embedding-training

embedding-training is a Fine-tuning & training data skill for AI agents, published by ProfSynapse in the Synaptic-Tuner repository on GitHub. Skillspace rates embedding-training F (45/100) and the safety scan rated it risky; the rating is based on static analysis only.

Risky. This skill has patterns associated with unsafe behaviour. Read the source carefully before running it.

Complete reference for the embedding fine-tuning pipeline (SentenceTransformers bi-encoders) — the `embedding` training method, model registry, dual loader (Unsloth fast path + ST fallback), adapter modes (full/lora/frozen_head), triplet/pairs dataset format, retrieval evaluation (recall@k/MRR/nDCG/MAP via the `retrieval` verifier), and the local-Docker smoke recipe. Use when training a retrieval embedder, picking a base model + adapter mode, preparing triplet data, or evaluating a fine-tuned embedder against a labeled corpus. This skill is about USING the embedding pipeline via CLI and YAML — never modifying source code.

Grade

F

Quality

45 / 100

Safety

Risky

GitHub stars

26

Unproven: rated by static analysis only, not yet compared head-to-head.

Our two independent classifiers differ on this skill's category, so treat the placement as provisional.

This rating describes the version of the repository we crawled; it may have changed since.

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.