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 PRO
ryota39
AI & ML interests
LLM × RL
Recent Activity
new activity
about 14 hours ago
microsoft/ms_marco:License
updated
a dataset
1 day ago
preference-team/dataset-for-annotation-v2-annotated
updated
a dataset
1 day ago
preference-team/progress
Organizations
Collections
7
spaces
2
models
17
ryota39/gemma-2-2b-jpn-it-q8
Updated
•
22
ryota39/Tora-12B
Text Generation
•
Updated
•
12
•
1
ryota39/Tora-7B-v0.1
Text Generation
•
Updated
•
28
•
2
ryota39/mluke-large-lite-reward
Text Classification
•
Updated
•
92
ryota39/retriva-bert-preference-classifier
Text Classification
•
Updated
•
160
ryota39/Tora-7B-v0.2
Text Generation
•
Updated
•
13
•
1
ryota39/llm-jp-1b-sft-100k-LoRA-dpo-12k
Text Generation
•
Updated
•
93
ryota39/Phi-3-mini-4k-instruct-dpo
Text Generation
•
Updated
•
157
•
3
ryota39/llm-jp-1b-sft-15k
Text Generation
•
Updated
•
88
ryota39/llm-jp-1b-sft-100k-LoRA
Text Generation
•
Updated
•
18
datasets
29
ryota39/test
Viewer
•
Updated
•
5
•
45
ryota39/wild_chat_ja
Viewer
•
Updated
•
3.49k
•
87
ryota39/aya-evol-instruct
Viewer
•
Updated
•
29.2k
•
63
ryota39/JCommonsenseMorality
Viewer
•
Updated
•
9.98k
•
101
ryota39/hh-rlhf
Viewer
•
Updated
•
169k
•
71
ryota39/preference-en-ja-100k
Viewer
•
Updated
•
101k
•
69
•
1
ryota39/preference_test
Viewer
•
Updated
•
29.6k
•
65
ryota39/preference_test_annotated
Viewer
•
Updated
•
5
•
60
ryota39/open_preference_v0.4
Viewer
•
Updated
•
202k
•
74
•
1
ryota39/webgpt_comparisons-ja
Viewer
•
Updated
•
17.4k
•
63
•
1