15 17 1

Yi Cui

onekq

https://onekq.ai

AI & ML interests

Benchmark, Code Generation Model

Recent Activity

posted an update 1 day ago

The bitter lesson is super counter intuitive. Even those of us who pledge to it keep violating it 😅🤗 https://lukaspetersson.com/blog/2025/bitter-vertical/

posted an update 2 days ago

🐋DeepSeek-v3-0324🐋 ranks higher than v3, now is tied with QwQ-32B https://huggingface.co/spaces/onekq-ai/WebApp1K-models-leaderboard

updated a Space 2 days ago

onekq-ai/WebApp1K-models-leaderboard

View all activity

Organizations

onekq's activity

posted an update 1 day ago

Post

727

The bitter lesson is super counter intuitive. Even those of us who pledge to it keep violating it 😅🤗

https://lukaspetersson.com/blog/2025/bitter-vertical/

posted an update 2 days ago

Post

1775

🐋DeepSeek-v3-0324🐋 ranks higher than v3, now is tied with QwQ-32B
onekq-ai/WebApp1K-models-leaderboard

updated a Space 2 days ago

WebApp1K Models Leaderboard

🥇

Rank and compare models using pass@k metrics

posted an update 4 days ago

Post

3583

I shared my view on Qwen vs DeepSeek (student vs genius), and I forgot to mention this: they are neighbors in the same city.
https://en.wikipedia.org/wiki/Hangzhou

posted an update 6 days ago

Post

3719

Folks, let's get ready.🥳 We will be busy soon. 😅🤗https://github.com/huggingface/transformers/pull/36878

replied to their post 6 days ago

Yes! I'm looking forward to R2

replied to their post 7 days ago

I tested and ranked every model drop for my leaderboard https://huggingface.co/spaces/onekq-ai/WebApp1K-models-leaderboard but this time I gave up.

Whatever questions this model aims to solve, they are out of my league.

posted an update 7 days ago

Post

1553

I like to benchmark 💵o1-pro💵 but it is way too expensive for me 🤦‍♂️

4 replies

New activity in onekq-ai/OneSQL-v0.1-Qwen-7B-GGUF 7 days ago

Example prompt and response here

#3 opened 10 days ago by

JLouisBiz

How do you practicale use it or see practical usage for other users?

#1 opened 10 days ago by

JLouisBiz

replied to their post 8 days ago

You can infer on CPU, but it will be very very slow 😕

posted an update 8 days ago

Post

442

The majority of OneSQL downloads went to the lowest end (7B-GGUF). I didn't expect this at all. The accuracy of this variant is the lowest, as the tradeoff for its small size.

Like all LLMs, coding models hallucinate too. The wrong answers they give are only inches away from the right answers. In case of SQL, the code is not only presentable, but also executable, hence returning the wrong rows.

I'm clueless, and curious how users will deal with this.

3 replies

updated 2 models 9 days ago

onekq-ai/OneSQL-v0.1-Qwen-7B

Text Generation • Updated 9 days ago

onekq-ai/OneSQL-v0.1-Qwen-32B

Text Generation • Updated 9 days ago • 6

New activity in onekq-ai/OneSQL-v0.1-Qwen-7B-GGUF 9 days ago

Proposal to rename files

#2 opened 10 days ago by

JLouisBiz

updated 2 models 9 days ago

onekq-ai/OneSQL-v0.1-Qwen-32B-GGUF

Updated 9 days ago • 581

onekq-ai/OneSQL-v0.1-Qwen-7B-GGUF

Updated 9 days ago • 1.03k

posted an update 10 days ago

Post

2265

Introducing 🎉 OneSQL-v0.1🥳, our first text-to-SQL model based on Qwen2.5-Coder. This model has achieved an EX score of 63.33 on the BIRD leaderboard (https://bird-bench.github.io/).

The model family includes 7B and 32B,
onekq-ai/onesql-v01-qwen-67d8e3eb1611c5532bb90c5f
and can be also found on Ollama (https://ollama.com/onekq/OneSQL-v0.1-Qwen)

My goal is to make OneSQL the most usable open-weights model for text-to-SQL. I'm currently working on best practices to help users use this model the right away and avoid pitfalls. After that, I plan to train the next version to push for a higher EX score.

Enjoy this model and feel free to share comments/questions 🤗

1 reply

updated a collection 10 days ago

OneSQL-v0.1-Qwen

Collection

Text-to-SQL model • 4 items • Updated 10 days ago • 1