SinclairWang (Zengzhi Wang)

upvoted an article 7 days ago

Article

Releasing the largest multilingual open pretraining dataset

By

•

8 days ago

• 94

upvoted 3 papers 10 days ago

Self-Consistency Preference Optimization

Paper • 2411.04109 • Published 15 days ago • 14

Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models

Paper • 2411.04996 • Published 14 days ago • 48

Balancing Pipeline Parallelism with Vocabulary Parallelism

Paper • 2411.05288 • Published 14 days ago • 19

upvoted a paper 11 days ago

OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models

Paper • 2411.04905 • Published 14 days ago • 108

upvoted a collection 12 days ago

Qwen2.5-Coder

Collection

Code-specific model series based on Qwen2.5 • 40 items • Updated 3 days ago • 223

upvoted a paper 17 days ago

OS-ATLAS: A Foundation Action Model for Generalist GUI Agents

Paper • 2410.23218 • Published 22 days ago • 46

upvoted 2 papers 28 days ago

What Matters for Model Merging at Scale?

Paper • 2410.03617 • Published Oct 4 • 8

A Comparative Study on Reasoning Patterns of OpenAI's o1 Model

Paper • 2410.13639 • Published Oct 17 • 16

upvoted a paper about 1 month ago

MathCoder2: Better Math Reasoning from Continued Pretraining on Model-translated Mathematical Code

Paper • 2410.08196 • Published Oct 10 • 44

upvoted an article about 1 month ago

Article

Scaling AI-based Data Processing with Hugging Face + Dask

Oct 9

• 23

upvoted 2 papers about 1 month ago

TLDR: Token-Level Detective Reward Model for Large Vision Language Models

Paper • 2410.04734 • Published Oct 7 • 16

LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning

Paper • 2410.02884 • Published Oct 3 • 50

upvoted 5 papers about 2 months ago

Revisit Large-Scale Image-Caption Data in Pre-training Multimodal Foundation Models

Paper • 2410.02740 • Published Oct 3 • 52

VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment

Paper • 2410.01679 • Published Oct 2 • 22

A Survey on the Honesty of Large Language Models

Paper • 2409.18786 • Published Sep 27 • 31

Atlas-Chat: Adapting Large Language Models for Low-Resource Moroccan Arabic Dialect

Paper • 2409.17912 • Published Sep 26 • 21

TPI-LLM: Serving 70B-scale LLMs Efficiently on Low-resource Edge Devices

Paper • 2410.00531 • Published Oct 1 • 29

upvoted a collection about 2 months ago

📑Trending Papers - September 9⃣️

Collection

10 items • Updated 6 days ago • 8

upvoted an article about 2 months ago

Article

RegMix: Data Mixture as Regression for Language Model Pre-training

By

•

Jul 11

• 10

Zengzhi Wang

AI & ML interests

Organizations

SinclairWang's activity

Releasing the largest multilingual open pretraining dataset

Self-Consistency Preference Optimization

Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models

Balancing Pipeline Parallelism with Vocabulary Parallelism

OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models

Qwen2.5-Coder

OS-ATLAS: A Foundation Action Model for Generalist GUI Agents

What Matters for Model Merging at Scale?

A Comparative Study on Reasoning Patterns of OpenAI's o1 Model

MathCoder2: Better Math Reasoning from Continued Pretraining on Model-translated Mathematical Code

Scaling AI-based Data Processing with Hugging Face + Dask

TLDR: Token-Level Detective Reward Model for Large Vision Language Models

LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning

Revisit Large-Scale Image-Caption Data in Pre-training Multimodal Foundation Models

VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment

A Survey on the Honesty of Large Language Models

Atlas-Chat: Adapting Large Language Models for Low-Resource Moroccan Arabic Dialect

TPI-LLM: Serving 70B-scale LLMs Efficiently on Low-resource Edge Devices

📑Trending Papers - September 9⃣️

RegMix: Data Mixture as Regression for Language Model Pre-training