chansung park's picture

chansung park PRO

chansung

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 12 days ago

EXAONE 4.0: Unified Large Language Models Integrating Non-reasoning and Reasoning Modes

reacted to their post with 👍 21 days ago

YAML engineering becomes more and more important than ever from infra provisioning to model training (recipes). Here, I built a simple editor first for @dstackai, and I will share the live endpoint this week. Let me know what you think about this approach. Based on this approach, if people think this is useful, I am going to do the same thing for the LLM training recipes for popular frameworks such as Hugging Face open-r1, Axolotl, and so on. Let me hear.

posted an update 21 days ago

YAML engineering becomes more and more important than ever from infra provisioning to model training (recipes). Here, I built a simple editor first for @dstackai, and I will share the live endpoint this week. Let me know what you think about this approach. Based on this approach, if people think this is useful, I am going to do the same thing for the LLM training recipes for popular frameworks such as Hugging Face open-r1, Axolotl, and so on. Let me hear.

View all activity

Organizations

chansung 's models 122

chansung/Qwen2.5-1.5B-CCRL-CUR-VAR-3E

Text Generation • 2B • Updated Jun 12 • 2

chansung/Qwen2.5-7B-CCRL-CUR-VAR-ASCE-REV-3E

Text Generation • 8B • Updated Jun 12 • 2

chansung/Qwen2.5-3B-CCRL-CUR-UNI-3E

Text Generation • 3B • Updated Jun 11 • 3

chansung/Qwen2.5-1.5B-CCRL-CUR-VAR-ASCE-REV-1E

Text Generation • 2B • Updated Jun 10 • 3

chansung/Gemma3-4B-CCRL-CUR-UNI-1E

chansung/Qwen2.5-1.5B-CCRL-CUR-COMPLEX-ONLY-1E

Text Generation • 2B • Updated Jun 9 • 2

chansung/Qwen2.5-1.5B-CCRL-CUR-EDGE-ONLY-1E

Text Generation • 2B • Updated Jun 9 • 2

chansung/Qwen2.5-1.5B-CCRL-CUR-BASIC-ONLY-1E

Text Generation • 2B • Updated Jun 9 • 2

chansung/Qwen2.5-1.5B-CCRL-CUR-VAR-1E

Text Generation • 2B • Updated Jun 9 • 2

chansung/Qwen2.5-1.5B-CCRL-CUR-VAR-ASCE-NORMAL-1E

Text Generation • 2B • Updated Jun 9 • 3

chansung/Qwen2.5-1.5B-CCRL-CUR-UNI-1E

Text Generation • 2B • Updated Jun 9 • 45

chansung/Qwen2.5-3B-CCRL-CUR-EDGE-ONLY-1E

Text Generation • 3B • Updated Jun 5 • 2

chansung/Qwen2.5-3B-CCRL-CUR-COMPLEX-ONLY-1E

Text Generation • 3B • Updated Jun 5 • 2

chansung/Gemma3-12B-CCRL-CUR-UNI-1E

chansung/Qwen2.5-3B-CCRL-CUR-VAR-1E

Text Generation • 3B • Updated Jun 5 • 2

chansung/Qwen2.5-3B-CCRL-CUR-VAR-ASCE-REV-1E

Text Generation • 3B • Updated Jun 5 • 2

chansung/Qwen2.5-3B-CCRL-CUR-VAR-ASCE-NORMAL-1E

Text Generation • 3B • Updated Jun 4 • 2

chansung/Qwen2.5-3B-CCRL-CUR-BASIC-ONLY-1E

Text Generation • 3B • Updated Jun 4 • 2

chansung/Qwen2.5-3B-CCRL-CUR-UNI-1E

Text Generation • 3B • Updated Jun 4 • 2

chansung/Qwen2.5-7B-CCRL-CUR-COMPLEX-ONLY-1E

Text Generation • 8B • Updated May 23 • 4

chansung/Qwen2.5-7B-CCRL-CUR-EDGE-ONLY-1E

Text Generation • 8B • Updated May 22 • 4

chansung/Qwen2.5-7B-CCRL-CUR-BASIC-ONLY-1E

Text Generation • 8B • Updated May 22 • 4

chansung/Qwen2.5-7B-CCRL-CUR-VAR-ASCE-REV-1E

Text Generation • 8B • Updated May 20 • 4

chansung/Qwen2.5-7B-CCRL-CUR-VAR-ASCE-NORMAL-1E

Text Generation • 8B • Updated May 20 • 4

chansung/Qwen2.5-7B-CCRL-CUR-VAR-1E

Text Generation • 8B • Updated May 19 • 5 • 2

chansung/Qwen2.5-7B-CCRL-CUR-UNI-1E

Text Generation • 8B • Updated May 19 • 4

chansung/Qwen2.5-7B-CCRL-CUR-1E

Text Generation • 8B • Updated May 14 • 5 • 1

chansung/Qwen2.5-7B-CCRL-3

8B • Updated May 5 • 1

chansung/Qwen2.5-7B-CCRL-0

Text Generation • 8B • Updated May 4 • 5

chansung/Qwen2.5-7B-CCRL-2

Text Generation • 8B • Updated May 3 • 339