Yulianghua

lianghua

6 14

AI & ML interests

None yet

Recent Activity

upvoted an article 2 days ago

The Most Intuitive Way to Understand Score Function Centering: Understand Trainer-Generator Mismatch in Async RL from the Score Function

upvoted an article 8 months ago

Unlocking Agentic RL Training for GPT-OSS: A Practical Retrospective

liked a Space about 1 year ago

HuggingFaceTB/smol-training-playbook

View all activity

Organizations

upvoted an article 2 days ago

Article

The Most Intuitive Way to Understand Score Function Centering: Understand Trainer-Generator Mismatch in Async RL from the Score Function

NormalUhr

•

22 days ago

• 16

upvoted an article 8 months ago

Article

Unlocking Agentic RL Training for GPT-OSS: A Practical Retrospective

•

Jan 27

• 82

liked a Space about 1 year ago

The Smol Training Playbook

📚

3.35k

The secrets to building world-class LLMs

liked a model about 1 year ago

meituan-longcat/LongCat-Flash-Chat

Text Generation • 562B • Updated Sep 24, 2025 • 13.5k • 540

upvoted an article over 1 year ago

Article

SmolLM3: smol, multilingual, long-context reasoner

eliebak, cmpatino, anton-l, edbeeching, m-ric, nouamanetazi, akseljoonas, guipenedo, hynky, clefourrier, SaylorTwift, kashif, qgallouedec, hlarcher, glutamatt, Xenova, reach-vb, ngxson, craffel, lewtun, loubnabnl, lvwerra, thomwolf

•

Jul 8, 2025

• 805

liked 3 Spaces over 1 year ago

LLM训练终极指南 | The Ultra-Scale Playbook

🔥

277

了解LLM训练的方方面面

FineWeb: decanting the web for the finest text data at scale

🍷

1.46k

Explore the FineWeb dataset and its creation process

The Ultra-Scale Playbook

🌌

4.12k

The ultimate guide to training LLM on large GPU Clusters

upvoted 2 articles over 1 year ago

Article

DualPipe Explained: A Comprehensive Guide to DualPipe That Anyone Can Understand—Even Without a Distributed Training Background

NormalUhr

•

Feb 28, 2025

• 22

Article

Open R1: Update #3

open-r1

•

Mar 11, 2025

• 297

liked a model almost 2 years ago

TencentBAC/Conan-embedding-v1

0.3B • Updated Nov 27, 2024 • 484k • 166

upvoted a collection over 2 years ago

Zephyr ORPO

Collection

Models and datasets to align LLMs with Odds Ratio Preference Optimisation (ORPO). Recipes here: https://github.com/huggingface/alignment-handbook • 3 items • Updated Aug 3 • 19

liked a model over 2 years ago

meta-llama/Meta-Llama-3-8B

Text Generation • 8B • Updated Sep 27, 2024 • 123k • • 6.79k

liked a dataset over 2 years ago

Open-Orca/OpenOrca

Viewer • Updated Feb 19, 2025 • 2.94M • 13.6k • 1.63k

liked a Space over 2 years ago

LLaMA Board

🦙

216

Fine-tuning large language model with Gradio UI

liked 2 models over 2 years ago

BAAI/bge-m3

openai/whisper-large-v3

Automatic Speech Recognition • 2B • Updated Aug 12, 2024 • 3.54M • • 6.76k

liked 3 models almost 3 years ago

Yulianghua

AI & ML interests

Recent Activity

Organizations

lianghua's activity

The Most Intuitive Way to Understand Score Function Centering: Understand Trainer-Generator Mismatch in Async RL from the Score Function

Unlocking Agentic RL Training for GPT-OSS: A Practical Retrospective

The Smol Training Playbook

SmolLM3: smol, multilingual, long-context reasoner

LLM训练终极指南 | The Ultra-Scale Playbook

FineWeb: decanting the web for the finest text data at scale

The Ultra-Scale Playbook

DualPipe Explained: A Comprehensive Guide to DualPipe That Anyone Can Understand—Even Without a Distributed Training Background

Open R1: Update #3

LLaMA Board