Update README.md

README.md

@@ -115,6 +115,14 @@ F2LLM-v2 is fully open. We release base models in 5 sizes, instruct models in 8
 | 8B    | [🤗F2LLM-v2-8B-Preview](https://huggingface.co/codefuse-ai/F2LLM-v2-8B-Preview)     | [🤗F2LLM-v2-8B](https://huggingface.co/codefuse-ai/F2LLM-v2-8B)     |
 | 14B   | [🤗F2LLM-v2-14B-Preview](https://huggingface.co/codefuse-ai/F2LLM-v2-14B-Preview)   | [🤗F2LLM-v2-14B](https://huggingface.co/codefuse-ai/F2LLM-v2-14B)   |
 
+## Performance
+
+The F2LLM-v2 family set a new state-of-the-art on a wide range of MTEB benchmarks, including Code, European, Scandinavian, German, French, Spanish, Polish, Dutch, Japanese, Vietnamese, Thai, Indic, Persian, among others.
+
+<img src="img/performance.png" width="100%" alt="Performance">
+
+For details, refer to the [MTEB leaderboard](https://huggingface.co/spaces/mteb/leaderboard).
+
 ## Usage
 
 ### With Sentence Transformers
@@ -199,6 +207,21 @@ In general, for retrieval and reranking tasks:
 
 For symmetric tasks such as STS, clustering, and bitext mining, you can encode the documents either with or without prompts. The model is trained to support both scenarios.
 
+### MRL Support
+
+This model is trained with Matryoshka Representation Learning (MRL), allowing for a superior tradeoff between performance and embedding size. You can truncate the embeddings to keep only the first `d` dimensions to reduce storage and speed up vector search in downstream systems. The model is trained with a smallest Matryoshka dimension of 8.
+
+<img src="img/mrl.png" width="80%" alt="MRL results">
+
+Example:
+```python
+embedding = embedding[..., :128]
+embedding = torch.nn.functional.normalize(embedding, p=2, dim=-1)
+```
+> Note: you need to apply normalization **after** trucation, not the other way around.
+
+If you are using sentence transformer, you can also simply pass `truncate_dim=128` to the encode interface.
+
 ## Intermediate Checkpoints
 
 To facilitate future research, we release intermediate checkpoints in the `intermediate_checkpoints` branch.