Train Sentence Transformers
Plugin Verified ActiveTrain or fine-tune sentence-transformers models across all three architectures: SentenceTransformer (bi-encoder embeddings), CrossEncoder (rerankers), and SparseEncoder (SPLADE). Covers loss selection, hard-negative mining, evaluators, distillation, LoRA, Matryoshka, and Hugging Face Hub publishing.
To provide a structured and comprehensive system for users to train or fine-tune sentence-transformers models across various architectures and techniques, simplifying complex ML workflows.
Features
- Supports SentenceTransformer, CrossEncoder, and SparseEncoder architectures
- Covers loss selection, hard-negative mining, and evaluators
- Includes guidance on LoRA, Matryoshka, and distillation
- Facilitates Hugging Face Hub publishing
- Provides production-ready example scripts and detailed references
Use Cases
- Training sentence-transformers for retrieval, similarity search, or clustering.
- Fine-tuning models for specific downstream tasks like classification or reranking.
- Implementing SPLADE models for sparse retrieval systems.
- Exploring advanced training techniques like LoRA or distillation.
Non-Goals
- Synthesizing training scripts from scratch without using provided templates.
- Replacing the core Hugging Face `transformers` or `sentence-transformers` libraries.
- Providing a GUI for model training.
Installation
First, add the marketplace
/plugin marketplace add huggingface/skills/plugin install train-sentence-transformers@huggingface-skillsQuality Score
VerifiedTrust Signals
Similar Extensions
Autoresearch Agent
100Autonomous experiment loop that optimizes any file by a measurable metric. 5 slash commands, 8 evaluators, configurable loop intervals (10min to monthly).
Unslop
100Make assistant output sound human. Strip AI-isms (sycophancy, stock vocab, hedging stacks, em-dash pileups), engineer burstiness, restore voice. Preserves code, URLs, and technical accuracy.
Ruflo Agentdb
97Substrate plugin for Ruflo memory: AgentDB controller bridge (15 agentdb_* MCP tools), RuVector ONNX embeddings (10 embeddings_* tools incl. RaBitQ 32x quantization), and WASM HNSW pattern router (3 ruvllm_hnsw_* tools)
Voltagent Data Ai
97Data engineering, ML, and AI specialists - data pipelines, machine learning, LLM architecture
Transformers Js
96Run state-of-the-art machine learning models directly in JavaScript/TypeScript for NLP, computer vision, audio processing, and multimodal tasks. Works in Node.js and browsers with WebGPU/WASM using Hugging Face models.