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 8 hours ago
nvidia/Llama-3.1-Nemotron-70B-Reward-HF
liked
a model
about 11 hours ago
unsloth/Qwen2.5-0.5B-Instruct
liked
a model
1 day ago
nvidia/Nemotron-4-340B-Reward
Organizations
Collections
7
models
23
ryota39/Tora-12B
Text Generation
•
Updated
•
11
ryota39/Tora-7B-v0.1
Text Generation
•
Updated
•
15
•
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
•
16
ryota39/bge-m3-preference-classifier
Text Classification
•
Updated
•
7
ryota39/retriva-bert-preference-classifier
Text Classification
•
Updated
•
8
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
•
8
datasets
25
ryota39/preference-en-ja-100k
Viewer
•
Updated
•
101k
•
96
•
1
ryota39/preference_test
Viewer
•
Updated
•
29.6k
•
48
ryota39/preference_test_annotated
Viewer
•
Updated
•
5
•
25
ryota39/open_preference_v0.4
Viewer
•
Updated
•
202k
•
20
•
1
ryota39/webgpt_comparisons-ja
Viewer
•
Updated
•
17.4k
•
20
•
1
ryota39/synthetic-instruct-gptj-pairwise-ja
Viewer
•
Updated
•
33.1k
•
19
•
1
ryota39/self-rewarding_instruct_AIFT_M3_scored
Viewer
•
Updated
•
7.11k
•
38
ryota39/self-rewarding_instruct_AIFT_M2_scored
Viewer
•
Updated
•
7k
•
39
ryota39/self-rewarding_instruct_AIFT_M1_scored
Viewer
•
Updated
•
4k
•
46
ryota39/Synthetic-JP-Conversations-Magpie-Nemotron-4-10k_scored
Viewer
•
Updated
•
10.1k
•
35