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
kaeru39
ryota39
AI & ML interests
language model
Organizations
Collections
7
models
22
ryota39/calm2-tokenizer
Updated
ryota39/luke-japanese-base-lite-reward
Text Classification
•
Updated
•
7
ryota39/mluke-large-lite-reward
Text Classification
•
Updated
•
8
ryota39/bge-m3-preference-classifier
Text Classification
•
Updated
•
7
ryota39/retriva-bert-preference-classifier
Text Classification
•
Updated
•
11
ryota39/RakutenAI-7B-instruct-reward
Text Generation
•
Updated
•
16
•
1
ryota39/Gakki-7B-reward-v0.1
Text Generation
•
Updated
•
16
ryota39/Gakki-7B
Text Generation
•
Updated
•
15
ryota39/Tora-7B-v0.2
Text Generation
•
Updated
•
19
•
1
ryota39/Tora-7B-v0.1
Text Generation
•
Updated
•
12
•
2
datasets
22
ryota39/wildchat-en
Viewer
•
Updated
•
284k
•
15
ryota39/open-preference-en-ja
Viewer
•
Updated
•
101k
•
63
ryota39/self-rewarding_instruct_AIFT_M3_scored
Viewer
•
Updated
•
7.11k
•
48
ryota39/self-rewarding_instruct_AIFT_M2_scored
Viewer
•
Updated
•
7k
•
47
ryota39/ichikara_preferance_scored
Viewer
•
Updated
•
1.73k
•
52
ryota39/self-rewarding_instruct_AIFT_M1_scored
Viewer
•
Updated
•
4k
•
52
ryota39/Synthetic-JP-Conversations-Magpie-Nemotron-4-10k_scored
Viewer
•
Updated
•
10.1k
•
46
ryota39/aya_ja_evol
Viewer
•
Updated
•
31.3k
•
14
ryota39/hh-rlhf-12k-ja_orpo
Viewer
•
Updated
•
12k
•
97
•
1
ryota39/izumi-lab-dpo-45k
Viewer
•
Updated
•
45.7k
•
65
•
1