Beast code in Giters

frank-peng's starred repositories

LiveTalking

Real time interactive streaming digital human

Language:PythonApache-2.0390000

transformers_tasks

⭐️ NLP Algorithms with transformers lib. Supporting Text-Classification, Text-Generation, Information-Extraction, Text-Matching, RLHF, SFT etc.

Language:Jupyter Notebook215300

textgen

TextGen: Implementation of Text Generation models, include LLaMA, BLOOM, GPT2, BART, T5, SongNet and so on. 文本生成模型，实现了包括LLaMA，ChatGLM，BLOOM，GPT2，Seq2Seq，BART，T5，UDA等模型的训练和预测，开箱即用。

Language:PythonApache-2.093500

Awesome-Chinese-LLM

整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。

1599200

awesome-multimodal-ml

Reading list for research topics in multimodal machine learning

MIT609100

ScaleLLM

A high-performance inference system for large language models, designed for production environments.

Language:C++Apache-2.038800

MedicalGPT

MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型，实现了包括增量预训练(PT)、有监督微调(SFT)、RLHF、DPO、ORPO。

Language:PythonApache-2.0334800

SynapseML

Simple and Distributed Machine Learning

Language:ScalaMIT506800

mem0

The Memory layer for your AI apps

Language:PythonApache-2.02282900

llm.c

LLM training in simple, raw C/CUDA

Language:CudaMIT2441400

timesfm

TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.

Language:PythonApache-2.0378100

graphrag

A modular graph-based Retrieval-Augmented Generation (RAG) system

Language:PythonMIT1908000

DeepSpeedExamples

Example models using DeepSpeed

Language:PythonApache-2.0608400

mmf

A modular framework for vision & language multimodal research from Facebook AI Research (FAIR)

Language:PythonNOASSERTION550000

mmaction2

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

Language:PythonApache-2.0429600

mlx

MLX: An array framework for Apple silicon

Language:C++MIT1723700

Open-Sora

Open-Sora: Democratizing Efficient Video Production for All

Language:PythonApache-2.02224300

RecBole

A unified, comprehensive and efficient recommendation library

Language:PythonMIT344700

kungfu

Kungfu Trader

Language:C++Apache-2.0340100

DeepSpeed

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

Language:PythonApache-2.03546400

ML-NLP

此项目是机器学习(Machine Learning)、深度学习(Deep Learning)、NLP面试中常考到的知识点和代码实现，也是作为一个算法工程师必会的理论基础知识。

Language:Jupyter Notebook1606000

llm-cookbook

面向开发者的 LLM 入门教程，吴恩达大模型系列课程中文版

Language:Jupyter Notebook1191900

DirectML is a high-performance, hardware-accelerated DirectX 12 library for machine learning. DirectML provides GPU acceleration for common machine learning tasks across a broad range of supported hardware and drivers, including all DirectX 12-capable GPUs from vendors such as AMD, Intel, NVIDIA, and Qualcomm.

Language:C++MIT222800

freeCodeCamp

freeCodeCamp.org's open-source codebase and curriculum. Learn to code for free.

Language:TypeScriptBSD-3-Clause40552300

safe-rlhf

Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback

Language:PythonApache-2.0134500

generative-recommenders

Repository hosting code used to reproduce results in "Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations" (https://arxiv.org/abs/2402.17152).

Language:PythonApache-2.074400

cs-self-learning

计算机自学指南

Language:HTMLMIT5790700

FreeAskInternet

FreeAskInternet is a completely free, PRIVATE and LOCALLY running search aggregator & answer generate using MULTI LLMs, without GPU needed. The user can ask a question and the system will make a multi engine search and combine the search result to LLM and generate the answer based on search results. It's all FREE to use.

Language:PythonApache-2.0848900

onerec

在常规推荐系统算法和系统双优化的范式下，一线公司针对单个任务或单个业务的效果挖掘几乎达到极限。从2019年我们开始关注多种信息的萃取融合，提出了OneRec算法，希望通过平台或外部各种各样的信息来进行知识集成，打破数据孤岛，极大扩充推荐的“Extra World Knowledge”。已实践的算法包括行为数据，内容描述，社交信息，知识图谱等。在OneRec，每种信息和整体算法的集成是可插拔的，这样的话一方面方便大家在自己的平台数据下灵活组合各种信息，另一方面方便开源共建，大家可以在上边集成自己的各种算法。今天分享的都是之前在线上验证过效果的工作，相关代码和论文已经开源在：。欢迎大家开源共建。

Language:Python9700