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
liked
a model
about 21 hours ago
Qwen/Qwen3-8B
liked
a model
about 21 hours ago
Qwen/Qwen3-4B
liked
a model
about 23 hours ago
gaotang/RM-R1-Qwen2.5-Instruct-7B
Organizations
Collections
7
spaces
2
models
17
ryota39/gemma-2-2b-jpn-it-q8
Updated
•
1
ryota39/Tora-12B
Text Generation
•
Updated
•
3
•
1
ryota39/Tora-7B-v0.1
Text Generation
•
Updated
•
6
•
2
ryota39/mluke-large-lite-reward
Text Classification
•
Updated
ryota39/retriva-bert-preference-classifier
Text Classification
•
Updated
ryota39/Tora-7B-v0.2
Text Generation
•
Updated
•
8
•
1
ryota39/llm-jp-1b-sft-100k-LoRA-dpo-12k
Text Generation
•
Updated
•
6
ryota39/Phi-3-mini-4k-instruct-dpo
Text Generation
•
Updated
•
6
•
3
ryota39/llm-jp-1b-sft-15k
Text Generation
•
Updated
•
2
ryota39/llm-jp-1b-sft-100k-LoRA
Text Generation
•
Updated
•
4
datasets
32
ryota39/reviews_and_summaries2
Viewer
•
Updated
•
50
•
104
ryota39/reviews_and_summaries
Viewer
•
Updated
•
50
•
94
ryota39/movie_reviews_local
Viewer
•
Updated
•
50
•
118
ryota39/movie_reviews
Viewer
•
Updated
•
50
•
104
ryota39/wild_chat_ja
Viewer
•
Updated
•
3.49k
•
18
ryota39/aya-evol-instruct
Viewer
•
Updated
•
29.2k
•
24
ryota39/JCommonsenseMorality
Viewer
•
Updated
•
9.98k
•
19
ryota39/hh-rlhf
Viewer
•
Updated
•
169k
•
9
ryota39/preference-en-ja-100k
Viewer
•
Updated
•
101k
•
25
•
1
ryota39/preference_test
Viewer
•
Updated
•
29.6k
•
15