kaeru39's picture

kaeru39 PRO

ryota39

·

AI & ML interests

LLM × RL

Recent Activity

liked a model about 8 hours ago

LiquidAI/LFM2.5-1.2B-JP

liked a model about 9 hours ago

Qwen/Qwen3-1.7B

liked a model 8 days ago

Qwen/Qwen3-30B-A3B-Instruct-2507

View all activity

Organizations

ryota39 's models 19

ryota39/Qwen3-8B-math-RL-ja

8B • Updated Dec 9, 2025 • 1

ryota39/Qwen3-8B-math-RL-en

Text Generation • 8B • Updated Dec 9, 2025 • 1

ryota39/gemma-2-2b-jpn-it-q8

3B • Updated Feb 22, 2025 • 5

ryota39/Tora-12B

Text Generation • 12B • Updated Nov 25, 2024 • 2 • 1

ryota39/Tora-7B-v0.1

Text Generation • Updated Nov 20, 2024 • 3 • 2

ryota39/mluke-large-lite-reward

Text Classification • 0.6B • Updated Jul 25, 2024 • 2

ryota39/retriva-bert-preference-classifier

Text Classification • 1B • Updated Jul 24, 2024 • 3

ryota39/Tora-7B-v0.2

Text Generation • 7B • Updated Jun 4, 2024 • 4 • 1

ryota39/llm-jp-1b-sft-100k-LoRA-dpo-12k

Text Generation • 1B • Updated May 1, 2024 • 3

ryota39/Phi-3-mini-4k-instruct-dpo

Text Generation • 4B • Updated May 1, 2024 • 5 • 3

ryota39/llm-jp-1b-sft-15k

Text Generation • 1B • Updated May 1, 2024 • 3

ryota39/llm-jp-1b-sft-100k-LoRA

Text Generation • 1B • Updated May 1, 2024 • 1

ryota39/llm-jp-1b-sft-15k-dpo-12k

Text Generation • 1B • Updated May 1, 2024 • 2 • 1

ryota39/llm-jp-1b-sft-100k-LoRA-dpo-45k

Text Generation • 1B • Updated May 1, 2024 • 5

ryota39/llm-jp-1b-sft-100k-LoRA-dpo-194k

Text Generation • 1B • Updated May 1, 2024 • 1

ryota39/llm-jp-1b-sft-2M-dpo-194k

Text Generation • 1B • Updated May 1, 2024 • 3

ryota39/llm-jp-1b-sft-2M

Text Generation • 1B • Updated May 1, 2024 • 4

ryota39/bilingual-gpt-neox-4b-instruction-sft-en-ja-84k

Text Generation • 4B • Updated Mar 24, 2024 • 4 • 1

ryota39/Tora_4B

Text Generation • 4B • Updated Mar 24, 2024 • 5 • 2