Drop-Upcycling
updated
9B • Updated • 93
9B • Updated • 118
19B • Updated • 131
9B • Updated • 138
9B • Updated • 131
0.4B • Updated • 142
0.4B • Updated • 120
0.4B • Updated • 144
0.4B • Updated • 146
9B • Updated • 130
19B • Updated • 143
0.4B • Updated • 136
9B • Updated • 131
0.4B • Updated • 137
• 1
2B • Updated • 90
0.2B • Updated • 93
4B • Updated • 88
14B • Updated • 114
llm-jp/Dense-btx-code-expert-152M
0.2B • Updated • 85
• 1
llm-jp/Dense-btx-english-expert-1.5B
2B • Updated • 83
llm-jp/Dense-btx-code-expert-1.5B
2B • Updated • 80
• 1
llm-jp/Dense-btx-japanese-expert-1.5B
2B • Updated • 150
• 1
llm-jp/Dense-btx-english-expert-152M
0.2B • Updated • 77
llm-jp/Dense-btx-japanese-expert-152M
0.2B • Updated • 127
Drop-Upcycling: Training Sparse Mixture of Experts with Partial
Re-initialization
Paper
• 2502.19261
• Published • 5
Text Generation
• 73B • Updated • 138
llm-jp/llm-jp-3-8x13b-instruct3
Text Generation
• 73B • Updated • 282
• 8
llm-jp/llm-jp-3-8x1.8b-instruct3
Text Generation
• 9B • Updated • 200
• 4
Text Generation
• 9B • Updated • 268
llm-jp/llm-jp-3-8x13b-instruct2
Text Generation
• 73B • Updated • 244
llm-jp/llm-jp-3-8x1.8b-instruct2
Text Generation
• 9B • Updated • 161
llm-jp/llm-jp-3.1-8x13b-instruct4
Text Generation
• 73B • Updated • 186
• 4
Text Generation
• 73B • Updated • 156