Wentao Ma

tonymwt's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

liked a dataset 4 days ago

bosonai/IHBench

Updated 3 days ago • 47 • 1

upvoted an article 4 days ago

view article

Article

Keep the Tokens Flowing: Lessons from 16 Open-Source RL Libraries

• 
• 
• +7

aminediroHF, qgallouedec, kashif, lewtun, edbeeching, albertvillanova, nouamanetazi, lvwerra, sergiopaniego

•

Mar 10

• 164

liked a Space 4 days ago

Running

191

The ultimate guide to RL environments: building and scaling them in the LLM era

📝

191

Building and scaling RL environments for LLM training

published a dataset 4 days ago

bosonai/IHBench

Updated 3 days ago • 47 • 1

New activity in bosonai/IHBench 4 days ago

Add dataset

#2 opened 4 days ago by

ahmadsalimi

liked a model 12 days ago

Qwen/Qwen3.5-4B

Image-Text-to-Text • 5B • Updated Mar 2 • 9.62M • • 669

liked a dataset 12 days ago

Snowflake/AgentWorldModel-1K

Updated Feb 17 • 1.03k • 71

liked a model 17 days ago

bosonai/higgs-audio-v3-tts-4b

Text-to-Speech • 5B • Updated 6 days ago • 76.1k • 510

authored a paper about 1 month ago

Back to Basics: Revisiting ASR in the Age of Voice Agents

Paper • 2603.25727 • Published Mar 26 • 1

upvoted a paper about 1 month ago

Back to Basics: Revisiting ASR in the Age of Voice Agents

Paper • 2603.25727 • Published Mar 26 • 1

liked 3 datasets 2 months ago

HuggingFaceH4/ultrachat_200k

Viewer • Updated Oct 16, 2024 • 515k • 59.3k • 734

Magpie-Align/Magpie-Llama-3.1-Pro-MT-300K-Filtered

Viewer • Updated Aug 28, 2024 • 300k • 516 • 17

HuggingFaceTB/smoltalk

Viewer • Updated Feb 10, 2025 • 2.2M • 19.3k • 415

updated a dataset 2 months ago

bosonai/WildASR

Viewer • Updated Apr 13 • 10.1k • 217 • 9

liked 2 datasets 2 months ago

bosonai/WildASR

Viewer • Updated Apr 13 • 10.1k • 217 • 9

stepfun-ai/Step-3.5-Flash-SFT

Viewer • Updated Mar 14 • 1.62M • 5.19k • 338

published a dataset 3 months ago

bosonai/WildASR

Viewer • Updated Apr 13 • 10.1k • 217 • 9

updated a collection 3 months ago

posttrain_model_ckpts

Collection

LoRA checkpoints for post-training experiments on LLaMA-2-7B with various data selection methods (MMLU task). • 8 items • Updated Mar 18