Camelidae-8×34B

Reported on 4 benchmarks across 2 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing4 results

Question AnsweringonPIQA
Accuracy· 2024-01-05
82.7
best: 90.1 (Unicorn 11B (fine-tuned))
Parameter-Efficient Sparsity Crafting from Dense to Mixture-of-Experts for Instruction Tuning on General Tasks arXiv:2401.02731
Common Sense ReasoningonWinoGrande
Accuracy· 2024-01-05
80.9
best: 96.1 (ST-MoE-32B 269B (fine-tuned))
Parameter-Efficient Sparsity Crafting from Dense to Mixture-of-Experts for Instruction Tuning on General Tasks arXiv:2401.02731
Common Sense ReasoningonARC (Challenge)
Accuracy· 2024-01-05
65.2
best: 96.4 (GPT-4 (few-shot, k=25))
Parameter-Efficient Sparsity Crafting from Dense to Mixture-of-Experts for Instruction Tuning on General Tasks arXiv:2401.02731
Common Sense ReasoningonARC (Easy)
Accuracy· 2024-01-05
86.2
best: 95.2 (ST-MoE-32B 269B (fine-tuned))
Parameter-Efficient Sparsity Crafting from Dense to Mixture-of-Experts for Instruction Tuning on General Tasks arXiv:2401.02731