mit10000 Goto Github PK

1667

a_journey_into_math_of_ml

汉语自然语言处理视频教程-开源学习资料

ai_and_memory_wall

AI and Memory Wall blog post

alpaca-lora

Instruct-tune LLaMA on consumer hardware

awesome-llm-inference

📖A curated list of Awesome LLM Inference Paper with codes, TensorRT-LLM, vLLM, streaming-llm, AWQ, SmoothQuant, WINT8/4, Continuous Batching, FlashAttention, PagedAttention etc.

awesome-production-machine-learning

A curated list of awesome open source libraries to deploy, monitor, version and scale your machine learning

awesome-real-time-ai

This is a list of awesome edgeAI inference related papers.

backtesting.py

:mag_right: :chart_with_upwards_trend: :snake: :moneybag: Backtest trading strategies in Python.

baichuan-7b

A large-scale 7B pretraining language model developed by BaiChuan-Inc.

bert4torch

An elegent pytorch implement of transformers

bilingual_book_maker

Make bilingual epub books Using AI translate

bladedisc

BladeDISC is an end-to-end DynamIc Shape Compiler project for machine learning workloads.

blue-porcelain

book-doc

books and docments

calculon

calm

C(UDA) accelerated language model inference

chaotic-transformer-tutorials

chatglm-6b

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

chatglm2-6b

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

chinese-alpaca-lora

骆驼:A Chinese finetuned instruction LLaMA. Developed by 陈启源 @ 华中师范大学 & 李鲁鲁 @ 商汤科技 & 冷子昂 @ 商汤科技

colossalai

Making large AI models cheaper, faster and more accessible

computer-science-textbooks

Collect some CS textbooks for learning.

cuda-animations

CUDA GPU memory access patterns animated

cuda_learning

learning how CUDA works

cvpr2022-dagan

Official code for CVPR2022 paper: Depth-Aware Generative Adversarial Network for Talking Head Video Generation

dataflow_optimizer

A general framework for optimizing DNN dataflow on systolic array

deeplearningsystem

Deep Learning System core principles introduction.

deepwalk

DeepWalk - Deep Learning for Graphs

dejavu

dinet

The source code of "DINet: deformation inpainting network for realistic face visually dubbing on high resolution video."