Update README.md

README.md

@@ -51,6 +51,7 @@ library_name: sentence-transformers
 
 ![kalm-reranker-v1-r2 architecture](./assets/framework.jpg)
 
+![kalm-reranker-v1-r2 training](./assets/training.jpg)
 
 | Capability | KaLM-Reranker-V1 | KaLM-Reranker-V1-R2 |
 |:--|:--|:--|
@@ -60,7 +61,6 @@ library_name: sentence-transformers
 | Multi-domain ranking | Strong | **Improved on BEIR for all three sizes** |
 | Multilingual ranking | Limited | **Substantially improved across MIRACL's 18 languages** |
 
-![kalm-reranker-v1-r2 training](./assets/training.jpg)
 
 ### KaLM-Reranker-V1-R2 vs. the original KaLM-Reranker-V1
 All results below use the same default compression ratio, `r=4`. KaLM-Reranker-V1 results are taken from the previous model cards; KaLM-Reranker-V1-R2 results are from the updated paper.
@@ -109,19 +109,20 @@ All results below use the same default compression ratio, `r=4`. KaLM-Reranker-V
 | **KaLM-Reranker-V1-Large-R2** | **75.12** | **74.92** | **74.50** | **73.85** | **73.26** | **72.46** | **71.97** |
 | **Delta** | **+4.82** | **+4.85** | **+4.87** | **+5.60** | **+7.32** | — | — |
 
-R2 consistently outperforms V1 at every shared compression ratio. The gains increase as compression becomes more aggressive, demonstrating substantially improved compression robustness.
+KaLM-Reranker-V1-R2 consistently outperforms KaLM-Reranker-V1 at every shared compression ratio. The gains increase as compression becomes more aggressive, demonstrating substantially improved compression robustness.
 
 
 
 ### Model family
 
+The reported sizes are **activated parameters**. Nano, Small, and Large are initialized from the T5Gemma2 270M-270M, 1B-1B, and 4B-4B encoder-decoder families, respectively.
+
 | Models                                                                                       | Activated Params. | Non-Embedding Params. | Embedding Params. | #Layers (encoder + decoder) | Sequence Length | Document Token Dim. | MEP Support | Instruction Aware | Test-Time Compute |
 | -------------------------------------------------------------------------------------------------  | -----------------: | --------------------: | ----------------: | --------------------------: | --------------: | ------------------: | ----------: | ----------------: | ----------------: |
 | [KaLM-Reranker-V1-Nano-R2](https://huggingface.co/KaLM-Embedding/KaLM-Reranker-V1-Nano-R2)   | 0.27B              | 100M                  | 168M              | 18+18                       | 128K            | 640                 | 1x-128x     | Yes               | Yes               |
 | [KaLM-Reranker-V1-Small-R2](https://huggingface.co/KaLM-Embedding/KaLM-Reranker-V1-Small-R2) | 1B                 | 698M                  | 302M              | 26+26                       | 128K            | 1152                | 1x-128x     | Yes               | Yes               |
 | [KaLM-Reranker-V1-Large-R2](https://huggingface.co/KaLM-Embedding/KaLM-Reranker-V1-Large-R2) | 4B                 | 3209M                 | 675M              | 34+34                       | 128K            | 2560                | 1x-128x     | Yes               | Yes               |
 
-The reported sizes are **activated parameters**. Nano, Small, and Large are initialized from the T5Gemma2 270M-270M, 1B-1B, and 4B-4B encoder-decoder families, respectively.
 
 
 ### Prompt Template