Drop-Upcycling
updated
9B • Updated • 96
9B • Updated • 121
19B • Updated • 128
9B • Updated • 135
9B • Updated • 130
0.4B • Updated • 139
0.4B • Updated • 124
0.4B • Updated • 142
0.4B • Updated • 142
9B • Updated • 128
19B • Updated • 142
0.4B • Updated • 132
9B • Updated • 130
0.4B • Updated • 135
• 1
2B • Updated • 93
0.2B • Updated • 98
4B • Updated • 92
14B • Updated • 118
llm-jp/Dense-btx-code-expert-152M
0.2B • Updated • 92
• 1
llm-jp/Dense-btx-english-expert-1.5B
2B • Updated • 88
llm-jp/Dense-btx-code-expert-1.5B
2B • Updated • 86
• 1
llm-jp/Dense-btx-japanese-expert-1.5B
2B • Updated • 152
• 1
llm-jp/Dense-btx-english-expert-152M
0.2B • Updated • 82
llm-jp/Dense-btx-japanese-expert-152M
0.2B • Updated • 130
Drop-Upcycling: Training Sparse Mixture of Experts with Partial
Re-initialization
Paper
• 2502.19261
• Published • 5
Text Generation
• 73B • Updated • 139
llm-jp/llm-jp-3-8x13b-instruct3
Text Generation
• 73B • Updated • 271
• 8
llm-jp/llm-jp-3-8x1.8b-instruct3
Text Generation
• 9B • Updated • 203
• 4
Text Generation
• 9B • Updated • 192
llm-jp/llm-jp-3-8x13b-instruct2
Text Generation
• 73B • Updated • 240
llm-jp/llm-jp-3-8x1.8b-instruct2
Text Generation
• 9B • Updated • 158
llm-jp/llm-jp-3.1-8x13b-instruct4
Text Generation
• 73B • Updated • 197
• 4
Text Generation
• 73B • Updated • 152