Language Modeling on PG19 100K
8.24PerplexitySHAREDLLM
Evaluation results
| Method | Links | |
|---|---|---|
| SHAREDLLMBase Model=LLaMA-2, Supervised fine-tuning=true2026.03 | 8.24 | |
| Activation BeaconBase Model=LLaMA-2, Supervised fine-tuning=true2026.03 | 8.5 | |
| SHAREDLLMBase Model=Mistral-7B, Supervised fine-tuning=true2026.03 | 9.05 | |
| StreamingLLMBase Model=LLaMA-2, Supervised fine-tuning=true2026.03 | 9.32 | |
| Activation BeaconBase Model=Mistral-7B, Supervised fine-tuning=true2026.03 | 9.48 | |
| StreamingLLMBase Model=Mistral-7B, Supervised fine-tuning=true2026.03 | 9.55 |