Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Language Modeling on WikiText-2, C4, and PTB Average
Loading...
26.68
Average Perplexity
Shortened LLaMA + Ghost Layer
22.2216
52.3158
82.41
112.5042
May 15, 2026
Average Perplexity
Updated 16d ago
Evaluation Results
Method
Method
Links
Average Perplexity
Shortened LLaMA + Ghost Layer
Model=LLaMA-3-8B, Prun...
2026.05
26.68
Shortened LLaMA + Ghost Layer
Model=DeepSeek-R1-Dist...
2026.05
39.8
LLM-Streamline + Ghost Layer
Model=LLaMA-3-8B, Prun...
2026.05
76.76
ShortGPT + Ghost Layer
Model=LLaMA-3-8B, Prun...
2026.05
87.61
LLM-Streamline + Ghost Layer
Model=DeepSeek-R1-Dist...
2026.05
124
ShortGPT + Ghost Layer
Model=DeepSeek-R1-Dist...
2026.05
138.14
Feedback
Search any
task
Search any
task