HF中国镜像站

Yi Cui's picture

Yi Cui

onekq

·

https://onekq.ai

AI & ML interests

Benchmark, Code Generation Model

Recent Activity

posted an update about 17 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 17 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 17 hours ago

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

View all activity

Organizations

onekq's activity

upvoted 4 papers 5 months ago

Cross-Entropy Loss Functions: Theoretical Analysis and Applications

Paper • 2304.07288 • Published Apr 14, 2023 • 1

Training Language Models on Synthetic Edit Sequences Improves Code Synthesis

Paper • 2410.02749 • Published Oct 3, 2024 • 12

Many-Shot In-Context Learning

Paper • 2404.11018 • Published Apr 17, 2024 • 4

Not All LLM Reasoners Are Created Equal

Paper • 2410.01748 • Published Oct 2, 2024 • 28

upvoted 10 papers 6 months ago

Batch Prompting: Efficient Inference with Large Language Model APIs

Paper • 2301.08721 • Published Jan 19, 2023 • 1

A Survey on In-context Learning

Paper • 2301.00234 • Published Dec 31, 2022 • 2

An Explanation of In-context Learning as Implicit Bayesian Inference

Paper • 2111.02080 • Published Nov 3, 2021 • 1

Explaining NonLinear Classification Decisions with Deep Taylor Decomposition

Paper • 1512.02479 • Published Dec 8, 2015 • 1

From Instructions to Constraints: Language Model Alignment with Automatic Constraint Verification

Paper • 2403.06326 • Published Mar 10, 2024 • 1

Is Prompt All You Need? No. A Comprehensive and Broader View of Instruction Learning

Paper • 2303.10475 • Published Mar 18, 2023 • 2

Eliciting Instruction-tuned Code Language Models' Capabilities to Utilize Auxiliary Function for Code Generation

Paper • 2409.13928 • Published Sep 20, 2024 • 1

WebApp1K: A Practical Code-Generation Benchmark for Web App Development

Paper • 2408.00019 • Published Jul 30, 2024 • 1

The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning

Paper • 2312.01552 • Published Dec 4, 2023 • 33

Instruction Following without Instruction Tuning

Paper • 2409.14254 • Published Sep 21, 2024 • 29

upvoted an article 6 months ago

Article

Our Transformers Code Agent beats the GAIA benchmark!

Jul 1, 2024

• 74

upvoted 2 papers 6 months ago

A Case Study of Web App Coding with OpenAI Reasoning Models

Paper • 2409.13773 • Published Sep 19, 2024 • 6

The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning

Paper • 2304.05366 • Published Apr 11, 2023 • 1