Provide with pre-build flash-attention 2 and 3 package wheels on Linux and Windows using GitHub Actions

Kernels, of the mega variety :)

Inference Llama 2 in one file of pure C

This is a collection of research papers for Self-Correcting Large Language Models with Automated Feedback.

Streamlined interface for generating images with AI in Krita. Inpaint and outpaint with optional text prompt, no tweaking required.

[ICLR 2025] Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing. Your efficient and high-quality synthetic data generation pipeline!

总结Prompt&LLM论文，开源数据&模型，AIGC应用

Convert HTML to Markdown

💩State-of-the-art shitcode principles your project should follow to call it a proper shitcode

面向开发者的 LLM 入门教程，吴恩达大模型系列课程中文版

A curation of awesome tools, documents and projects about LLM Security.

Reading list of hallucination in LLMs. Check out our new survey paper: "Siren’s Song in the AI Ocean: A Survey on Hallucination in Large Language Models"

Build your own Riscv Emulator in Rust.

RISC-V SoC designed by students in UCAS

Recent Advances in Vision and Language PreTrained Models (VL-PTMs)

Anime Girls Holding Programming Books

2018/2019/校招/春招/秋招/自然语言处理(NLP)/深度学习(Deep Learning)/机器学习(Machine Learning)/C/C++/Python/面试笔记，此外，还包括创建者看到的所有机器学习/深度学习面经中的问题。 除了其中 DL/ML 相关的，其他与算法岗相关的计算机知识也会记录。 但是不会包括如前端/测试/JAVA/Android等岗位中有关的问题。

该仓库主要记录 NLP 算法工程师相关的面试题

深度学习500问，以问答形式对常用的概率知识、线性代数、机器学习、深度学习、计算机视觉等热点问题进行阐述，以帮助自己及有需要的读者。 全书分为18个章节，50余万字。由于水平有限，书中不妥之处恳请广大读者批评指正。 未完待续............ 如有意合作，联系scutjy2015@163.com 版权所有，违权必究 Tan 2018.06

Awesome Neural Adaptation in Natural Language Processing. A curated list. https://arxiv.org/abs/2006.00632

Text2SQL 语义解析数据集、解决方案、paper资源整合项目

Enabling the Windows Subsystem for Linux to include support for Wayland and X server related scenarios

The entmax mapping and its loss, a family of sparse softmax alternatives.

A syntax-highlighting pager for git, diff, grep, rg --json, and blame output

Arknights Auto Helper based on ADB and Python | 基于python的明日方舟护肝助手

fastHan是基于fastNLP与pytorch实现的中文自然语言处理工具，像spacy一样调用方便。

DEPRECATED - Let's make a SQL parser so we can provide a familiar interface to non-sql datastores!

Lark is a parsing toolkit for Python, built with a focus on ergonomics, performance and modularity.

The Resources for "Natural Language to Logical Form" ; "自然语言转逻辑形式"研究资料收集。

北京航空航天大学大数据高精尖中心自然语言处理研究团队开展了智能问答的研究与应用总结。包括基于知识图谱的问答（KBQA），基于文本的问答系统（TextQA），基于表格的问答系统（TableQA）、基于视觉的问答系统（VisualQA）和机器阅读理解（MRC）等，每类任务分别对学术界和工业界进行了相关总结。