Update README.md

README.md

@@ -172,7 +172,6 @@ For all benchmarks, we used [LM Eval Harness](https://github.com/EleutherAI/lm-e
 | Llama 3.1 Base | 65.3 | 20.4 | 58.9 | 85.8 | 46.4 | 84.2 | 75.2 | **92.0** | **32.3** | 56.8 | 81.9 | 79.4 | **74.7** | 33.3 | 66.4 | 65.5 | 45.8 | 82.9 | 74.4 | 83.5 |
 | OLMo 2 Base | 64.9 | 17.4 | 60.7 | 85.0 | 44.4 | 85.5 | 75.4 | 89.0 | 26.8 | **67.6** | 81.7 | 80.5 | 73.1 | 30.6 | 63.9 | 61.9 | **46.2** | 82.5 | 74.3 | **86.1** |
 | MAP NEO 7B | 59.5 | **23.0** | 52.0 | 81.1 | 42.4 | 84.7 | **81.7** | 82.0 | 27.8 | 48.0 | 73.3 | 72.5 | 64.6 | 25.2 | 58.2 | 56.4 | 39.4 | 79.0 | 66.1 | 73.3 |
-| Amber 7B | 48.1 | 19.1 | 41.6 | 74.7 | 31.6 | 68.8 | 20.6 | 87.0 | 26.3 | 4.4 | 73.9 | 72.4 | 66.8 | 11.6 | 26.6 | 26.7 | 39.2 | 79.8 | 65.3 | 76.9 |
 
 Marin 8B Base fares well on most of these tasks.