgpt-on-wechat

Chinese-Text-Classification-Pytorch

中文文本分类，TextCNN，TextRNN，FastText，TextRCNN，BiLSTM_Attention，DPCNN，Transformer，基于pytorch，开箱即用。

Chinese-Word-Vectors

100+ Chinese Word Vectors 上百种预训练中文词向量

CLLE

Code and Datasets of " CLLE: A Benchmark for Continual Language Learning Evaluation in Multilingual Machine Translation"

DeepCTR

Easy-to-use,Modular and Extendible package of deep-learning based CTR models.

DeepFM_with_PyTorch

A PyTorch implementation of DeepFM for CTR prediction problem.

flamingo-pytorch

Implementation of 🦩 Flamingo, state-of-the-art few-shot visual question answering attention net out of Deepmind, in Pytorch

football

Check out the new game server:

forecasting

Time Series Forecasting Best Practices & Examples

Kashgari

Kashgari is a production-level NLP Transfer learning framework built on top of tf.keras for text-labeling and text-classification, includes Word2Vec, BERT, and GPT2 Language Embedding.

KIP_frame

code for paper KIP-Framework

knowledge_graph_attention_network

KGAT: Knowledge Graph Attention Network for Recommendation, KDD2019

M2M-by-fastmoe

We modify the M2M-100(Facebook) MLP layers by fastmoe

nlp-recipes

Natural Language Processing Best Practices & Examples

offline-alignment-methods-based-on-trlx

Performer_mindspore

使用Mindspore复现谷歌的Performer模型

pytorch_geometric

Geometric Deep Learning Extension Library for PyTorch

recommenders

Best Practices on Recommendation Systems

reinforcement-learning

Implementation of Reinforcement Learning Algorithms. Python, OpenAI Gym, Tensorflow. Exercises and Solutions to accompany Sutton's Book and David Silver's course.

Stock-Prediction-Models

Gathers machine learning and deep learning models for Stock forecasting including trading bots and simulations