Language Modeling on CodeParrot 100K
2.36PerplexitySHAREDLLM
Evaluation results
| Method | Links | |
|---|---|---|
| SHAREDLLMBase Model=LLaMA-2, Supervised fine-tuning=true2026.03 | 2.36 | |
| StreamingLLMBase Model=LLaMA-2, Supervised fine-tuning=true2026.03 | 2.56 | |
| Activation BeaconBase Model=LLaMA-2, Supervised fine-tuning=true2026.03 | 2.62 | |
| SHAREDLLMBase Model=Mistral-7B, Supervised fine-tuning=true2026.03 | 2.76 | |
| Activation BeaconBase Model=Mistral-7B, Supervised fine-tuning=true2026.03 | 2.92 | |
| StreamingLLMBase Model=Mistral-7B, Supervised fine-tuning=true2026.03 | 3.02 |