Language Modeling on ProofPile 32K
3.21PerplexitySHAREDLLM
Evaluation Results
| Method | Links | |
|---|---|---|
| SHAREDLLMBase Model=LLaMA-2, Supervised fine-tuning=true2026.03 | 3.21 | |
| Activation BeaconBase Model=LLaMA-2, Supervised fine-tuning=true2026.03 | 3.32 | |
| SHAREDLLMBase Model=Mistral-7B, Supervised fine-tuning=true2026.03 | 3.49 | |
| StreamingLLMBase Model=LLaMA-2, Supervised fine-tuning=true2026.03 | 3.5 | |
| Activation BeaconBase Model=Mistral-7B, Supervised fine-tuning=true2026.03 | 3.69 | |
| StreamingLLMBase Model=Mistral-7B, Supervised fine-tuning=true2026.03 | 4.16 |