qikahh

antlr4

ANTLR (ANother Tool for Language Recognition) is a powerful parser generator for reading, processing, executing, or translating structured text or binary files.

ast-probe

Code and data of the paper https://arxiv.org/abs/2206.11719

awesome-active-learning

主动学习 (Active Learning) 综合知识库

Beijing_Daxuexi_Simple

北京 青年大学习 使用Github Actions自动完成

BIG-bench

多种任务衡量LLM推断和生成能力

CG-RL

Code for "Exploring Dynamic Selection of Branch Expansion Orders for Code Generation"

ChatGLM-6B

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

CoCoBench

CodeRanker

Fault-aware neural code rankers

CodeRL

This is the official code for the paper CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning.

ColossalAI

AI模型的简化版复刻

DAMO-ConvAI

DAMO-ConvAI: The official repository which contains the codebase for Alibaba DAMO Conversational AI.

Easy-Transformer

机械可解释性分析GPT如何预测间接宾语

EasyKV

Easy control for Key-Value Constrained Generative LLM Inference(https://arxiv.org/abs/2402.06262)

faiss

快速检索和聚类库

jedi

Awesome autocompletion, static analysis and refactoring library for python

lark

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

learned_optimization

全自动调参的优化器，基于MLP和LSTM

LesPapiers

SEKE 组会分享论文记录

ml4se

与软件工程机器学习相关的论文

NewEraAI-Papers

The repository provides links to collections of influential and interesting research papers from top AI conferences, with open-source code to promote reproducibility and provide detailed implementation insights beyond the scope of the article. Stay up to date with the latest advances in AI research!

parallelformers

部署模型并行化 仅用于推理

python-graphs

静态分析python图

repo_level_prompt_generation

se-project

Team project for software engineering course.

skill-map

程序员技能图谱

text-to-text-transfer-transformer

Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"

Transfer-Learning-Library

Transfer Learning Library for Domain Adaptation, Task Adaptation, and Domain Generalization

tuning_playbook

超参调试指南

WizardLM

LLMs build upon Evol Insturct: WizardLM, WizardCoder, WizardMath