List your company
ResearchFormerly WizWand

Dialogue Generation on UnNI

23.2Rouge-LXPERT-DeepSeek
17.937619.303820.6722.0362May 9, 2026
Updated 5mo ago

Evaluation results

MethodLinks
XPERT-DeepSeek#Params=570M, #Size=dim=2048 16 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0523.2
XPERT-OLMoE#Params=570M, #Size=dim=2048 16 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0522.6
XPERT-OLMoE#Params=480M, #Size=dim=2048 12 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0521.83
XPERT-OLMoE#Params=270M, #Size=dim=1024 16 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0521.55
XPERT-OLMoE#Params=391M, #Size=dim=2048 8 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0521.47
Distillation#Params=480M, #Size=dim=2048 12 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0521.47
XPERT-DeepSeek#Params=270M, #Size=dim=1024 16 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0521.33
Scratch#Params=480M, #Size=dim=2048 12 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0520.76
Distillation#Params=270M, #Size=dim=1024 16 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0520.5
XPERT-DeepSeek#Params=480M, #Size=dim=2048 12 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0520.48
Distillation#Params=570M, #Size=dim=2048 16 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0520.27
XPERT-DeepSeek#Params=391M, #Size=dim=2048 8 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0520.02
Scratch#Params=570M, #Size=dim=2048 16 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0519.67
Scratch#Params=270M, #Size=dim=1024 16 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0519.32
Scratch#Params=391M, #Size=dim=2048 8 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0518.16
Distillation#Params=391M, #Size=dim=2048 8 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0518.14