metadata
title: Datasent
emoji: 🟪
colorFrom: indigo
colorTo: blue
sdk: static
pinned: true
Datasent builds Polygen, an SDK that tokenizes numeric, image, text, audio,
and video data by fitting a compact basis to each window, with a lossless
x = f_x + r decomposition: the fitted prediction f_x plus the residual r.
The representation is small, structured, and decodes exactly.
Polygen for Qwen2-VL
Our flagship demo applies Polygen to a vision-language model: it compresses the visual tokens Qwen2-VL feeds to the LLM, and a small LoRA adapter teaches the model to read the compressed representation. On ScienceQA the recipe holds or improves accuracy while shrinking the visual sequence:
- +8.4pp accuracy over the un-spliced baseline at the accuracy tier (T=3)
- At the compression tier (T=2, +7.4pp accuracy): ~49% fewer visual tokens and ~3.7x (nearly 4x) more requests per GPU in cached serving
- ~5x smaller stored visual representation
The vision encoder and LLM weights are otherwise untouched; the compression sits between the merger and the LLM.
Try it
- Polygen for Qwen2-VL -- upload an image, compare answers with and without compression, scored per image
- Polygen RAG demo -- retrieval over a compressed visual-token corpus
- Polygen tokenization demo -- the core tokenizer
Models
- qwen2vl-polygen-7b-lora-r16-1000 -- 7B LoRA adapter
- qwen2vl-polygen-lora-r16-1000 -- 2B LoRA adapter
Learn more at datasent.com.