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
updated
a dataset
about 5 hours ago
preference-team/dataset-for-annotation-v2-annotated
updated
a dataset
about 5 hours ago
preference-team/progress
updated
a dataset
3 days ago
preference-team/dataset-for-annotation-v2-resume
Organizations
Collections
7
models
18
ryota39/test
Text Generation
•
Updated
•
36
ryota39/Tora-12B
Text Generation
•
Updated
•
16
•
1
ryota39/Tora-7B-v0.1
Text Generation
•
Updated
•
20
•
2
ryota39/mluke-large-lite-reward
Text Classification
•
Updated
•
18
ryota39/bge-m3-preference-classifier
Text Classification
•
Updated
•
11
ryota39/retriva-bert-preference-classifier
Text Classification
•
Updated
•
5
ryota39/Tora-7B-v0.2
Text Generation
•
Updated
•
25
•
1
ryota39/llm-jp-1b-sft-100k-LoRA-dpo-12k
Text Generation
•
Updated
•
21
ryota39/Phi-3-mini-4k-instruct-dpo
Text Generation
•
Updated
•
17
•
3
ryota39/llm-jp-1b-sft-15k
Text Generation
•
Updated
•
24
datasets
27
ryota39/JCommonsenseMorality
Viewer
•
Updated
•
9.98k
•
9
ryota39/hh-rlhf
Viewer
•
Updated
•
169k
•
49
ryota39/preference-en-ja-100k
Viewer
•
Updated
•
101k
•
31
•
1
ryota39/preference_test
Viewer
•
Updated
•
29.6k
•
30
ryota39/preference_test_annotated
Viewer
•
Updated
•
5
•
31
ryota39/open_preference_v0.4
Viewer
•
Updated
•
202k
•
32
•
1
ryota39/webgpt_comparisons-ja
Viewer
•
Updated
•
17.4k
•
34
•
1
ryota39/synthetic-instruct-gptj-pairwise-ja
Viewer
•
Updated
•
33.1k
•
37
•
1
ryota39/self-rewarding_instruct_AIFT_M3_scored
Viewer
•
Updated
•
7.11k
•
30
ryota39/self-rewarding_instruct_AIFT_M2_scored
Viewer
•
Updated
•
7k
•
30