📊 Showing 4 results | 📏 Metric: Average Score
Rank | Model | Paper | Average Score | Date | Code |
---|---|---|---|---|---|
1 | GALI(Llama3-8b-ins-4k-to-16k) | A Training-Free Length Extrapolation Approach for LLMs: Greedy Attention Logit Interpolation (GALI) | 59.21 | 2025-02-04 | 📦 academycityl/gali |
2 | GALI(Llama3-8b-ins-4k-to-32k) | A Training-Free Length Extrapolation Approach for LLMs: Greedy Attention Logit Interpolation (GALI) | 59.10 | 2025-02-04 | 📦 academycityl/gali |
3 | GALI(Llama3-8b-ins-8k-to-32k) | A Training-Free Length Extrapolation Approach for LLMs: Greedy Attention Logit Interpolation (GALI) | 42.79 | 2025-02-04 | 📦 academycityl/gali |
4 | GALI(Llama3-8b-ins-8k-to-16k) | A Training-Free Length Extrapolation Approach for LLMs: Greedy Attention Logit Interpolation (GALI) | 42.32 | 2025-02-04 | 📦 academycityl/gali |