Update README.md
Browse files
README.md
CHANGED
|
@@ -43,3 +43,12 @@ We instantiate KaLM-Reranker-V1 in three sizes, `Nano`, `Small`, and `Large`, wi
|
|
| 43 |
|
| 44 |
Extensive experiments on BEIR, MIRACL, and LMEB show that the KaLM-Reranker-V1 series achieves competitive reranking performance compared with strong industrial rerankers while significantly reducing online overhead.
|
| 45 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 43 |
|
| 44 |
Extensive experiments on BEIR, MIRACL, and LMEB show that the KaLM-Reranker-V1 series achieves competitive reranking performance compared with strong industrial rerankers while significantly reducing online overhead.
|
| 45 |
|
| 46 |
+
# Model Details
|
| 47 |
+
|
| 48 |
+
# The KaLM series model specifications
|
| 49 |
+
| Models | Activated Params. | Non-Embedding Params. | Embedding Params. | #Layers | Sequence Length | Document Token Dim. | MEP Support | Instruction Aware |
|
| 50 |
+
| ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- | ---- |
|
| 51 |
+
| [KaLM-Reranker-V1-Nano](https://huggingface.co/KaLM-Embedding/KaLM-Reranker-V1-Nano) | 0.27B | 100M | 168M | 18 | 128K | 640 | 1x-32x | Yes |
|
| 52 |
+
| [KaLM-Reranker-V1-Small](https://huggingface.co/KaLM-Embedding/KaLM-Reranker-V1-Small) | 1B | 698M | 302M | 26 | 128K | 1152 | 1x-32x | Yes |
|
| 53 |
+
| [KaLM-Reranker-V1-Large](https://huggingface.co/KaLM-Embedding/KaLM-Reranker-V1-Large) | 4B | 3209M | 675M | 34 | 128K | 2560 | 1x-32x | Yes |
|
| 54 |
+
|