am team

a-m-team's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Articles

Emperorizzis 

authored 2 papers 19 days ago

Exploring the Potential of Offline RL for Reasoning in LLMs: A Preliminary Study

Paper • 2505.02142 • Published May 4, 2025

ASTRA: Automated Synthesis of agentic Trajectories and Reinforcement Arenas

Paper • 2601.21558 • Published 23 days ago • 58

Emperorizzis 

submitted a paper to Daily Papers 20 days ago

ASTRA: Automated Synthesis of agentic Trajectories and Reinforcement Arenas

Paper • 2601.21558 • Published 23 days ago • 58

howtain 

in a-m-team/AM-DeepSeek-R1-0528-Distilled 6 months ago

教师模型是 AM-DeepSeek-R1-0528还是 DeepSeek-R1-0528？

1

#11 opened 6 months ago by

flishwang

howtain 

in a-m-team/AM-DeepSeek-R1-0528-Distilled 7 months ago

verify_score的计算方法是什么？

1

#9 opened 7 months ago by

lzzdmoo

howtain 

in a-m-team/AM-DeepSeek-R1-0528-Distilled 8 months ago

What's the context length for SFT tuning?

1

#7 opened 8 months ago by

Dengdong

Emperorizzis 

in a-m-team/AM-DeepSeek-R1-0528-Distilled 8 months ago

Unable to load dataset

➕ 1

2

#3 opened 9 months ago by

lewtun

howtain 

in a-m-team/AM-DeepSeek-R1-0528-Distilled 8 months ago

什么叫中国速度！

6

#1 opened 9 months ago by

reign12

Emperorizzis 

in a-m-team/AM-DeepSeek-R1-0528-Distilled 8 months ago

什么叫中国速度！

6

#1 opened 9 months ago by

reign12

Emperorizzis 

in a-m-team/AM-Thinking-v1-Distilled 8 months ago

Which model is AM-Deepseek-R1-0528?

➕ 1

2

#4 opened 9 months ago by

SDSB

Emperorizzis 

in a-m-team/AM-DeepSeek-R1-0528-Distilled 8 months ago

Discovered a very strange problem

🔥 1

5

#5 opened 9 months ago by

Night-Quiet

Emperorizzis 

updated a dataset 8 months ago

a-m-team/AM-Thinking-v1-Distilled

Preview • Updated Jun 12, 2025 • 1.08k • 58

howtain 

in a-m-team/AM-DeepSeek-R1-0528-Distilled 8 months ago

Discovered a very strange problem

🔥 1

5

#5 opened 9 months ago by

Night-Quiet

howtain 

in a-m-team/AM-Thinking-v1-Distilled 8 months ago

Which model is AM-Deepseek-R1-0528?

➕ 1

2

#4 opened 9 months ago by

SDSB

Emperorizzis 

updated a dataset 9 months ago

a-m-team/AM-DeepSeek-R1-0528-Distilled

Preview • Updated Jun 9, 2025 • 903 • 100

Emperorizzis 

updated a collection 9 months ago

AM-Distilled-Dataset

Collection

AM-Distilled-Dataset • 5 items • Updated Jun 5, 2025 • 3

Emperorizzis 

published a dataset 9 months ago

a-m-team/AM-DeepSeek-R1-0528-Distilled

Preview • Updated Jun 9, 2025 • 903 • 100

Emperorizzis 

in a-m-team/AM-Thinking-v1 9 months ago

AIME 2024 contamination

1

#6 opened 9 months ago by

autoprogrammer

Emperorizzis 

in a-m-team/AM-Thinking-v1-Distilled 9 months ago

add more metadata

2

#3 opened 9 months ago by

davanstrien

Emperorizzis 

updated a dataset 9 months ago

a-m-team/AM-Qwen3-Distilled

Preview • Updated May 22, 2025 • 1.07k • 21