Train miniCOIL sparse neural retrieval models with per-word 4D projections.
npx skills add https://github.com/JoaquinCampo/Skills --skill minicoil-training
Please help me install this Agent Skill. Skill: minicoil-training Source: https://github.com/JoaquinCampo/Skills/tree/main/minicoil-training Command: npx skills add https://github.com/JoaquinCampo/Skills --skill minicoil-training
This Skill provides a comprehensive reference for training miniCOIL sparse neural retrieval models, enabling context-aware semantic search within inverted indexes.
Run a demo by loading the per-word linear layers and encoding sample text into a 4D sparse vector.
High-intent search queries and answers about installing and using this skill.
To train sparse retrieval models for inverted indexes, this Skill builds a 30,000-word vocabulary and learns per-word 4D projections using triplet loss. It outputs deployment-ready weights that augment inverted indexes with semantic context.
miniCOIL sparse neural retrieval works by training a tiny per-word linear layer that outputs 4D vectors. It uses semi-hard triplet mining to create distinct word sense representations, enhancing inverted index search with semantic awareness.
Yes, you need 512D input embeddings to train sparse per-word vectors with this workflow. The pipeline takes these 512D inputs and applies TripletMarginLoss optimization to project them down to a 4D output per word.
Yes, you can evaluate sparse retrieval models on BEIR benchmarks. The end-to-end training pipeline includes a BEIR evaluation step to test the performance of your newly trained per-word semantic vectors.
You deploy trained sparse vectors with Qdrant by using the generated weight and bias artifacts, word_layers.pt. These deployment-ready artifacts enable direct integration into your sparse-vector search backend.
A limitation of per-word 4D projections for sparse retrieval is that the training workflow is designed for English-only data. It also strictly requires a 30,000-word vocabulary and 512D input embeddings to function correctly.
Huzaifa4412Correct grammar and polish tone while preserving original meaning.
jayll1303Generate local embeddings and build retrieval-augmented generation pipelines with sentence-transformers and FAISS.
JoaquinCampoCreate sparse and hybrid collections in Qdrant using Python.
ccfSelect and optimize embedding models for semantic search and RAG applications.
