Language Modeling on CodeParrot 16K
2.25PerplexitySHAREDLLM
Evaluation Results
| Method | Links | |
|---|---|---|
| SHAREDLLMBase Model=LLaMA-2, Supervised fine-tuning=true2026.03 | 2.25 | |
| Activation BeaconBase Model=LLaMA-2, Supervised fine-tuning=true2026.03 | 2.43 | |
| LongAlpaca-16KBase Model=LLaMA-2, Supervised fine-tuning=true2026.03 | 2.54 | |
| StreamingLLMBase Model=LLaMA-2, Supervised fine-tuning=true2026.03 | 2.6 | |
| SHAREDLLMBase Model=Mistral-7B, Supervised fine-tuning=true2026.03 | 2.68 | |
| Activation BeaconBase Model=Mistral-7B, Supervised fine-tuning=true2026.03 | 2.85 | |
| StreamingLLMBase Model=Mistral-7B, Supervised fine-tuning=true2026.03 | 3.05 | |
| LongAlpaca-16KBase Model=Mistral-7B, Supervised fine-tuning=true2026.03 | 3.21 |