LateOn-hpool-regularized

About

What LateOn-hpool-regularized is

[](https://lighton.ai) [](https://www.linkedin.com/company/lighton/) [](https://x.com/LightOnIO) 📚 Collection | 📝 Blog Overview LateOn-hpool-regularized is a ColBERT-style multi-vector retrieval model trained by LightOn using PyLate. It is built on the LateOn family and regularized specifically to make hierarchical pooling much more effective. Late interaction models are powerful because they store one embedding per document token and score with MaxSim. The downside is index size: long documents require many vectors. We previously introduced hierarchical pooling to reduce this footprint by clustering and merging similar token embeddings inside each document. This model is trained so that such pooling preserves retrieval quality even at aggressive compression ratios. The headline result is simple: LateOn-hpool-regularized reaches 98.7% retention at a 32-token document budget, corresponding to roughly 5× compression, with negligible impact on full-token retrieval performance. This model is the recommended LateOn checkpoint when you want a versatile ColBERT that works well across all compression levels. It is trained with multiple pooling budgets ([4, 8, 16, 32, 64, 128, 300]) so you can set the compression ratio at inference time. If you know your deployment target, training specifically for that budget pushes retention even further (see Targeted Training below). If you only use full-token PLAID retrieval without pooling, LateOn or LateOn-regularized remain strong choices. For the complete methodology and analysis, refer to our blog post. Method Hierarchical pooling contains a discrete operation: cluster assignment. Tokens are merged according to a hierarchical clustering tree, and this assignment is not differentiable. To train through it, we use a Straight-Through Estimator. During training: 1. The model encodes query and document tokens normally. 2. Document token embeddings are hierarchically clustered and pooled in the forward pass. 3. Retrieval scores are computed on the pooled document representation. 4. The loss combines the standard full-token MaxSim loss with a pooled-representation loss. 5. During the backward pass, the Straight-Through Estimator lets g

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

How it works

How embedding models work

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys lateon-hpool-regularized for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (lateon-hpool-regularized below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/embeddings \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"lateon-hpool-regularized","input":"text to embed"}'

Details

Languages, data & research

Papers

Licence

Open weights

Sources

Weights & code

Explore

More embedding models