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
updated
a dataset
about 3 hours ago
preference-team/dataset-for-annotation-v2-annotated
updated
a dataset
about 3 hours ago
preference-team/progress
liked
a dataset
about 23 hours ago
nvidia/HelpSteer3
Organizations
Collections
7
spaces
2
models
18

ryota39/compact-coder-3b
Text Generation
•
Updated
•
7

ryota39/gemma-2-2b-jpn-it-q8
Updated
•
25

ryota39/Tora-12B
Text Generation
•
Updated
•
10
•
1

ryota39/Tora-7B-v0.1
Text Generation
•
Updated
•
16
•
2

ryota39/mluke-large-lite-reward
Text Classification
•
Updated
•
7

ryota39/retriva-bert-preference-classifier
Text Classification
•
Updated
•
9

ryota39/Tora-7B-v0.2
Text Generation
•
Updated
•
6
•
1

ryota39/llm-jp-1b-sft-100k-LoRA-dpo-12k
Text Generation
•
Updated
•
11

ryota39/Phi-3-mini-4k-instruct-dpo
Text Generation
•
Updated
•
56
•
3

ryota39/llm-jp-1b-sft-15k
Text Generation
•
Updated
•
46
datasets
28
ryota39/wild_chat_ja
Viewer
•
Updated
•
3.49k
•
46
ryota39/aya-evol-instruct
Viewer
•
Updated
•
29.2k
•
61
ryota39/JCommonsenseMorality
Viewer
•
Updated
•
9.98k
•
95
ryota39/hh-rlhf
Viewer
•
Updated
•
169k
•
65
ryota39/preference-en-ja-100k
Viewer
•
Updated
•
101k
•
65
•
1
ryota39/preference_test
Viewer
•
Updated
•
29.6k
•
47
ryota39/preference_test_annotated
Viewer
•
Updated
•
5
•
65
ryota39/open_preference_v0.4
Viewer
•
Updated
•
202k
•
85
•
1
ryota39/webgpt_comparisons-ja
Viewer
•
Updated
•
17.4k
•
72
•
1
ryota39/synthetic-instruct-gptj-pairwise-ja
Viewer
•
Updated
•
33.1k
•
78
•
1