🏆 #2,638 overall#593 of 1,378 in Language Models

RUCKBReasoning /OmniSQL

[VLDB' 25] Synthesizing High-quality Text-to-SQL Data at Scale. SynSQL-2.5M is the first million-scale cross-domain text-to-SQL dataset.

$ git clone https://github.com/RUCKBReasoning/OmniSQL.git
GitHub social preview for RUCKBReasoning/OmniSQL
Stars
456
456
This week
-1 ★
+1 this month
Forks
50
50
Language
Python
License
None
Created
Feb 27, 2025
1.7 years old
Last push
Sep 8, 2025

Stars, last 30 days

Oct 15, 2026 → Nov 16, 2026
★ 455▲ +1★ 456

Categories

GitHub topics

More in Language Models

Language Models

PKU-Alignment/beavertails

BeaverTails is a collection of datasets designed to facilitate research on safety alignment in large language models (LLMs).

MakefileApache-2.0updated Oct 27, 2023
GitHub ↗★ 185⑂ 6
Language Models

nlp-uoregon/mlmm-evaluation

Multilingual Large Language Models Evaluation Benchmark

🧠 Natural Language Processing
PythonApache-2.0updated Aug 21, 2024
GitHub ↗★ 135⑂ 18
Language Models

rasbt/LLMs-from-scratch

▲ +499 ★ this week

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

✂️ Tokenization & Preprocessing🧠 Natural Language Processing
Jupyter NotebookOtherupdated Nov 9, 2026
GitHub ↗★ 108.5K⑂ 16.8K
Language Models

dair-ai/Prompt-Engineering-Guide

▲ +216 ★ this week

🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.

🔍 Search & Retrieval
MDXMITupdated Mar 11, 2026
GitHub ↗★ 80.1K⑂ 8.8K

Data from GitHub · snapshot Nov 16, 2026