Trim README

README.md

@@ -47,10 +47,9 @@ Models Are Secretly Powerful Text Encoders**.
 
 ### Usage
 
-This is a [sentence-transformers](https://www.sbert.net/) model. The LLM2Vec
-adapters have been merged into the base model, so you no longer need the
-`llm2vec` package or multi-stage adapter loading — it loads directly. The
-bidirectional encoder and the LLM2Vec instruction-aware mean pooling are
+This is a [sentence-transformers](https://www.sbert.net/) model — it loads
+directly and needs no packages beyond `sentence-transformers`. The
+bidirectional Llama encoder and the LLM2Vec instruction-aware mean pooling are
 provided by small custom modules in this repo, loaded via `trust_remote_code`.
 
 ```bash
@@ -117,6 +116,5 @@ Approximate memory footprint: **bfloat16 ≈ 14 GB**, **8-bit ≈ 8 GB**,
 
 ### Credits
 
-Approach from **LLM2Vec** (McGill-NLP). The original instruction-based usage
-was adapted from
-https://huggingface.co/McGill-NLP/LLM2Vec-Meta-Llama-3-8B-Instruct-mntp-supervised.
+Approach from **LLM2Vec** (McGill-NLP). Related model:
+https://huggingface.co/McGill-NLP/LLM2Vec-Meta-Llama-3-8B-Instruct-mntp-supervised