Drop-Upcycling
updated
9B • Updated • 110
9B • Updated • 111
19B • Updated • 107
9B • Updated • 111
9B • Updated • 108
0.4B • Updated • 110
0.4B • Updated • 108
0.4B • Updated • 112
0.4B • Updated • 117
9B • Updated • 101
19B • Updated • 116
0.4B • Updated • 111
9B • Updated • 101
0.4B • Updated • 108
• 1
2B • Updated • 121
0.2B • Updated • 123
4B • Updated • 102
14B • Updated • 124
llm-jp/Dense-btx-code-expert-152M
0.2B • Updated • 113
• 1
llm-jp/Dense-btx-english-expert-1.5B
2B • Updated • 109
llm-jp/Dense-btx-code-expert-1.5B
2B • Updated • 113
• 1
llm-jp/Dense-btx-japanese-expert-1.5B
2B • Updated • 212
• 1
llm-jp/Dense-btx-english-expert-152M
0.2B • Updated • 112
llm-jp/Dense-btx-japanese-expert-152M
0.2B • Updated • 155
Drop-Upcycling: Training Sparse Mixture of Experts with Partial
Re-initialization
Paper
• 2502.19261
• Published • 6
Text Generation
• 73B • Updated • 131
llm-jp/llm-jp-3-8x13b-instruct3
Text Generation
• 73B • Updated • 299
• 8
llm-jp/llm-jp-3-8x1.8b-instruct3
Text Generation
• 9B • Updated • 131
• 4
Text Generation
• 9B • Updated • 295
llm-jp/llm-jp-3-8x13b-instruct2
Text Generation
• 73B • Updated • 272
llm-jp/llm-jp-3-8x1.8b-instruct2
Text Generation
• 9B • Updated • 124
llm-jp/llm-jp-3.1-8x13b-instruct4
Text Generation
• 73B • Updated • 227
• 4
Text Generation
• 73B • Updated • 135