Update README.md

README.md

@@ -52,25 +52,33 @@ library_name: sentence-transformers
 
 
 ### 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.
 
-| Model | BEIR KaLM-Reranker-V1 | BEIR KaLM-Reranker-V1-R2 | Delta | MIRACL KaLM-Reranker-V1 | MIRACL KaLM-Reranker-V1-R2 | Delta |
-|:--|--:|--:|--:|--:|--:|--:|
-| Nano | 57.41 | **58.54** | **+1.13** | 62.08 | **71.11** | **+9.03** |
-| Small | 60.01 | **61.07** | **+1.06** | 66.89 | **74.06** | **+7.17** |
-| Large | 62.87 | **63.53** | **+0.66** | 70.07 | **74.92** | **+4.85** |
+#### BEIR — Multi-domain Reranking
+
+| Model | KaLM-Reranker-V1 | KaLM-Reranker-V1-R2 | Δ |
+|:--|--:|--:|--:|
+| Nano | 57.41 | **58.54** | **+1.13** |
+| Small | 60.01 | **61.07** | **+1.06** |
+| Large | 62.87 | **63.53** | **+0.66** |
+
+#### MIRACL — Multilingual Reranking
+
+| Model | KaLM-Reranker-V1 | KaLM-Reranker-V1-R2 | Δ |
+|:--|--:|--:|--:|
+| Nano | 62.08 | **71.11** | **+9.03** |
+| Small | 66.89 | **74.06** | **+7.17** |
+| Large | 70.07 | **74.92** | **+4.85** |
 
 | Capability | KaLM-Reranker-V1 | KaLM-Reranker-V1-R2 |
 |:--|:--|:--|
 | Validated MEP range | 1x-32x | **1x-128x** |
 | Test-time compute |  Flexible compression | **Flexible allocation of inference-time computation** |
-| Training | Original supervised checkpoints | **High-quality SFT -> soft-label distillation -> model soup** |
+| Training | Supervised checkpoints | **High-quality SFT -> soft-label distillation -> model soup** |
 | Multi-domain ranking | Strong | **Improved on BEIR for all three sizes** |
 | Multilingual ranking | Limited | **Substantially improved across MIRACL's 18 languages** |
 
 ## Model family
-
 | Model | Activated parameters | Layers (encoder + decoder) | Sequence length | Document token dimension | MEP support | Instruction aware |
 |:--|--:|--:|--:|--:|:--:|:--:|
 | [KaLM-Reranker-V1-Nano-R2](https://huggingface.co/KaLM-Embedding/KaLM-Reranker-V1-Nano-R2) | 0.27B | 18 + 18 | 128K | 640 | 1x-128x | Yes |
@@ -80,6 +88,22 @@ All results below use the same default compression ratio, `r=4`. KaLM-Reranker-V
 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
+```python
+ f"<Document>: {document}"
+
+```
+```python
+(
+    f"<bos><start_of_turn>user\n"
+    f"Judge whether the Document meets the requirements based on the Query and the Instruct provided. Note that the answer can only be \"yes\" or \"no\".\n\n"
+    f"<Instruct>: {task_instruction}\n"
+    f"<Query>: {query}<end_of_turn>\n"
+    f"<start_of_turn>model\n\n\n\n"
+)
+
+```
+
 
 # Acknowledgements
 We sincerely thank `jina-reranker-v3` and `Qwen3-Reranker` for their valuable inspiration and contributions to the reranking community, from which we have learned a lot.