arxiv:2402.01680
Yaqi Wang
qiqiquq
AI & ML interests
None yet
Organizations
None yet
models
62
qiqiquq/GPTNeoX-160M-minipile-full
0.2B
•
Updated
qiqiquq/sft-dporanker-halfdata-1204-merged-16bit
Text Generation
•
7B
•
Updated
qiqiquq/sft-dporanker-checkpoint
Updated
qiqiquq/sft-reranker-step2000-1203
Text Generation
•
7B
•
Updated
•
8
qiqiquq/sft-reranker-step2000-1203-adapter
Updated
qiqiquq/sft-reranker-e1-1203
Text Generation
•
7B
•
Updated
•
2
qiqiquq/sft-reranker-1203
Updated
qiqiquq/dporanker-checkpoint
Updated
qiqiquq/dpo-rpo-ranker-halfdata-1202-merged-16bit
Text Generation
•
7B
•
Updated
•
2
qiqiquq/dporanker-halfdata-12020204-merged-16bit
Text Generation
•
7B
•
Updated
•
2