12 17 1

Yi Cui

onekq

https://onekq.ai

AI & ML interests

Benchmark, Code Generation Model

Recent Activity

posted an update about 2 hours ago

Qwen made good students, DeepSeek made a genius. This is my summaries of their differentiations. I don't think these two players are coordinated but they both have clear goals. One is to build ecosystem and the other is to push AGI. And IMO they are both doing really well.

replied to their post about 2 hours ago

The performance of deepseek-r1-distill-qwen-32b is abysmal. I know Qwen instruct (not coder) is quite poor on coding. As such, I have low expectation on other R1 repro works also based on Qwen instruct too. https://huggingface.co/collections/onekq-ai/r1-reproduction-works-67a93f2fb8b21202c9eedf0b This makes it particularly mysterious what went into QwQ-32B? Why did it work so well? Was it trained from scratch? Anyone has insights about this? https://huggingface.co/spaces/onekq-ai/WebApp1K-models-leaderboard

updated a model about 2 hours ago

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

View all activity

Organizations

Posts 26

Post

Qwen made good students, DeepSeek made a genius.

This is my summaries of their differentiations. I don't think these two players are coordinated but they both have clear goals. One is to build ecosystem and the other is to push AGI.

And IMO they are both doing really well.

View all Posts

Articles 2

Article

Does Daily Software Engineering Work Need Reasoning Models?

View all Articles

Papers 3

arxiv:2409.13773

arxiv:2409.05177

arxiv:2408.00019

models

None public yet

datasets

None public yet