Jinsei Shiraishi
OsakanaTeishoku
AI & ML interests
Large Language Models, Computer Vision, AI/ML application to medical settings
Recent Activity
upvoted an article about 20 hours ago
Mixture of Experts Explained upvoted an article 4 days ago
TRL v1.0: Post-Training Library Built to Move with the Field liked a Space 9 days ago
ACE-Step/Ace-Step-v1.5Organizations
experimental post-trained models of sbintuitions/sarashina2.2-3b and sbintuitions/sarashina2.2-3b-instruct-v0.1
-
sbintuitions/sarashina2.2-3b
3B • Updated • 633 • 16 -
sbintuitions/sarashina2.2-3b-instruct-v0.1
Text Generation • 3B • Updated • 3.74k • 36 -
OsakanaTeishoku/sarashina2.2-3b-cot-sft-20250920
Text Generation • 3B • Updated • 10 -
OsakanaTeishoku/sarashina2.2-3b-cot-sft-step1000-test-20251006
3B • Updated
experimental post-trained models of sbintuitions/sarashina2.2-3b and sbintuitions/sarashina2.2-3b-instruct-v0.1
-
sbintuitions/sarashina2.2-3b
3B • Updated • 633 • 16 -
sbintuitions/sarashina2.2-3b-instruct-v0.1
Text Generation • 3B • Updated • 3.74k • 36 -
OsakanaTeishoku/sarashina2.2-3b-cot-sft-20250920
Text Generation • 3B • Updated • 10 -
OsakanaTeishoku/sarashina2.2-3b-cot-sft-step1000-test-20251006
3B • Updated
models 24
OsakanaTeishoku/Qwen3-4B-Thinking-2507-reasoning-ja-20260329
Text Generation • 4B • Updated • 765
OsakanaTeishoku/Qwen3-4B-Thinking-2507-reasoning-ja-20260329-GGUF
4B • Updated • 268
OsakanaTeishoku/Qwen3-4B-Thinking-2507-reasoning-ja-20260328-GGUF
4B • Updated • 384
OsakanaTeishoku/Qwen3-4B-Thinking-2507-reasoning-ja-20260328
Text Generation • 4B • Updated • 283
OsakanaTeishoku/qwen3-4b-structured-output-20260108_cot3_epoch3_T4_merged_DPO
Text Generation • 4B • Updated • 1
OsakanaTeishoku/sarashina-toolcall-exp-20251213
Text Generation • 3B • Updated • 3
OsakanaTeishoku/gpt-oss-120b-distill-sarashina2.2-3b-cot-sft-step1000-test-20251006-lora-exp
Updated
OsakanaTeishoku/sarashina2.2-3b-cot-sft-step1000-test-20251006
3B • Updated
OsakanaTeishoku/sarashina2.2-3b-cot-sft-20250920
Text Generation • 3B • Updated • 10
OsakanaTeishoku/sarashina2.2-3b-unsloth-sft-20250627
Text Generation • Updated • 1
datasets 11
OsakanaTeishoku/Magpie-Tanuki-8B-CoT-formatted
Viewer • Updated • 8.39k • 17
OsakanaTeishoku/structured_data_with_cot_dataset_512_v2_dpo
Viewer • Updated • 3.93k • 3
OsakanaTeishoku/structured_data_with_cot_dataset_512_v2_dpo_before_processing
Viewer • Updated • 3.93k • 4
OsakanaTeishoku/matrix-gen-gpt5-with-modulator-incomplete
Viewer • Updated • 2 • 12
OsakanaTeishoku/matrix-gen-gpt5
Viewer • Updated • 3 • 9
OsakanaTeishoku/magpie-sft-v1.0-10k-gpt-oss-120b
Viewer • Updated • 10k • 4 • 1
OsakanaTeishoku/Zero_SFT_Ja_v3_Reasoning_formatted
Viewer • Updated • 32.7k • 15
OsakanaTeishoku/Qwen2.5-7B-Instruct-magpie-R-questions-ja-0.8k-tmp
Viewer • Updated • 800 • 7 • 1
OsakanaTeishoku/Qwen2.5-7B-Instruct-magpie-R-questions-10k
Viewer • Updated • 10k • 4
OsakanaTeishoku/qwen2.5-7b-magpie-test
Viewer • Updated • 10 • 6