Update README

README.md

@@ -9078,7 +9078,7 @@ Key Features:
 
 3. Compression-friendly: Achieves high-quality retrieval with embeddings as small as 128 bytes/vector using Matryoshka Representation Learning (MRL) and quantization-aware embedding training. **Please note that like our v1.5 model, the MRL for this model is 256 dimensions, and high-quality 128-byte compression is achieved via 4-bit quantization (e.g. using a [`pq256x4fs` fast-scan FAISS index](https://github.com/facebookresearch/faiss/wiki/The-index-factory#encodings) or using the [example code published alongside our 1.5 model](https://github.com/Snowflake-Labs/arctic-embed/blob/main/compressed_embeddings_examples/score_arctic_embed_m_v1dot5_with_quantization.ipynb)).**
 
-4. Drop-In Replacement: arctic-embed-l-v2.0 builds on BAAI/bge-m3-retromae](https://huggingface.co/BAAI/bge-m3-retromae) which allows direct drop-in inference replacement with any form of new libraries, kernels, inference engines etc. 
+4. Drop-In Replacement: arctic-embed-l-v2.0 builds on [BAAI/bge-m3-retromae](https://huggingface.co/BAAI/bge-m3-retromae) which allows direct drop-in inference replacement with any form of new libraries, kernels, inference engines etc. 
 
 5. Long Context Support: arctic-embed-l-v2.0 builds on [BAAI/bge-m3-retromae](https://huggingface.co/BAAI/bge-m3-retromae) which can support a context window of up to 8192 via the use of RoPE.