ryota39/Phi-3-mini-4k-instruct-dpo
Text Generation
•
Updated
•
21
•
3
Local AI Hackathon#001
メタデータラボ様からの計算資源のご提供により構築したモデルおよびデータセットhttps://prtimes.jp/main/html/rd/p/000000008.000056944.html
-
-
ryota39/truthy-dpo-ja
Viewer • Updated • 1.02k • 56 -
ryota39/dpo-ja-194k
Viewer • Updated • 194k • 72 • 1 -
ryota39/hh-rlhf-12k-ja_orpo
Viewer • Updated • 12k • 39 • 1 -
ryota39/dpo-ja-45k
Viewer • Updated • 45.2k • 60 -
ryota39/llm-jp-1b-sft-2M-dpo-194k
Text Generation • Updated • 18 -
ryota39/llm-jp-1b-sft-100k-LoRA
Text Generation • Updated • 19 -
ryota39/llm-jp-1b-sft-2M
Text Generation • Updated • 17 -
ryota39/llm-jp-1b-sft-15k-dpo-12k
Text Generation • Updated • 13 • 1 -
ryota39/llm-jp-1b-sft-100k-LoRA-dpo-45k
Text Generation • Updated • 22 -
ryota39/llm-jp-1b-sft-100k-LoRA-dpo-194k
Text Generation • Updated • 414 -
ryota39/llm-jp-1b-sft-100k-LoRA-kto-194k
Text Generation • Updated • 19 -
ryota39/newschat_1k
Viewer • Updated • 1.05k • 45 • 1