bowendoctor1616 Goto Github PK

awesome-pretrained-chinese-nlp-models

Awesome Pretrained Chinese NLP Models，高质量中文预训练模型集合

bert-kpe

bert-utils

一行代码使用BERT生成句向量，BERT做文本分类、文本相似度计算

bert4rec

BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer

bert_seq2seq

pytorch实现 Bert 做seq2seq任务，使用unilm方案,现在也可以做自动摘要，文本分类，情感分析，NER，词性标注等任务,支持t5模型，支持GPT2进行文章续写。

bertopic

Leveraging BERT and c-TF-IDF to create easily interpretable topics.

chatglm-6b

ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型

chatglm-6b-qlora

使用peft库，对chatGLM-6B/chatGLM2-6B实现4bit的QLoRA高效微调，并做lora model和base model的merge及4bit的量化（quantize）。

chinesebert

co-action-network

Implementation of CAN: Revisiting Feature Co-Action for Click-Through RatePrediction

cpt

CPT: A Pre-Trained Unbalanced Transformer for Both Chinese Language Understanding and Generation

dbrl

Dataset Batch(offline) Reinforcement Learning for recommender system

deepct

DeepCT and HDCT uses BERT to generate novel, context-aware bag-of-words term weights for documents and queries.

deepctr

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

deeprec

DeepRec is a high-performance recommendation deep learning framework based on TensorFlow. It is hosted in incubation in LF AI & Data Foundation.

deepspeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

demos

一些 demo

detext

DeText: A Deep Neural Text Understanding Framework for Ranking and Classification Tasks

dfn

Deep Feedback Network for Recommendation

dgcn

The official implementation of "DGCN: Diversified Recommendation with Graph Convolutional Networks" (WWW '21)

dkn

A tensorflow implementation of DKN (Deep Knowledge-aware Network for News Recommendation)

dmr

Deep Match to Rank Model for Personalized Click-Through Rate Prediction

drl-rec

Deep reinforcement learning for recommendation system

essaykiller_v2

基于开源GPT2.0的初代创作型人工智能 | 可扩展、可进化

fast-map-dpp

Fast Greedy MAP Inference for DPP

fengshenbang-lm

Fengshenbang-LM(封神榜大模型)是IDEA研究院认知计算与自然语言研究中心主导的大模型开源体系，成为中文AIGC和认知智能的基础设施。

google-research

Google Research

grpc

The C based gRPC (C++, Python, Ruby, Objective-C, PHP, C#)

image-composition-assessment-dataset-cadb

[BMVC2021] The first image composition assessment dataset. Used in the paper "Image Composition Assessment with Saliency-augmented Multi-pattern Pooling". Useful for image composition assessment, image aesthetic assesment, etc.

informer-tensorflow