mr-nineteen Goto Github PK

adanet

Fast and flexible AutoML with learning guarantees.

ai_tutorial

精华机器学习，NLP，图像识别， 深度学习等人工智能领域学习资料，搜索，推荐，广告系统架构及算法技术资料整理

aigc_llm_engineering

alpaca-rlhf

Finetuning LLaMA with RLHF (Reinforcement Learning with Human Feedback) based on DeepSpeed Chat

annotated-transformer

An annotated implementation of the Transformer paper.

ant-learn-pandas

pandas学习课程代码仓库

bagua

Bagua is a flexible and performant distributed training algorithm development framework.

baichuan-dynamic-ntk-alibi

百川Dynamic NTK-ALiBi的代码实现：无需微调即可推理更长文本

bazel-cpp-demo

A simple demo of Bazel with C++

bazelisk

A user-friendly launcher for Bazel.

belle

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

bert-as-service

Mapping a variable-length sentence to a fixed-length vector using BERT model

billa

BiLLa: A Bilingual LLaMA with Enhanced Reasoning Ability

buildtools

A bazel BUILD file formatter and editor

chatglm2-6b

ChatGLM2-6B: An Open Bilingual Chat LLM | 开源双语对话语言模型

chinese-llama-alpaca

中文LLaMA&Alpaca大语言模型+本地CPU/GPU部署 (Chinese LLaMA & Alpaca LLMs)

chinese-llama2

Repo for adapting Meta LlaMA2 in Chinese! META最新发布的LlaMA2的汉化版！ （完全开源可商用）

community

community-1

Stores documents used by the TensorFlow developer community

controlnet_stable_tensorrt

stable diffusion, controlnet, tensorrt, accelerate

convert-pytorch-onnx-tensorrt

Converting weights of Pytorch models to ONNX & TensorRT engines

cpp_book

cuda-optimization-guide

Xiao's CUDA Optimization Guide [Active Adding New Contents]

cuda-programming

Sample codes for my CUDA programming book

cuda-programming-guide-in-chinese

This is a Chinese translation of the CUDA programming guide

cuda-samples

Samples for CUDA Developers which demonstrates features in CUDA Toolkit

cudalibrarysamples

CUDA Library Samples

custom-op

Guide for building custom op for TensorFlow

deep-learning-models

Keras code and weights files for popular deep learning models.

deeplearningexamples

State-of-the-Art Deep Learning scripts organized by models - easy to train and deploy with reproducible accuracy and performance on enterprise-grade infrastructure.