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
Recent Activity
liked
a model
about 3 hours ago
nvidia/Nemotron-4-340B-Reward
liked
a model
about 3 hours ago
Skywork/Skywork-Reward-Gemma-2-27B-v0.2
liked
a model
about 4 hours ago
Skywork/Skywork-Reward-Llama-3.1-8B
Organizations
Collections
7
models
23
ryota39/Tora-12B
Text Generation
•
Updated
•
7
ryota39/Tora-7B-v0.1
Text Generation
•
Updated
•
13
•
2
ryota39/waka-2B-simpo
Text Generation
•
Updated
•
13
ryota39/luke-japanese-base-lite-reward
Text Classification
•
Updated
•
1
ryota39/mluke-large-lite-reward
Text Classification
•
Updated
•
12
ryota39/bge-m3-preference-classifier
Text Classification
•
Updated
•
7
ryota39/retriva-bert-preference-classifier
Text Classification
•
Updated
•
3
ryota39/RakutenAI-7B-instruct-reward
Text Generation
•
Updated
•
10
•
1
ryota39/Gakki-7B-reward-v0.1
Text Generation
•
Updated
•
18
ryota39/Gakki-7B
Text Generation
•
Updated
•
7
datasets
25
ryota39/preference-en-ja-100k
Viewer
•
Updated
•
101k
•
78
•
1
ryota39/preference_test
Viewer
•
Updated
•
29.6k
•
45
ryota39/preference_test_annotated
Viewer
•
Updated
•
5
•
24
ryota39/open_preference_v0.4
Viewer
•
Updated
•
202k
•
19
•
1
ryota39/webgpt_comparisons-ja
Viewer
•
Updated
•
17.4k
•
19
•
1
ryota39/synthetic-instruct-gptj-pairwise-ja
Viewer
•
Updated
•
33.1k
•
18
•
1
ryota39/self-rewarding_instruct_AIFT_M3_scored
Viewer
•
Updated
•
7.11k
•
41
ryota39/self-rewarding_instruct_AIFT_M2_scored
Viewer
•
Updated
•
7k
•
41
ryota39/self-rewarding_instruct_AIFT_M1_scored
Viewer
•
Updated
•
4k
•
48
ryota39/Synthetic-JP-Conversations-Magpie-Nemotron-4-10k_scored
Viewer
•
Updated
•
10.1k
•
39