huggingface/sentence-transformers
State-of-the-Art Embeddings, Retrieval, and Reranking
https://skillcdn.ai/gh/huggingface/sentence-transformers내 AI에 이 주소를 연결하면 이 스킬들을 쓸 수 있어요. 연결 방법 보기
- 미확인
- 기본 브랜치
main - 커밋
4a3b5cd - 라이선스
Apache-2.0
저장소 둘러보기
스킬과 문서의 원문에서 찾습니다. 화면용 번역은 검색되지 않아요.
문서
- Base Model SelectionLeaderboards rotate every few months. Don't trust any hardcoded "best" pick. Discover current options live. Run both sort orders since most-downloaded surfaces proven options and trending surfaces re…skills/train-sentence-transformers/references/base_model_selection.md
- Dataset FormatsThis reference covers: how datasets map to losses, how to reshape data when it doesn't fit, and how to mine hard negatives.skills/train-sentence-transformers/references/dataset_formats.md
- Evaluators (Cross-Encoder)All cross-encoder evaluators live in sentence_transformers.cross_encoder.evaluation.skills/train-sentence-transformers/references/evaluators_cross_encoder.md
- Multi-Vector-Encoder EvaluatorsAll evaluators live in sentence_transformers.multi_vector_encoder.evaluation. They mirror the bi-encoder evaluators but use MaxSim scoring end-to-end.skills/train-sentence-transformers/references/evaluators_multi_vector_encoder.md
- Evaluators (Bi-Encoder)All bi-encoder evaluators live in sentence_transformers.sentence_transformer.evaluation.skills/train-sentence-transformers/references/evaluators_sentence_transformer.md
- Evaluators (Sparse Encoder)All sparse-encoder evaluators live in sentence_transformers.sparse_encoder.evaluation. They mirror the bi-encoder versions with a Sparse prefix and default to dot product similarity (cosine on sparse…skills/train-sentence-transformers/references/evaluators_sparse_encoder.md
- Hardware GuideTraining embedding models is memory-bound more often than compute-bound.skills/train-sentence-transformers/references/hardware_guide.md
- Hugging Face Jobs ExecutionRun training on Hugging Face's managed GPUs without provisioning any local infrastructure. The same training script runs locally and on Jobs. This reference covers only the Jobs-specific concerns.skills/train-sentence-transformers/references/hf_jobs_execution.md
- Cross-Encoder Losses (reranker)All losses live in sentence_transformers.cross_encoder.losses.skills/train-sentence-transformers/references/losses_cross_encoder.md
- Multi-Vector-Encoder Losses (ColBERT / late-interaction)All losses live in sentence_transformers.multi_vector_encoder.losses.skills/train-sentence-transformers/references/losses_multi_vector_encoder.md
- Bi-Encoder Losses (SentenceTransformer)All losses live in sentence_transformers.sentence_transformer.losses.skills/train-sentence-transformers/references/losses_sentence_transformer.md
- Sparse-Encoder Losses (SPLADE)All losses live in sentence_transformers.sparse_encoder.losses.skills/train-sentence-transformers/references/losses_sparse_encoder.md
- Model Architectures (SentenceTransformer)The SentenceTransformer class is a torch.nn.Sequential of modules. The common shape is Transformer + Pooling (+ optional Normalize / Dense), but four distinct architecture families are supported and…skills/train-sentence-transformers/references/model_architectures.md
- Prompts and InstructionsModern embedding models (E5, BGE, GTE, Qwen3-Embedding, Nomic, Instructor, etc.) use prompts / instructions at encode time (short prefixes like "query: ", "passage: ", or "Represent this sentence for…skills/train-sentence-transformers/references/prompts_and_instructions.md
- Training ArgumentsSentenceTransformerTrainingArguments, CrossEncoderTrainingArguments, and SparseEncoderTrainingArguments all inherit from Hugging Face's TrainingArguments, so 95% of the arguments are the same.skills/train-sentence-transformers/references/training_args.md
- TroubleshootingCommon failures in sentence-transformers training, with root causes and fixes. Organized by symptom.skills/train-sentence-transformers/references/troubleshooting.md