12 17 1

Yi Cui PRO

onekq

https://onekq.ai

AI & ML interests

Benchmark, Code Generation Model

Recent Activity

updated a model 3 minutes ago

onekq-ai/granite-20b-code-base-8k-bnb-4bit

updated a collection about 23 hours ago

QLora-ready Coding Models

updated a collection about 23 hours ago

QLora-ready Coding Models

View all activity

Articles

Does Daily Software Engineering Work Need Reasoning Models?

Sep 24, 2024

• 5

All LLMs Write Great Code, But Some Make (A Lot) Fewer Mistakes

Sep 12, 2024

• 4

Organizations

onekq's activity

updated a model 3 minutes ago

onekq-ai/granite-20b-code-base-8k-bnb-4bit

Text Generation • Updated 3 minutes ago

updated a collection about 23 hours ago

QLora-ready Coding Models

Collection

For Finetuning. GPU is needed for both quantization and inference. • 15 items • Updated about 23 hours ago

updated a dataset 5 days ago

onekq-ai/the-stack-v2-dedup-sql-annotate

Viewer • Updated 5 days ago • 4.19M • 7

updated a Space 9 days ago

Running

🥇

WebApp1K Models Leaderboard

posted an update 14 days ago

Post

3020

🐋 DeepSeek 🐋v3 achieves a solid 7 point jump than v2.5, surpassing GPT-4o, but is still behind 🍓 o1 🍓and Claude 3.5.

onekq-ai/WebApp1K-models-leaderboard

posted an update 3 months ago

Post

586

October version of Claude 3.5 lifts SOTA (set by its June version) by 7 points.
onekq-ai/WebApp1K-models-leaderboard

Closed sourced models are widening the gap again.

Note: Our frontier leaderboard now uses double test scenarios because the single-scenario test suit has been saturated.