SkillRouter-Embedding-0.6B

Model overview

pipizhao publishes SkillRouter-Embedding-0.6B as a feature-extraction model. Captured config identifies Qwen3Model with a qwen3 model type, and Safetensors metadata reports 595,776,512 parameters. Card data records apache-2.0. Hub tags include embedding, retrieval, skill-routing, and Qwen/Qwen3-Embedding-0.6B as base model and finetune.

Recorded capabilities

Use cases in the source record

• First-stage retrieval of skills, tools, or plugin documents from a registry before reranking, as described on the model card.
• Cosine-similarity search over L2-normalized dense embeddings, according to the publisher model summary.

Limitations and unknowns

• No independent evaluation scores were extracted as Ethen-verified results. Benchmark improvement language in the card remains a publisher claim.
• Provider state is historical snapshot data, not independently refreshed current availability.
• Embedding format, 80K-skill routing scope, and Qwen3-Embedding-0.6B fine-tune details come from the publisher model card and have not been independently verified by Ethen.

Source and provenance

Source: pipizhao/SkillRouter-Embedding-0.6B

Captured: Unknown. Processed: 2026-09-07T19:36:00.519387+00:00.

SR-Emb-0.6B SR-Emb-0.6B is a compact embedding model for skill retrieval in large LLM-agent skill registries. It is the encoder used in the SkillRouter retrieve-and-rerank pipeline and is fine-tuned from Qwen/Qwen3-Embedding-0.6B for full-text skill routing over approximately 80K skills. Model Summary Base model: Qwen/Qwen3-Embedding-0.6B Architecture: bi-encoder / dual-encoder retrieval model Input: Query: task description with an instruction prefix Document: full skill text formatted as name | description | body Output: L2-normalized dense embeddings for cosine similarity search Intended use: first-stage retrieval in a two-stage s…