Model card: drop training details from the introduction

README.md

@@ -21,9 +21,7 @@ language:
 A bi-encoder for **agent-skill retrieval**: given a task description, embed it and
 the skill documents into one space so the relevant skills come back by nearest
 neighbour. Fine-tuned from
-[Qwen/Qwen3-Embedding-0.6B](https://huggingface.co/Qwen/Qwen3-Embedding-0.6B)
-with an in-batch InfoNCE loss on LLM-written task requests, each paired with a
-section of its skill and contrasted with mined hard negatives.
+[Qwen/Qwen3-Embedding-0.6B](https://huggingface.co/Qwen/Qwen3-Embedding-0.6B).
 
 This is the encoder of SkillRep, where it is combined with query-side and
 document-side expansion, background projection and a BM25 channel. It indexes a