Hugging Face's logo

ONEKQ AI

company
https://onekq.ai
onekq_ai
onekq
Activity Feed

AI & ML interests

Benchmark, Code Generation, LLM

Recent Activity

onekq  updated a Space 2 days ago
onekq-ai/WebApp1K-models-leaderboard
onekq  new activity 7 days ago
onekq-ai/OneSQL-v0.1-Qwen-7B-GGUF:Example prompt and response here
onekq  new activity 7 days ago
onekq-ai/OneSQL-v0.1-Qwen-7B-GGUF:How do you practicale use it or see practical usage for other users?
View all activity

onekq-ai's activity

onekq 
posted an update about 20 hours ago
onekq 
posted an update 2 days ago
onekq 
updated a Space 2 days ago
onekq 
posted an update 3 days ago
onekq 
posted an update 6 days ago
view post
Post
3716
Folks, let's get ready.🥳 We will be busy soon. 😅🤗https://github.com/huggingface/transformers/pull/36878
onekq 
posted an update 7 days ago
view post
Post
1552
I like to benchmark 💵o1-pro💵 but it is way too expensive for me 🤦‍♂️
·
onekq 
in onekq-ai/OneSQL-v0.1-Qwen-7B-GGUF 7 days ago

Example prompt and response here

3
#3 opened 9 days ago by
JLouisBiz

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

7
#1 opened 9 days ago by
JLouisBiz
onekq 
posted an update 8 days ago
view post
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
·
onekq 
updated 2 models 9 days ago
onekq 
in onekq-ai/OneSQL-v0.1-Qwen-7B-GGUF 9 days ago

Proposal to rename files

2
#2 opened 9 days ago by
JLouisBiz
onekq 
updated 2 models 9 days ago
onekq 
posted an update 9 days ago
view post
Post
2264
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
·
onekq 
updated a collection 9 days ago
onekq 
posted an update 11 days ago
view post
Post
2471
Common formula to DIY a LLM:

Post train a Qwen model with a dataset distilled from DeepSeek 😂

  • 2 replies
·