The request "set-encoder-base" names no product, so the closest matches are encoder and sentence-embedding tooling: Sentence Transformers (SBERT) is the go-to Python module for computing embeddings and training embedding models 4, and Hugging Face Transformers offers a skill to train or fine-tune sentence-transformers models 1020. The request is ambiguous about what "set encoder base" should configure, so a clarifying question is included.
A question back: Which encoder base do you mean: a model to load as the base for fine-tuning, or a configuration setting in a specific framework or product?
- 1
Sentence Transformers (SBERT)sbert.netverified and signed
Python module for computing embeddings from text, images, audio or video and for training embedding and reranker encoder models 414.
official:SDK · sentence-transformers+24 community tools built for it
for agents: embedding · deep · XLNet
- 2
Hugging Face Transformershuggingface.coverified and signed
Provides a transformers SDK and a train-sentence-transformers skill that trains or fine-tunes sentence-transformers encoder models 1020.
official:SDK · transformersskill · train-sentence-transformersskill · transformers-js+13 community tools built for it
for agents: train-sentence-transformers · inference · python
- 3
Sources
- 2Mistral | #1 in Sovereign AI: Frontier Open Models You Ownmistral.ai · read 2026-10-30
- 4SentenceTransformers Documentation — Sentence Transformers documentationsbert.net · read 2026-10-29
- 10Hugging Face – The AI community building the future.huggingface.co · read 2026-10-29
- 12mistral-vibe: declares "llm" (the record we read and signed)unfragile.ai · read 2026-10-24
- 14sentence-transformers: declares "embedding" (the record we read and signed)unfragile.ai · read 2026-10-24
- 20train-sentence-transformers: declares "train-sentence-transformers" (the record we read and signed)unfragile.ai · read 2026-10-24
For agents: the 10 actions behind this answer
build-perf-baseline · build-perf-baseline verified and signed
Establish MSBuild/.NET build performance baselines before optimizing. USE FOR: unranked slow builds; cold, warm, incremental or no-op measurements; before/after comparisons; CI output caching; static graph, artifacts output and dependency graph trimming. Start here before build-perf-diagnostics, inc
llm · mistral-vibe verified and signed
acquire-codebase-knowledge · acquire-codebase-knowledge verified and signed
Use this skill when the user explicitly asks to map, document, or onboard into an existing codebase. Trigger for prompts like "map this codebase", "document this architecture", "onboard me to this repo", or "create codebase docs". Do not trigger for routine feature implementation, bug fixes, or narr
embedding · sentence-transformers verified and signed
cloudflare-images-base-image · Cloudflare API verified and signed
Download image
python · fastcore verified and signed
tao-train-mask-auto-encoder · tao-train-mask-auto-encoder verified and signed
Masked Auto-Encoder (MAE) for self-supervised pretraining and fine-tuning. Masks random patches and reconstructs them to learn visual representations; supports pretrain and finetune stages. Use when training, evaluating, exporting, or running inference for a TAO MAE backbone. Trigger phrases include
createAppsV1NamespacedReplicaSet · Kubernetes verified and signed
create a ReplicaSet
airtable_create_base · Airtable (Activepieces) verified and signed
Create Base — Create a new base with a specified table structure.
train-sentence-transformers · train-sentence-transformers verified and signed
Train or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder, dense or static embedding model for retrieval, similarity, clustering, classification, paraphrase mining, dedup, multimodal), `CrossEncoder` (reranker, pair scoring for two-stage retrieval / pair classification
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.