TeleMem is a high-performance drop-in replacement for Mem0, featuring semantic deduplication, long-term dialogue memory, and multimodal video reasoning.

🧠「大模型」2小时完全从0训练64M的小参数LLM！Train a 64M-parameter LLM from scratch in just 2h!

😝 TensorFlowTTS: Real-Time State-of-the-art Speech Synthesis for Tensorflow 2 (supported including English, French, Korean, Chinese, German and Easy to adapt for other languages)

Inference code for Llama models

BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）

双塔模型的优化实践 - tf2.x

[KDD 2021] Model-Agnostic Counterfactual Reasoning for Eliminating Popularity Bias in Recommender System

基于tf 1.14 estimator实现推荐排序模型

多标签文本分类

推荐系统从入门到实战

Open source annotation tool for machine learning practitioners.

Tensorflow2.0 🍎🍊 is delicious, just eat it! 😋😋

该仓库主要记录 NLP 算法工程师相关的顶会论文研读笔记

Chinese Named Entity Recognition with IDCNN/biLSTM+CRF, and Relation Extraction with biGRU+2ATT 中文实体识别与关系提取

Tensorflow solution of NER task Using BiLSTM-CRF model with Google BERT Fine-tuning And private Server services

基于金融-司法领域(兼有闲聊性质)的聊天机器人，其中的主要模块有信息抽取、NLU、NLG、知识图谱等，并且利用Django整合了前端展示,目前已经封装了nlp和kg的restful接口

MFC-seetaFace人脸识别程序（需要自行添加３个seetaface的模型）

ctr、cvr预估

keras implement of transformers for humans

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

推荐、广告工业界经典以及最前沿的论文、资料集合/ Must-read Papers on Recommendation System and CTR Prediction

DIEN-pipline implement

An implementation of a deep learning recommendation model (DLRM)

Language Understanding Evaluation benchmark for Chinese: datasets, baselines, pre-trained models,corpus and leaderboard

Pre-Trained Chinese XLNet（中文XLNet预训练模型）

Accelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, DeepSeek, Mixtral, Gemma, Phi, MiniCPM, Qwen-VL, MiniCPM-V, etc.) on Intel XPU (e.g., local PC with iGPU and NPU, discr…

Step-by-step Deep Leaning Tutorials on Apache Spark using BigDL

Deep Learning Book Chinese Translation