Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
Awesome-Text2SQL
Curated tutorials and resources for Large Language Models, Text2SQL, Text2DSL、Text2API、Text2Vis and more.
https://github.com/eosphoros-ai/Awesome-Text2SQL
Last synced: 4 days ago
JSON representation
-
📖 Survey
-
🔔 Leaderboard
- SDSQL - T5-SR) | 82.3 <br/>(2023/06-[C3 + ChatGPT + Zero-Shot](https://arxiv.org/pdf/2307.07306.pdf)) | 71.35 <br/>(2024/01-MCS-SQL + GPT-4) | 65.45 <br/>(2024/01-MCS-SQL + GPT-4) |
- IE-SQL+Execution-Guided Decoding - CatSQL + GraPPa) | 86.2 <br/>(2023/08-[DAIL-SQL + GPT-4](https://arxiv.org/pdf/2308.15363.pdf)) | 76.11 <br/>(2024/07-RECAP + Gemini) | 69.03 <br/>(2024/07-RECAP + Gemini) |
- HydraNet+Execution-Guided Decoding - [SHiP + PICARD](https://arxiv.org/pdf/2212.08785.pdf)) | 85.6 <br/>(2023/10-DPG-SQL + GPT-4 + Self-Correction) | 73.24 <br/>(2024/07-ByteBrain) | 68.87 <br/>(2024/07-ByteBrain) |
- BRIDGE - [N-best List Rerankers + PICARD](https://arxiv.org/pdf/2210.10668.pdf)) | 80.8 <br/>(2023/07-Hindsight Chain of Thought with GPT-4 and Instructions) | 69.56 <br/>(2024/04-GRA-SQL） | 65.34 <br/>(2024/07-Insights AI） |
- X-SQL+Execution-Guided Decoding - RESDSQL+T5-1.1-lm100k-xl) | 83.9 <br/>(2023/07-Hindsight Chain of Thought with GPT-4) | 72.63 <br/>(2024/05-[CHESS](https://arxiv.org/pdf/2405.16755)) ） | 66.69 <br/>(2024/05-[CHESS](https://arxiv.org/pdf/2405.16755)) |
- Text2SQLGen + EG - [S²SQL + ELECTRA ](https://arxiv.org/pdf/2203.06958.pdf)) | 79.9 <br/>(2023/02-[RESDSQL-3B + NatSQ](https://arxiv.org/pdf/2302.05965.pdf)) | 68.90 <br/>(2024/02-PB-SQL） | 64.95 <br/>(2024/04-OpenSearch-SQL,v1 + GPT-4) |
- WikiSQL - lily.github.io/spider)<br/>Exact Match(EM) | [Spider](https://yale-lily.github.io/spider)<br/>Exact Execution(EX) | [BIRD](https://bird-bench.github.io/)<br/>Valid Efficiency Score (VES) | [BIRD](https://bird-bench.github.io/)<br/>Execution Accuracy (EX) |
- SeaD+Execution-Guided Decoding - MiniSeek) | **91.2** <br/>(2023/11-MiniSeek) | **80.40** <br/>(2024/05-ExSL + granite-20b-code) | **71.83** <br/>(2024/07-Distillery + GPT-4o) |
- SeqGenSQL+EG - [RESDSQL-3B + NatSQL](https://arxiv.org/pdf/2302.05965.pdf)) | 78.5 <br/>(2022/11-SeaD + PQL) | 68.82 <br/>(2024/07-Insights AI） | 64.84 <br/>(2024/02-PB-SQL v1) |
- HydraNet+Execution-Guided Decoding - [SHiP + PICARD](https://arxiv.org/pdf/2212.08785.pdf)) | 85.6 <br/>(2023/10-DPG-SQL + GPT-4 + Self-Correction) | 73.24 <br/>(2024/07-ByteBrain) | 68.87 <br/>(2024/07-ByteBrain) |
- SeaD+Execution-Guided Decoding - MiniSeek) | **91.2** <br/>(2023/11-MiniSeek) | **80.40** <br/>(2024/05-ExSL + granite-20b-code) | **71.83** <br/>(2024/07-Distillery + GPT-4o) |
- SDSQL - T5-SR) | 82.3 <br/>(2023/06-[C3 + ChatGPT + Zero-Shot](https://arxiv.org/pdf/2307.07306.pdf)) | 71.35 <br/>(2024/01-MCS-SQL + GPT-4) | 65.45 <br/>(2024/01-MCS-SQL + GPT-4) |
- BRIDGE - [N-best List Rerankers + PICARD](https://arxiv.org/pdf/2210.10668.pdf)) | 80.8 <br/>(2023/07-Hindsight Chain of Thought with GPT-4 and Instructions) | 69.56 <br/>(2024/04-GRA-SQL） | 65.34 <br/>(2024/07-Insights AI） |
- X-SQL+Execution-Guided Decoding - RESDSQL+T5-1.1-lm100k-xl) | 83.9 <br/>(2023/07-Hindsight Chain of Thought with GPT-4) | 72.63 <br/>(2024/05-[CHESS](https://arxiv.org/pdf/2405.16755)) ） | 66.69 <br/>(2024/05-[CHESS](https://arxiv.org/pdf/2405.16755)) |
- SeqGenSQL+EG - [RESDSQL-3B + NatSQL](https://arxiv.org/pdf/2302.05965.pdf)) | 78.5 <br/>(2022/11-SeaD + PQL) | 68.82 <br/>(2024/07-Insights AI） | 64.84 <br/>(2024/02-PB-SQL v1) |
-
💬 Classic Model
- [code
- [paper
- [code
- ![ - lily.github.io/spider)
- ![ - bench.github.io/)
- [paper
- [code
- [paper
- [code
- ![ - main.105.pdf)
- ![
- ![ - bench.github.io/)
- [paper
- [code
- [paper
- [code
- ![
- ![
- [code
- ![ - bench.github.io/)
- [paper
- [code
- ![
- [paper
- ![
- ![ - long.142.pdf)
- ![ - explorer/)
- ![ - main.562.pdf)
- ![
- ![
- [paper
- ![
- ![
- ![
- [paper
- [code
- ![
- ![
- [paper
- ![
- [paper
- [paper
- ![
- [paper
- [code
- ![
- [paper
- [code
- ![
- ![
- [paper
- [paper
- [paper
- [paper
- [paper
- [code
- [paper
- ![
- ![ - us/download/details.aspx?id=54253)
- [paper
- [paper
- ![
- [paper
- [code
- [paper
- [code
- [paper
- [code
- [paper
- [code
- [paper
- [code
- ![
- [paper
- [code
- [paper
- [paper
- [code
- [code
- [paper
- [code
- [paper
- [code
- ![ - 1021.pdf)
- [paper
- [code
- [paper
- [code
- [paper
- [code
- [paper
- [code
- [paper
- [code
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
- [paper
-
🔥 Base Model
- [paper - llama)]
- [paper - 6B/blob/main/README.md)] [[model](https://huggingface.co/THUDM/chatglm-6b)]
- General Language Model
- [paper - lab/stanford_alpaca)] [[model](https://huggingface.co/tatsu-lab/alpaca-7b-wdiff/tree/main)]
- [paper - sys/FastChat)] [[model](https://huggingface.co/lmsys)]
- [paper
- [paper - 6B/blob/main/README_EN.md)] [[model](https://huggingface.co/THUDM/chatglm2-6b)]
- [code - inc/Baichuan-7B)]
- [code - inc/Baichuan-13B-Base)]
- [paper
- [paper - llama)]
- [paper
- [paper
- [paper
- [code - inc)]
- [paper - 1_5)]
- phi-1 - 1.5 demonstrates a nearly state-of-the-art performance among models with less than 10 billion parameters. 2023/12, They propose [Phi-2](https://huggingface.co/microsoft/phi-2), a 2.7 billion-parameter language model that demonstrates outstanding reasoning and language understanding capabilities, showcasing state-of-the-art performance among base language models with less than 13 billion parameters.
- [paper
- [model
- [paper
- [code
- [model
- [paper
- [code
- [model
- [paper - started/open_weight_models/)] [[model](https://huggingface.co/mistral-community/Mixtral-8x22B-v0.1)]
- [paper - 3-mini-128k-instruct)]
- [paper - llama/llama3)] [[model](https://huggingface.co/meta-llama)]
- [paper - 110B)]
- [paper - 6659360b33528ced941e557f)]
-
💡 Fine-tuning
-
💪 Dataset
- [paper
- [paper - lily.github.io/spider)]
- [paper
- [paper - 8zixluQuLa?usp=sharing)]
- [paper - lily.github.io/cosql)] [[dataset](https://yale-lily.github.io/cosql)]
- [paper
- [paper
- [paper - Hsuan-Lee/KaggleDBQA/)] [[dataset](https://github.com/Chia-Hsuan-Lee/KaggleDBQA/tree/main?tab=readme-ov-file#Data-Format)]
- [paper - intsoft/chase)] [[dataset](https://github.com/xjtu-intsoft/chase/tree/page/data)]
-
📦 Libraries
-
🔧 Practice Project
- ![GitHub Repo stars - ai/DB-GPT-Hub/stargazers)
- last commit
- sqlcoder
- ![GitHub Repo stars - ai/sqlcoder/stargazers)
- last commit
- modal_finetune_sql
- ![GitHub Repo stars - llama/modal_finetune_sql/stargazers)
- last commit
- ![GitHub Repo stars - Efficient-Tuning/stargazers)
- last commit
-
🤝 Friendship Links
- eosphoros
- ![GitHub Repo stars - ai)
- last commit
- Awesome-AIGC-Tutorials
- ![GitHub Repo stars - agi/Awesome-AIGC-Tutorials/stargazers)
- last commit
- ![Star History Chart - history.com/#eosphoros-ai/Awesome-Text2SQL)
Programming Languages
Categories
Sub Categories
Keywords
natural-language-processing
6
database
4
chatgpt
4
text-to-sql
4
artificial-intelligence
3
ceval
3
chinese
3
gpt-4
3
huggingface
3
large-language-models
3
semantic-parsing
3
mmlu
3
natural-language-interface
3
benchmark
2
deep-learning
2
llm
2
nlp
2
structured-prediction
1
pytorch
1
dbqa
1
nl2sql
1
heterogeneous-graph-neural-network
1
dialog
1
conversational-ai
1
natural-language
1
machine-learning
1
tutorials
1
stable-diffusion
1
prompt-engineering
1
multimodal
1
midjourney
1
courses-resource
1
awesome
1
aigc
1
ai
1
llama2
1
gpt
1
llama
1
wikisql
1
transformers
1
question-answering
1
program-synthesis
1
dataset
1