train-sentence-transformers

原文涵盖的主题

• Train a sentence-transformers Model
• 1. Identify the model type
• 2. Required reading
• Per-type: always required
• Cross-cutting: always required (regardless of task)
• Cross-cutting: load when applicable
• Variant scripts (open when the task matches)
• 3. Defaults

This SKILL.md is a router, not a manual. It tells you which references and example scripts to load for your task. The actual content (recommended losses, evaluators, training-script structure, model selection, training-arg knobs, troubleshooting) lives in references/ and scripts/. Do not synthesize a training script from this file alone. Open the per-type production template (scripts/train example.py) and copy it as your starting point. The templates contain load-bearing scaffolding (autocast helper, model-card class, logger silencing list, force=True, seed, TF32, version-compatible imports, named-evaluator metric handling) that prior agent runs have repeatedly missed when rolling their own from a synthesized snippet. | Tag | Class | What it does | When to pick | |---|---|---|---| | [SentenceTransformer] | SentenceTransformer (bi-encoder) | Maps each input to a fixed-dim dense vector | Retrieval, similarity, clustering, classification, paraphrase mining, dedup | | [CrossEncoder] | CrossEncoder (reranker) | Scores (query, passage) pairs jointly | Two-stage retrieval (rerank top-100 from bi-encoder), pair classification | | [SparseEncoder] | SparseEncoder (SPLADE) | Sparse vectors ov

这里只展示节选，请以完整原文和当前要求为准。