ruilinWho

wandb

The AI developer platform. Use Weights & Biases to train and fine-tune models, and manage models from experimentation to production.

codes

magicoder

[ICML'24] Magicoder: Empowering Code Generation with OSS-Instruct

SPIN

The official implementation of Self-Play Fine-Tuning (SPIN)

DataDreamer

DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models.   🤖💤

Awesome-LLM-Synthetic-Data

A reading list on LLM based Synthetic Data Generation 🔥

lotus

LOTUS: The semantic query engine - process data with LMs over tables of unstructured and structured data

TAG-Bench

TAG: Table-Augmented Generation

Knowledge-to-SQL

[ACL2024 Findings] Knowledge-to-SQL: Enhancing SQL Generation with Data Expert LLM

LLM4DB

NL2SQL_Handbook

This is a continuously updated handbook for readers to easily track the latest NL2SQL techniques in the literature and provide practical guidance for researchers and practitioners.

Sense

[ACL24] Official repo for "Synthesizing Text-to-SQL Data from Weak and Strong LLMs"

Awesome-LLM-Tabular

Awesome-LLM-Tabular: a curated list of Large Language Model applied to Tabular Data

CHESS

Contextual Harnessing for Efficient SQL Synthesis

E5-Hierarchical-Table-Analysis

The official code for NAACL 2024 paper: $E^5$: Zero-shot Hierarchical Table Analysis using Augmented LLMs via Explain, Extract, Execute, Exhibit and Extrapolate

learning_research

本人的科研经验

DeepSeek-Coder-V2

DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence

LLM101n

LLM101n: Let's build a Storyteller

repo-level-codegen-papers

Repo-Level Code generation papers

Hack

A typeface designed for source code

TA-SQL

sciencebenchmark_dataset

granite-code-models

Granite Code Models: A Family of Open Foundation Models for Code Intelligence

jsterm

JavaScript terminal using a JSON pseudo-filesystem.

DS-1000

[ICML 2023] Data and code release for the paper "DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation".

sqlglot

Python SQL Parser and Transpiler

LLMs_interview_notes

该仓库主要记录 大模型（LLMs） 算法工程师相关的面试题

text2sql-schema-filter

The source code for the schema filter (question + schema only)

codes

The source code of CodeS (SIGMOD 2024).

statistical-learning-method-solutions-manual

统计学习方法习题解答，在线阅读地址：https://datawhalechina.github.io/statistical-learning-method-solutions-manual