List your company
ResearchFormerly WizWand

Dialogue Generation on Vicuna

15.05Rouge-LXPERT-OLMoE
12.928413.479214.0314.5808May 9, 2026
Updated 5mo ago

Evaluation results

MethodLinks
XPERT-OLMoE#Params=391M, #Size=dim=2048 8 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0515.05
XPERT-OLMoE#Params=480M, #Size=dim=2048 12 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0514.83
XPERT-OLMoE#Params=570M, #Size=dim=2048 16 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0514.57
XPERT-OLMoE#Params=270M, #Size=dim=1024 16 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0514.46
Distillation#Params=480M, #Size=dim=2048 12 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0514.39
XPERT-DeepSeek#Params=570M, #Size=dim=2048 16 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0514.37
Scratch#Params=391M, #Size=dim=2048 8 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0514.25
Scratch#Params=480M, #Size=dim=2048 12 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0514.2
Distillation#Params=570M, #Size=dim=2048 16 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0514.09
XPERT-DeepSeek#Params=391M, #Size=dim=2048 8 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0513.99
XPERT-DeepSeek#Params=480M, #Size=dim=2048 12 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0513.92
Scratch#Params=270M, #Size=dim=1024 16 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0513.77
Distillation#Params=270M, #Size=dim=1024 16 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0513.52
Scratch#Params=570M, #Size=dim=2048 16 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0513.42
XPERT-DeepSeek#Params=270M, #Size=dim=1024 16 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0513.25
Distillation#Params=391M, #Size=dim=2048 8 Layers, Pre-training Tokens=5B, Fine-tuning Dataset=Dolly2026.0513.01