List your company
ResearchFormerly WizWand

Dialogue Generation on DollyEval

24.19ROUGE-LXPERT-OLMoE
21.194821.972422.7523.5276May 9, 2026
Updated 5mo ago

Evaluation results

MethodLinks
XPERT-OLMoE#Params=570M, #Size=dim=2048 16 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0524.19
XPERT-OLMoE#Params=270M, #Size=dim=1024 16 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0523.67
XPERT-DeepSeek#Params=570M, #Size=dim=2048 16 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0523.42
XPERT-DeepSeek#Params=480M, #Size=dim=2048 12 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0523.38
XPERT-OLMoE#Params=480M, #Size=dim=2048 12 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0523.36
XPERT-DeepSeek#Params=391M, #Size=dim=2048 8 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0523.35
XPERT-DeepSeek#Params=270M, #Size=dim=1024 16 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0523.22
XPERT-OLMoE#Params=391M, #Size=dim=2048 8 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0523.17
Scratch#Params=391M, #Size=dim=2048 8 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0522.94
Distillation#Params=480M, #Size=dim=2048 12 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0522.9
Scratch#Params=570M, #Size=dim=2048 16 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0522.86
Distillation#Params=391M, #Size=dim=2048 8 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0522.78
Scratch#Params=480M, #Size=dim=2048 12 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0522.48
Distillation#Params=270M, #Size=dim=1024 16 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0522.43
Distillation#Params=570M, #Size=dim=2048 16 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0522.09
Scratch#Params=270M, #Size=dim=1024 16 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0521.31