List your company
ResearchFormerly WizWand

Dialogue Generation on S-NI

19.82Rouge-LXPERT-OLMoE
14.46415.854517.24518.6355May 9, 2026
Updated 5mo ago

Evaluation results

MethodLinks
XPERT-OLMoE#Params=570M, #Size=dim=2048 16 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0519.82
XPERT-OLMoE#Params=480M, #Size=dim=2048 12 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0519.43
XPERT-DeepSeek#Params=480M, #Size=dim=2048 12 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0518.01
XPERT-DeepSeek#Params=570M, #Size=dim=2048 16 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0517.99
XPERT-OLMoE#Params=391M, #Size=dim=2048 8 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0517.39
XPERT-DeepSeek#Params=391M, #Size=dim=2048 8 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0517.34
Distillation#Params=391M, #Size=dim=2048 8 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0516.63
XPERT-OLMoE#Params=270M, #Size=dim=1024 16 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0516.58
Scratch#Params=480M, #Size=dim=2048 12 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0516.57
Distillation#Params=570M, #Size=dim=2048 16 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0516.06
Distillation#Params=480M, #Size=dim=2048 12 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0515.7
Scratch#Params=391M, #Size=dim=2048 8 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0515.69
Scratch#Params=570M, #Size=dim=2048 16 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0515.61
XPERT-DeepSeek#Params=270M, #Size=dim=1024 16 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0515.2
Distillation#Params=270M, #Size=dim=1024 16 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0515
Scratch#Params=270M, #Size=dim=1024 16 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0514.67